IMG.LY: Blog

Evaluating CoDesign MCP performance in resizing

Dustin — Fri, 21 Aug 2026 09:00:00 GMT

You designed a banner. The same day, you need it in five sizes, and none of them can be wrong.

We handed that job to six AI models through CoDesign MCP: take this approved design and rebuild it for five ad formats. All six came back with ads you could ship. Gemini 3.7 Flash did it for thirty cents and passed every check we wrote.

That is what CoDesign MCP is for. You point an AI assistant such as Claude at your approved design, name the formats you need, and it opens the file, rebuilds the layout for each one and exports production files. What comes back is an editable design file, not a picture of one.

Speed and price are the easy things to measure. We wanted to measure quality too, so we built an eval that runs the job automatically, opens every result and reports what passed. This is the first scenario out of that suite.

Three banners, one brief

Three different models were handed the same 320×50 slot, cut from the same master creative against the same brief, and all three came back with an ad you could traffic tomorrow. Every one of them keeps the wordmark and the button, nothing is clipped, and no type is set below 11px.

The 300×250 they came from carried five things: the wordmark, the headline, a retention chart, the offer line and the button. At 320×50 the wordmark and the button survive and the chart cannot, which leaves room for exactly one line of copy, so each model had to choose between the headline and the offer.

One dropped the headline and kept the offer, “14-day free trial”.
One kept the headline but cut “your users” down to “users” to buy itself the line.
One kept the headline whole across two lines and dropped the offer.

We have opinions about which of those reads best, the way any design team would. What we do not have is a way to prove one of them correct, because the choice depends on whether this campaign is selling the product or the trial, and that lives in the media brief rather than in the design. Our checks can confirm that all three are valid and that none of them are broken; they cannot tell you which one the campaign actually needed. Grading the half that has a right answer and leaving the other half to the people who own the brief is the distinction our evals are built around.

What is gradeable and what is not

The obvious thing to evaluate is the thing that demos well, prompt in and poster out, but we were more interested in the work that actually fills a designer’s week, which is mostly derivative. The design decisions were made once, at the master, and everything after that is a matter of carrying them faithfully into thirty other shapes. That is more technical work than creative work, which is exactly why it is worth handing to an agent.

Ask which of the finished designs is better and you have a question with no ground truth to appeal to, since human raters disagree with each other and LLM judges reliably prefer their own output. You could ask a lot of humans and rank the results, but that is not something you can run on every build. Wrong designs, though, are wrong in ways you can query: text sitting behind another block, content off the page, type under the legibility floor. Part of design quality is judgement and part of it is fact, and what we have built grades the second part, which means everything below is an automated result rather than a design review. A model can pass every check we wrote and still make an ugly ad.

What we are doing right now

When a model finishes a scenario, programmatic checks open the result and ask whether it is plausibly good. That starts with whether the run produced every design artifact and .imgly file at the right sizes, and the rest depends on the scenario: in a localization run we also check that the words were actually replaced.

This is a technical floor rather than a grade. LLM judges are still unreliable enough that we do not use one on output quality, because if it is hard for us as designers to say which design is more correct, it is harder for a model, and the result would be noise.

In the future we plan to experiment more with such methodologies but we also do not want to rely on the false security of an extremely noisy grading process.

The comparison view for the display-banner matrix: cost and time sitting directly above what each model actually produced. The 1/1 counts runs, one repeat per cell, not check scores.

One master, five ad sizes

The scenario is a display campaign, because that is the version of this problem customers actually have: the same size matrix, every campaign. The master is a 300×250 MPU for ATLAS, an imaginary product-analytics SaaS running a free-trial campaign, carrying a wordmark, the headline “See what your users actually do”, a retention bar chart labelled “43% retained”, the line “14-day free trial. No card.”, and a “Start free trial” button.

The 300×250 master at the top, and the four other sizes on the media plan cut from it. ATLAS is our own fixture, not a real customer.

The brief asks for the full matrix: 300×250, 728×90, 160×600, 300×600 and 320×50. Those sizes span a 16:1 swing in aspect ratio, so the right answer at each one is a genuinely different composition, and at some of them it means taking content out rather than shrinking it.

Ten checks grade the result and two of them do the real work. 728×90: the chart was dropped, not shrunk kills the model that squashes a bar chart into a 90-pixel strip, which satisfies every geometric constraint in the brief while being completely wrong. the five sizes are different layouts kills the model that scales one composition five ways and calls it a matrix.

The master first, then the six 728×90 leaderboards. Every model that delivered deleted the retention chart.

Every model that delivered arrived at the same composition, wordmark left, headline across the middle, offer underneath it, button on the right and the retention chart deleted, which is six models from five different vendors reaching the same answer independently. We did not expect that, and it is still the result we find hardest to stop thinking about.

The same six at 160×600, master first. With vertical room they all kept the chart. The flat format is where the decision to drop it had to be made.

Which model is best for using with CoDesign MCP?

#	model	checks	model spend	time	tool calls
1	gemini-3.7-flash	10 / 10	$0.30	6.7 min	37
2	glm-5.2	10 / 10	$0.40	8.2 min	25
3	gpt-5.6-sol	10 / 10	$0.52	4.0 min	35
4	grok-4.6	10 / 10	$1.20	20.9 min	39
5	claude-fable-5	10 / 10	$3.95	10.3 min	26
6	claude-opus-5	10 / 10	$3.97	18.8 min	40

Running this scenario illustrates general numbers across our eval suite. The 6 models above are consistently able to follow the prompts to produce different output designs as requested in the scenario. These numbers also highlight quite the spread in model costs and time spend. What you do not see in these numbers is that glm 5.2, gpt-5.6-sol and grok 4.6 are producing suboptimal designs in our opinion. They are valid, but subjectively fable, opus and gemini 3.7 consistently across runs and across scenarios perform simply better.

The biggest surprise for us is Gemini 3.7 Flash, which produced the whole five-size matrix for $0.30 in model spend, in under seven minutes. At thirty cents a designer opens six composed variants instead of a blank artboard and takes the best one further, which changes what the tool is for.

Meanwhile there were no surprises regarding Opus 5.0 and Fable 5.0, both models perform really well - but are slow and expensive.

What does it mean for CoDesign MCP

You can now resize a master design into 5 different sizes reliably for $0.30 using Gemini 3.7 Flash and the CoDesign MCP.

If you are on a Claude Subscription plan, you might just want to continue using your Claude Code with the CoDesign MCP since it offers the best overall design quality - even if it’s slow and somewhat expensive.

We will continue to work on upgrading and improving measurements of how well CoDesign MCP works with different models, looking into other scenarios like localization (translating and changing a design for a different locality and language) as well as rebranding existing design assets.

You can install CoDesign MCP at img.ly/codesign.

CE.SDK v1.80 Release Notes

Neslihan — Thu, 20 Aug 2026 00:00:00 GMT

CE.SDK v1.80 makes it easier to find the Android guidance you need, from first integration steps to core editing workflows. This release also includes reliability fixes and improvements across the SDK.

Let’s dive in!

Navigate Android Documentation More Easily

Android guides have been reviewed and reorganized across core workflows, including creating compositions and templates, importing media, editing with filters, stickers, and shapes, applying rules, inserting media, and exporting projects.

Updated navigation and guide links make it easier to move between related topics and find the guidance needed for each step of an integration.

→ Explore the Android documentation

Want to Move Even Faster?

Quick reminder: Mobile Starter Kits give you a complete, working editor project for Android that you can make your own. Start with a proven setup for your use case, then inspect and adapt every configuration, callback, and UI choice directly in your codebase.

You stay in control of when to adopt new capabilities, while keeping the editor experience tailored to your product.

More in v1.80

This release also includes improvements to keyboard shortcuts, tracking events, export handling, text editing, media workflows, and stability across Android, iOS, web, and the engine.

All improvements and fixes are available in the v1.80.0 changelog.

Thank you for building with IMG.LY.

AI Design Agents in 2026: Which One Fits Your Work

Jan — Mon, 17 Aug 2026 09:00:00 GMT

Most roundups of AI design agents rank the tools one to six. That only works if every reader wants the same thing. A developer wiring up app screens and a brand manager producing a campaign are not shopping in the same market, even though the same six products keep showing up in both their search results.

This survey sorts by the work instead. Two questions do most of the sorting: what you are making, and what you are left holding when the agent stops. If you want the wider tool category rather than agents specifically, we have compared the AI design tools built around prompt-first workflows.

We ran five of the six ourselves, on the same two prompts, and the findings below are what we saw rather than what the marketing pages say.

Disclosure up front. IMG.LY publishes this survey, and two of the six tools here have a commercial relationship with us: CoDesign is our own product, and Manus is an IMG.LY customer. Both entries say so where they appear, we assess both against the same criteria as everything else, and anything we did not test ourselves rests on public sources.

What counts as a design agent

Three tests separate agents from the wider AI design tool space. The tool must plan multi-step work from a single goal. It must execute design operations rather than only advising. Its output must be usable design work: files, screens, or code.

These tests exclude two familiar groups. Image generators such as Midjourney and Ideogram produce strong single images without planning or executing a task around them. Chat assistants configured with design prompts, such as Taskade’s design agent templates, return recommendations in text. Both are useful, but neither does design work on your behalf.

Six products meet that definition in August 2026. We work through the definition in more detail in What Is an AI Design Agent?

How we tested

One prompt per category, given identically to every tool in that category.

For the interface tools: design a three-screen onboarding flow for a habit-tracking app, the screens in order being a welcome screen, a goal-setting screen, and a first habit formation screen, styled clean, high contrast, large type, one accent color.

For the graphic design tools: a launch campaign for a cold brew called Northwind, in three formats, an Instagram post, a story, and a DIN A5 flyer, warm and minimal, cream background, one product photo, headline supplied.

Two things decide it, and neither is how good the first draft looks.

Is the agent context aware? Can you feed it data, make it familiar with your brand, and does it hold that across every variant? We do not much care how fancy the design is. The table stakes have to be right before anything else counts.

And does it fit the habits you carried over from the before-AI age? Making a small revision by going back and prompting an AI again is the wrong shape. You want to be the human in the loop who makes that edit manually, because by the time you are prompting for the third time your frustration is already high enough that you have stopped wanting to.

One caveat on the Figma run, since it cuts against us: it executed the prompt inside IMG.LY’s own design system, so its icons, fonts, and patterns inherit work our designers had already done. That makes the head-to-head somewhat unfair in Figma’s favor.

Manus is the exception. We have not run it hands-on, and its entry below rests on public sources.

What you hold afterward

Generation quality converges fast. Every tool here produces a credible first draft, and the differences narrow every quarter. If you want to see where the underlying models differ, we benchmark 15 of them against the same design prompts.

What you keep does not converge. Some tools hand you a file inside an editor where you can select any element and change it. Others give you an export to finish in a different program. The rest keep the work inside their own platform, editable there and nowhere else.

AI design agents for app and web interfaces

Screen design has the most mature agent tooling, partly because UI has structure a model can reason about and partly because the output can be code.

Google Stitch

Stitch is a free experimental tool from Google Labs that generates multi-screen mobile and web interfaces, plus frontend code, from text or image prompts. It launched at I/O 2025 and gained Gemini 3 and interactive prototype flows in December 2025.

You describe an app and Stitch plans the screens, which you refine through further prompts. Screens render in the browser, with code export for the web stack and a paste-to-Figma path that preserves layers. Stitch has no source format of its own, so you can only keep editing in the exported code or the Figma file it hands off to. Reviewers recommend exploring in Stitch and refining elsewhere.

On our onboarding prompt it did not adhere to the brief. Habit formation came before goal setting, so the screen order was wrong. Button styles were somewhat inconsistent, the look and feel differed between screens, visible in the progress indicator on the welcome screen against the one on goal setting, and the aspect ratios were weird.

Editing is where it separates from Figma. Double-clicking does let you change the text, but you are apparently supposed to edit with AI, which is a nuisance when you only want to make a few design fixes. The brand kit is the part we liked: colors, accent colors, fonts, and spacing can all be changed globally. Though it looked like Stitch did not adhere to its own system that well.

It is free while in Google Labs. Google does not publish the generation caps, and third-party sources describe the limits inconsistently. Best fit is getting a first version on screen fast, especially for developers who want screens and starter code in one pass. Its Labs status makes it a tool to explore with rather than build a production process on.

Figma Agent

Figma’s agent works directly on the design canvas. It entered beta in May 2026 and gained custom skills, web search, and external MCP connections at Config in June 2026.

You prompt from any layer. The agent executes multi-step tasks: bulk edits across screens, dark-mode conversion, populating designs with real content, turning feedback threads into revisions. Custom skills written as markdown steer how it works.

Output is native Figma layers with components, variables, and design tokens preserved. This is the strongest design-system integration of the six, because the agent works inside the system your team already maintains rather than approximating it. Code generation routes through Figma Make, a separate product.

On our onboarding prompt it executed almost perfectly. The design was very clean, it adhered to the standards of modern apps, and it almost looked like something you would find browsing the App Store. Even the copy was decent, and it did not read like AI slop. The screens looked thought through: asked for a primary goal, it offered routines, breaking a bad habit, and staying consistent, which are the broad categories without too many assumptions on top. It stuck to the screen order, it baked in some interactivity, and it caught small details like “remind me every day at 8 a.m.” on the habit formation screen. As a novice you could take this and start prototyping.

Remember the caveat above, though: this run inherited IMG.LY’s design system, so the icons, fonts, and patterns were already good before the agent started.

The agent is free during beta, and Figma has said AI credits will apply at general availability without publishing amounts. It requires a full seat on Professional, Organization, or Enterprise; full seats start at $16 per person per month on the annual Professional plan. Early reviews report rough edges, including responsive layouts that broke on mobile.

In the head-to-head, Figma beat Stitch by a wide margin, which was to be expected.

Best fit is product and UI teams already working in Figma with an established design system.

AI design agents for marketing and brand assets

In campaign work you are producing dozens of assets at once, they all have to stay on brand, and some of them have to survive contact with a printer.

Lovart

Lovart is a dedicated design agent that turns a brief into a coordinated set of deliverables: logos, posters, packaging, social assets. It launched publicly in July 2025 after a closed beta that drew several hundred thousand users.

Give it a campaign-level brief and it analyzes intent, researches references, then generates dozens of assets sharing one visual system. You and the agent iterate on ChatCanvas, an infinite canvas where you both edit the same design through conversation. Results land as layers with typography kept separately, and Lovart offers targeted element and text edits in place.

On the Northwind campaign it was fairly quick, and the result was very aesthetically pleasing. We had very little to quibble with. The design subtleties were there, the product placement, the coffee beans, some cloth, and it stuck very well to the specification. Exactly what we had in mind.

The one quibble is brand drift. Look at the logo, look at the bottle, and there is significant drift in brand identity across the three formats. That is fixable in a real scenario, because you can link a brand, so you would have the product image and the logo ready and we would not expect much trouble then, whether you use Lovart to create variations, produce marketing material to A/B test, or adjust for different formats.

Editing is the problem. Ask to change the headline text and you cannot tell whether you are even looking at the same font. Quick edit means writing another prompt. There are no layers, and there is nothing you can do directly. So while the output looks nice, for revision work it is effectively useless.

Reviewers report that precise pixel-level work tends to move into Photoshop or Figma anyway, which matches what we found.

Pricing runs on credit tiers from Starter to Ultimate, 2,000 to 27,000 credits per month. Lovart renders prices dynamically and third-party reports of the dollar amounts vary between roughly $15 and $90 monthly, so check the pricing page directly. Credit consumption is hard to predict on agent-driven tasks.

Best fit is marketing teams whose unit of work is the campaign rather than the asset, and who accept a finishing pass elsewhere.

Canva AI Assistant

Canva’s assistant plans and executes design tasks by calling Canva’s own tools. It launched in April 2025 and received a tool-calling rebuild, announced as a research preview, in April 2026.

It runs multi-step jobs such as producing a multi-channel campaign, and pulls context from connected sources including Slack, Gmail, Google Drive, and Notion. Scheduled tasks run in the background, with finished work arriving as drafts for review.

Output is layered, fully editable Canva designs across presentations, social posts, documents, and spreadsheets. You can change any element without regenerating. The constraint is Canva itself. The work stays editable inside Canva, and getting it out means exporting.

On the same Northwind prompt it was fairly quick, and it appears to match the brief against the vast template library Canva already has. From the get-go, though, it did not really stick to the specification. We asked for a cream background and one product photo. There is no cream background on the first asset, and we do not know why the product would be displayed on a laptop, which is plain weird. Only the last of the three is anywhere near acceptable.

We also had no indication of whether it generated variations or ignored that part of the brief. Opening one of the designs gives you more variations, including the one you did not select. What you do not get is a multi-page layout you can change, or any way to specify changes precisely. At that point you are simply inside Canva, editing.

As a starting point we would have been just as well off picking one of the Canva templates, uploading the product image, and adjusting the text. Compared with Lovart on the identical brief, Canva really does fall short.

The assistant is available on the free tier with rate limits and monthly credits. Pro is $18 monthly. Business is $25 per user monthly with larger allowances. Reviewers warn that letting the assistant run a job end to end uses premium credits faster than editing by hand.

Best fit is teams already on Canva who want campaign production handled conversationally with brand kits applied automatically.

IMG.LY CoDesign

Disclosure: CoDesign is made by IMG.LY, which publishes this survey.

CoDesign is a free local MCP server that gives an agent you already use a full design engine. It entered technical preview in June 2026.

Instead of going to CoDesign, you install it into your own agent with one command, and the agent then performs design operations in conversation with you. IMG.LY documents the install for Claude Code and Codex, and any client that can run an MCP server locally works the same way. CoDesign can generate, rebrand, resize, edit, localize, import, and judge, the last checking a design against your brand rules. A representative chain: import a PSD, rebrand it, resize it to a dozen formats, check it against the rules, export.

Output is a structured scene rather than a flat image. It opens in an editor where you select any element and change it without regenerating anything. Underneath is CE.SDK, IMG.LY’s production design SDK. It imports PSD, IDML, PDF, and PPTX, and exports PDF with CMYK, bleed, and ICC profiles when a printer needs them. The agent, your code, and a human editor all work on the same file.

We ran the Northwind prompt through Claude Code. Before touching the canvas it asked where the product photo should come from, what accent color to use, what kind of cream we meant, and it drafted the copy for approval. In normal use you would run this inside your marketing documentation and brand assets, so your coding agent already carries a pile of context and can answer most of that itself. We gave it no brand context at all, to keep the comparison fair with the others.

It left us waiting a bit longer, though that is not quite fair to say, since it works in tandem with the coding agent. It was thorough and diligent. It ran a self-check against a set of axes before handing the design back, and because we supplied no brand context those came back blank. It passed, and returned one editable master file.

When it needed the product image it opened the IMG.LY dashboard, where the AI Gateway picked the model for it and credited the generation, which was frictionless.

The design that came back is fairly conservative and does not assume too much: some copy, “now pouring, limited first batch”, a CTA. Fairly bare bones, but it works. What matters is that it stuck perfectly to the specification. The square asset, the story asset, and a PDF carrying its color space and a resolution we could hand to a printer. Edit one element, tell it to regenerate, and it propagates: same colors, same logo, same product image across every variant.

All three formats came out of a single master file, generated in one pass from the same brief:

The local server is free to install and run with no account needed to start. An optional free account adds AI image generation, which routes out through IMG.LY’s AI Gateway. Paid licensing applies when you host the server for other people or embed it in a product.

Best fit is anyone running an agent-first local workflow who needs production-grade editing, print-ready files, and brand consistency across every variant. As a technical preview it is early, and behavior can change between releases.

Delegating design inside a larger task

Manus

Disclosure: Manus is an IMG.LY customer. This is also the one entry we did not run ourselves, so unlike the five above it rests on public sources rather than hands-on testing.

Manus is a general-purpose autonomous agent with a design workspace inside it. Design is one capability among research, app building, and document production.

Manus decomposes a goal into subtasks, browses for context, runs for long stretches without supervision, and continues while you are offline. For design work it researches before designing, then produces assets you refine through object-level edits: click an element to change colors, swap a background, or reshape it, without regenerating the whole asset.

Output covers images, video, 3D assets, and presentations. Its public documentation does not describe a layered source file of the kind a dedicated design tool exposes, so you edit objects rather than a design file. General agents are closing the gap on design output faster than anything else in this survey.

The free tier includes 300 daily refresh credits. Paid plans run $20, $40, and $200 monthly for 4,000, 8,000, and 40,000 credits. Reviews describe unpredictable credit burn on complex tasks.

Best fit is founders and operators who want one agent handling research, documents, and adequate design output, and who value autonomy over design-tool depth.

Which tools leave you a real editor

Three tools in this survey give you a real editor after generation. Figma Agent puts native layers on the Figma canvas. Canva’s assistant produces fully editable Canva designs. CoDesign returns a structured scene that opens in a full editor. In all three you select an element and change it, instead of rewriting the prompt and hoping the next version keeps the parts you liked.

Lovart sits between. It has a canvas and in-place editing, and precision work still tends to finish in Photoshop. Stitch hands off to Figma or to code. Manus edits at the object level, which suits an agent whose remit is much wider than design.

Revision takes longer than the first draft, and tools that keep you in control of the file absorb those cycles.

Destination app or capability in your stack

Five of the six tools here are destinations. You open Figma, Canva, Lovart, Stitch, or Manus, do the work there, and take the result away. That model is familiar and it works.

The sixth, CoDesign, is a design engine that installs into the agent you already use, so the design step happens inside your existing workflow.

That split is narrower than it first appears. Figma opened an MCP server in March 2026, so external coding agents can drive its canvas. Canva shipped an MCP server in February 2026 that exposes design generation inside ChatGPT, Claude, and Microsoft Copilot, and says more than 12 million designs have been created that way. Being reachable from your agent is not unique to CoDesign.

The tools differ in what they hand back. Drive Figma’s MCP and you get a Figma file, which is useful if your team lives in Figma. Drive Canva’s and you get a Canva design. Drive CoDesign and you get a portable scene file, PDF with CMYK and bleed, PSD and IDML import, and no platform you have to keep an account with. For teams whose output ends at a printer or inside their own product, that portability decides it. It matters much less if your work already lives in Figma or Canva.

How to choose

Start with what you are making. UI and app screens point to Stitch for speed or the Figma Agent for depth. Campaign and brand assets point to Lovart for volume from one brief, Canva for teams already there, or CoDesign for output that has to stay editable and reach print. If design is a side task inside something larger, Manus covers it.

Then check the exit path before you commit, because it is the part you cannot change later. Ask where the file lives, whether you can edit it without regenerating, and what happens when it needs to leave the tool.

Frequently asked questions

What is an AI design agent?

An AI design agent plans and executes multi-step design work from a goal, producing usable design output such as files, screens, or code. What Is an AI Design Agent? goes into where the line falls.

How is an AI design agent different from an image generator?

An image generator returns a picture for a prompt. An agent plans a sequence of steps, performs design operations, and produces work you can carry forward.

Are AI design agents free?

Three of the six have a free way in: Stitch while it is in Labs, Manus on its free tier, and CoDesign’s local server. Figma’s agent is free during beta but needs a paid seat. Lovart and full Canva use are subscriptions.

Do AI design agents replace designers?

No. Every tool in this survey keeps a person reviewing the output, and all six advertise editing after generation.

Which AI design agents produce editable files?

Figma Agent, Canva’s assistant, and CoDesign keep element-level editability in a design file. Lovart offers in-canvas editing, though external finishing is common. Manus edits objects in place. Stitch relies on its Figma and code exports.

Can I use a design agent inside Claude or ChatGPT?

Yes, through MCP. Canva exposes design generation in ChatGPT, Claude, and Copilot. Figma opened its MCP server to external coding agents. CoDesign runs as a local MCP server in coding agents such as Claude Code and Codex.

Introducing IMG.LY AI Benchmarks

Jan — Mon, 03 Aug 2026 00:00:00 GMT

IMG.LY GenAI Benchmarks is live. 15 text-to-image models, 37 prompts taken from real design jobs, three fixed seeds each, 1,662 generated images, roughly 7,400 scores. Every prompt, every score, every generated image and the full methodology are public.

Why we ran it

Our customers embed image generation in products that ship physical, commercial output. Web-to-print storefronts, merch platforms, campaign tooling, template systems. When they asked us which model to use, the honest answer was a shrug and a link to a leaderboard that measures something else.

The existing arenas rank aesthetic preference by crowd vote. That’s a signal, sure, but not the one most relevant to these use cases. They want to know whether the image has a real alpha channel, or whether users got the hex they asked for and whether a word is spelled right. A 10,000-piece personalization run needs to hold the character across every variant. Those are the failures that cost you a reprint or a support ticket, and none of them show up in a preference ranking.

So we built the one that answers our customers’ question. Which model should you build on for production design work.

Why some of it is judged, not measured

Plenty of what matters here is measurable, and we measure it. Native output size, wall-clock latency and price per image come straight off the run. Transparency is a file-level check for a real alpha channel rather than a painted-on white rectangle. Color accuracy is the CIEDE2000 distance between the hex the prompt required and the color that came back.

The rest needs a judgment call. Whether an image satisfies “three blue cubes stacked on the left and one red sphere on the right” is a checklist, and something has to look at the picture and tick it off. Whether a banner leaves a clean area for a headline has a right answer, but not a computable one.

For those criteria a vision model does the judging, against a checklist written per prompt before the run. We added two rules to make the VLM’s judgment more transparent and control for arbitrariness. Every judgment records a written rationale beside the score, so you can read why an image lost a point and tell us we’re wrong. The criterion that really does need a person, design-readiness, the “would a professional ship this with under five minutes of cleanup” question, is surfaced to a human in the loop (that would be yours truly, the author).

The rest of the protocol is the boring part that makes the numbers worth anything. Identical prompts for every model, default parameters, fixed seeds, no per-model prompt tuning ever, a versioned suite, and published scores that are never quietly restated. Partner models get no special treatment, and the Gateway links stay well away from the rankings.

Why we split it by use case

Average our eight criteria with equal weight and Nano Banana 2 Lite leads at 3.87 out of 5, while last place, at 2.55, goes to Nano Banana Pro, the most expensive flagship in the set. That’s not a data error. Nano Banana Pro has the best brand-color fidelity in the field and renders every required string in the suite exactly. It also costs 28 times more per image than the cheapest model and takes 23 seconds. An unweighted average treats all of that as equally important, so it buries the model with the best output.

This is the chart everyone asks for, and its vertical axis is the number you should not rank on. Explore the live, interactive version, where every point links to that model’s scores.

Which is what leaderboards do. So we publish the same measurements per use case as well, with a weight matrix per job and the reasoning behind each matrix written out. Print files weight resolution and color heavily, because a 1024px generation is a 3.4-inch print and an out-of-gamut red is a reprint. Personalization at scale weights cost and adherence, because unit economics decide the run. Merch weights the alpha channel above everything else, because a sticker without a clean cutout isn’t a sticker.

Same numbers, different question, different answer. That’s why the section opens by asking what you’re building instead of handing you a ranked list.

The result that surprised us most

Reweighting moves models the length of the table.

GPT Image 1.5 sits twelfth of fifteen on the unweighted blend, dragged down by cost and latency. Reweight for merch and stickers, where transparency carries 35 percent of the matrix, and it wins outright at 3.72, nearly a full point clear of second place. It’s the only model in the run that reliably returns a genuine alpha channel. Thirteen of the fifteen return none at all, and a few paint a fake checkerboard into the pixels, which looks like transparency right up until it reaches a printer.

On a general leaderboard, the best model for one of our customers’ most common jobs reads as a mid-table also-ran. That’s the argument for the whole project.

The typography column surprised us a second time. Ideogram has the strongest public reputation for rendering text, and in our run it ranks twelfth of fifteen on measured text accuracy, behind several general-purpose flagships that now render every required string in the suite exactly. Route typographic work to a specialist on reputation alone and you can end up with worse type than the model you already call by default.

Two more capability gaps got written up as standalone findings. Brand color, where the best model manages 3.67 out of 5 and most of the field sits below 3. And consistency, where no model holds a described character across three scenes and the ceiling is 3.89.

What this means for an editor

We build editors, so our conclusion isn’t neutral. The data still points where it points.

Read the four findings together and they describe the same problem four times. The cut-out is missing, the color is close but not the color in the brand book, the headline is right until it isn’t, and the character drifts between scenes. None of these are bugs waiting on the next model release. They’re what generation is, a probabilistic first draft. Getting from that draft to something a customer can order takes a handful of deterministic corrections, and somebody has to be able to make them.

That’s an editor’s job. Background removal and edge cleanup close the transparency gap. Brand kits and exact color values close the color gap. Editable text layers turn a wrong character into a two-second fix instead of a regeneration. Reusable assets and templates carry identity that regeneration won’t. Our AI Editor gives your users those controls over whatever model produced the image, and the AI Gateway makes routing per job, which the data says you should be doing, a config change instead of another integration.

We’d rather make that case with numbers anyone can check, including the ones that make models we partner with look bad.

Caveats, and what’s next

This is a pilot dataset. Quality criteria are judged by a vision model, not yet by the blind expert panel, and design-readiness isn’t scored at all. The weight matrices are provisional. When the frozen suite lands, scores restate once and the suite version changes; after that, nothing gets restated without a clearly labeled new methodology version.

The roster will grow. Image editing and video are the obvious next modalities, and we plan to re-run the suite whenever a notable model ships.

Go pick a use case and see which model wins your job. If the numbers disagree with your own experience, the prompts and the raw images are all sitting there, and we’d like to hear about it.

CE.SDK v1.79 Release Notes

Neslihan — Thu, 30 Jul 2026 00:00:00 GMT

CE.SDK v1.79 brings professional video transitions for web. Plus a round of fixes and refinements to the features you already rely on.

Let’s dive in!

Add Transitions Between Video Clips

The web video editor now supports clip-to-clip transitions.

Add one between two clips on the timeline. Pick a type from the library and tune it with a live preview.

Stay fast, too: apply or remove transitions across a whole track at once.

Out-of-the-Box Transitions

The catalog covers cross fade, cross blur, wipe, push, slide, and more.

The audio of video clips cross-fades automatically. This saves your users an extra editing step, for an elegant outcome.

→ Try it in the Live Demo
→ Apply Transitions Documentation (Web)

Changelog

All improvements, breaking changes, and fixes are in the v1.79.0 changelog.

Thank you for building with IMG.LY.

CE.SDK v1.78 Release Notes

Neslihan — Tue, 21 Jul 2026 12:00:00 GMT

CE.SDK v1.78 is a typography and reliability release. It adds a dedicated path control for curved text on the web, alongside a broad set of engine and editor fixes across web, mobile, and backend.

Let’s dive in.

More Expressive Typography

Curve Text with a Dedicated Path Control on the Web

The web editor gains a Path control for text blocks. Users can place text on a curve using Circle, Arch, and Wave presets, then adjust position, direction, and offset directly in the inspector.

For custom shapes, Edit Path lets users draw their own baseline instead of picking a preset, so text can follow whatever curve a design calls for. This builds on the text-on-path support added in v1.77.

→ Edit Text Documentation (Web)

Improvements

Keep Edited Text Above the Mobile Keyboard

On mobile web, the canvas reserves space for the on-screen keyboard and pans to the text cursor, so the text being edited stays visible while typing.

Browse Typefaces Smoothly on Slow Networks

The web typeface library shows font names immediately and loads previews lazily as rows scroll into view, keeping the picker responsive on low-end devices.

Refresh iOS Asset Libraries Automatically

On iOS, an open library updates in place when its source’s contents change, matching the web editor.

Stability and Fixes

This release includes a broad set of stability, performance, and rendering fixes across the engine and editors. Among them: a Safari video-export fix for projects that contain uploaded video, faster handling of large caption files, curved-text caret and selection fixes, iOS effect-sheet and web keyboard-accessibility fixes, and archive-loading crash guards. See the changelog for the full list.

Changelog

All improvements, breaking changes, and fixes are in the v1.78.0 changelog.

Thank you for building with IMG.LY.

CE.SDK v1.77 Release Notes

Neslihan — Wed, 01 Jul 2026 00:00:00 GMT

CE.SDK v1.77 is a workflow, typography, and platform release focused on making editing faster, more expressive, and more flexible across web, mobile, and backend environments.

This release brings keyboard shortcuts and better typeface discovery to the web, expands text styling and editing workflows on mobile, and improves performance for large photobook-style scenes. Lastly, you can add a branded photo camera to mobile!

Let’s dive in.

Create and Edit Faster

Speed Up Editing with Keyboard Shortcuts

CE.SDK now ships with keyboard shortcuts in the web editor, with 30 shortcuts out of the box for selection, editing, text formatting, zoom, undo, and playback.

Need something custom? Register your own through the cesdk.shortcuts.set API with single keys, modifier combinations, or multi-step sequences. Each shortcut can be scoped to a specific part of the UI so it only fires when it should.

Users can move faster without leaving the canvas, with shortcuts that match the tools they already know.

→ Keyboard Shortcut List & Documentation

Find the Right Typeface Faster

The web editor now comes with typeface browsing. Users can search, filter, and navigate typefaces more easily, making large font libraries feel more structured and easier to manage.

For your product, this means: a more polished typography experience without needing to build your own font discovery UI.

→ Customize Fonts Documentation

More Expressive Typography

Shape Text Around Paths for Web & Mobile

CE.SDK now supports text on curves, including the APIs and layout behavior needed to place and render text along circular and curved paths.

This opens up more expressive typography workflows for logos, badges, invitations, and other layout-driven designs. Now available for Web, iOS & Android.

For your product, this means: users can create more flexible text layouts directly in the editor instead of switching to external design tools.

Edit Text Documentation:
→ Web
→ iOS
→ Android

Bring Richer Text Workflows to Mobile

This release also expands how text is created and styled across iOS and Android.

Text and paragraph style presets are now available on iOS and Android. Apply and reuse consistent text styles without restyling everything from scratch.

Inline text run editing is also new. Select part of a text block and style just that portion, without affecting the rest.

Have More Control over Text Layout APIs

CE.SDK v1.77 also extends text positioning and layout capabilities through engine APIs.

This makes advanced text placement, alignment, and layout behavior easier to control in integrations that need more precise typography handling, including multilingual and design-heavy workflows.

→ Upgrade to v1.77

Mobile Creation Workflows

Remove Image Backgrounds on iOS and Android

Background removal is now available on iOS and Android. The same plugin your web editor uses, now on mobile.

For your product, this means: users can remove image backgrounds without leaving your app, on any platform you ship on.

→ Android Background Removal Documentation
→ iOS Background Removal Documentation

Add a Photo Camera to iOS and Android

Photo Camera is now part of CE.SDK on iOS and Android. Users capture photos and videos, then move straight into editing — all inside your app.

Useful for listing flows, content creation, document capture, or any mobile workflow where capture and editing need to feel like one thing.

For your product, this means: one less integration to manage, and a creation flow that stays inside your product. From taking a photo to a finished edit.

→ iOS Camera Configuration Documentation
→ Android Camera Configuration Documentation

Improvements

Import Richer Documents With Higher Fidelity

Our importer packages now preserve more of the structure and styling that matter in real-world design files.

PDF importer now keeps inline-styled text together as a single editable block while preserving mixed weights, styles, and colors.
PSD importer now supports Photoshop stroke layer styles and improves fallback behavior for off-canvas text.
PPTX importer now imports text decorations and nested lists. This includes your Canva designs exported as PPTX.
IDML importer can now import embedded PDF and Adobe Illustrator graphics as editable blocks instead of placeholders.

Imported content stays more editable, more faithful to the source, and requires less cleanup after import.

→ Explore Importer Demos

Export Print PDFs with Transparency & Vectors

Print-ready PDF export now supports PDF/X-4, preserving live transparency and vector text for more faithful, standards-compliant print workflows.

Handle Large Photobook Projects More Smoothly

We improved performance for large, image-heavy scenes such as photobooks and other complex multipage projects, reducing bottlenecks and keeping editing workflows more responsive as scene complexity grows. Users can smoothly work on and scroll through larger projects.

→ Explore Photobook Solutions

Developer Experience

Extend Your Mobile App with Plugins

This release makes it easier to extend your mobile app with add-on features and more customizable editing flows on iOS and Android.

Build more tailored mobile editing experiences with options like:

adding background removal on iOS and Android
integrating AI image generation on iOS and Android
building custom Android plugins to extend editor behavior
packaging mobile features as reusable plugin modules that are easier to integrate and maintain

→ iOS Background Removal Documentation
→ Android Background Removal Documentation
→ Android Custom Plugin Documentation
→ iOS AI Image Generation Documentation
→ Android AI Image Generation Documentation

Make Error Handling Easier to Understand

We improved error reporting with structured errors and better surfacing through bindings, making integration issues easier to diagnose and handle.

Update to Node.js 22

Node.js 22 is now the minimum supported version. Node.js 20 stopped receiving security updates in April 2026, so we strongly recommend upgrading to a supported version.

Changelog

All performance improvements, breaking changes, and fixes are in the v1.77.0 changelog.

Thank you for building with IMG.LY.

The Best GenAI Models for Web-to-Print: A Buyer's Guide

Jan — Fri, 26 Jun 2026 00:00:00 GMT

No single generative model is “best” for web-to-print. The right pick depends on the specific job, and print has jobs that screen-first leaderboards don’t measure. A model that tops a general image-quality benchmark can still be useless for print if it can’t render legible text, can’t output vector, or shifts hard out of CMYK gamut.

This guide gives you the criteria that actually matter for print, a scoring rubric to apply them, and a model-by-model read on where each one wins. The goal is to route each task to the model that fits it, which is why a model-agnostic (“bring your own model”) integration matters more than any one provider’s marketing.

How to read this guide. The criteria and rubric are the durable part. The model roster moves monthly: treat the specific model notes as a snapshot, and re-run the rubric against current versions before you commit. The per-model benchmark scores come from IMG.LY’s GenAI benchmark suite, which is now live: a pilot dataset you can explore today, re-run whenever new models drop. The gated PDF report that packages the weighted per-use-case totals and the full test set is the piece we’re opening to early-access subscribers first (sign-up at the end of this guide).

Why print needs its own criteria

A web-to-print product sells a physical object. That changes what “good” means:

The output is measured at 300 DPI on a substrate, not at 72 PPI on a retina screen.
Color is CMYK and spot, not sRGB.
Logos and type must scale and stay crisp: vector, not pixels.
The customer is a non-designer, so the model has to be controllable enough to stay inside a template.
And because it’s a commercial product sold to a customer, the licensing of the output carries real legal exposure.

General benchmarks (LMArena-style human preference, aesthetic scores) miss most of this. The eleven criteria below are built around it.

The eleven evaluation criteria

1. Output type and format: raster vs. vector

Why it matters for print: Logos, icons, line art, and type need to scale to any size and print crisply. Raster can’t; vector can. A model that outputs (or can be cleanly traced to) native SVG / vector is uniquely valuable for the print-specific elements that screen apps don’t care about.

What to test: Can it produce vector natively? If not, how cleanly does its output vectorize? Does the vector survive into PDF/X as real paths?

2. Resolution and maximum dimensions

Why it matters: A ~1024px generation is ~3.4” at 300 DPI. Large-format and even A4 need far more. Native max resolution, and how well the model holds detail when upscaled, determines whether you can print the output at size without a quality penalty.

What to test: Native max output dimensions; detail retention at 4×/8× upscale; effective printable size at 300 DPI.

3. Visual quality and fidelity

Why it matters: The baseline. Realism, coherence, absence of artifacts, anatomical and structural correctness. Crucially, how it holds up under print’s unforgiving close inspection: banding, mushy detail, and plasticky textures show more on paper than on screen.

What to test: Side-by-side preference on print-representative prompts; artifact rate; detail at print scale.

4. Text and typography rendering

Why it matters: Print is full of words, and most models garble text inside images. For anything where text-in-image is unavoidable (a generated poster, a label motif), legibility and kerning are make-or-break. Best practice is still to set real type as a separate layer, but some jobs need it baked in. Our text-reliability finding measures exactly this. The top of the field has largely solved Latin headlines: three models rendered every required string in our suite exactly. Small type and non-Latin scripts have not been solved, and the model most famous for typography ranks twelfth of fifteen. One wrong character still means regenerating the whole image, which is the real argument for keeping type on its own layer. Compare every model on the same wordmark prompt to see the spread.

What to test: Legibility of short and long strings; correct spelling; kerning; multi-line; non-Latin scripts.

5. Prompt adherence and controllability

Why it matters: Non-designers need predictable results, and templates need the output to land where it’s told. Controllability spans prompt adherence, image-to-image / inpainting / outpainting, style and reference-image conditioning, and seed stability for repeatable results.

What to test: Does it honor constraints? Quality of edits (generative fill, expand, object removal)? Reference-image fidelity? Same-seed reproducibility?

6. Color accuracy and CMYK-readiness

Why it matters: Vivid RGB outputs clip hard in CMYK and shift on press. Models that stay closer to printable gamut, and outputs that convert predictably, mean fewer surprises and less soft-proofing friction. Even before the CMYK conversion, hitting an exact brand hex in RGB is hard: our brand-color finding measures color accuracy with CIEDE2000 against the required hex, and no model reliably lands the color in your brand book.

What to test: Gamut coverage vs. CMYK; shift magnitude after ICC conversion; behavior on brand-critical colors and near-whites/blacks.

7. Transparency and background handling

Why it matters: Merch, stickers, die-cuts, and product compositing need clean subjects on transparent backgrounds and accurate edges (hair, glass, fine detail). Native transparent output and clean cutout edges save a manual masking step. In the models themselves this is close to unsolved: our transparency finding shows 13 of 15 tested models emit no real alpha channel at all, which is exactly why a background-removal step belongs in the pipeline rather than a prayer that the model returns a clean cutout.

What to test: Native alpha output; edge quality on hard cases; cutout-path readiness.

8. Responsiveness / latency

Why it matters: Two very different bars. In an interactive editor, anything over a few seconds breaks flow. In a batch/VDP run, throughput and concurrency matter more than per-image speed. The right model differs by context.

What to test: P50/P95 latency at your resolution; throughput under concurrency; cold-start behavior.

9. Cost per generation

Why it matters: Unit economics. A few cents per image is invisible for interactive one-offs and brutal across a 100k-recipient VDP run. Price has to be weighed against quality for the specific job. You don’t pay flagship prices for a draft thumbnail.

What to test: Cost per image at your resolution/step settings; cost of edit vs. generate; volume pricing.

10. Consistency and repeatability

Why it matters: Brand work needs the same input to yield the same (or controllably similar) output, and product likenesses must not drift. Seed control, character and style consistency, and low variance separate “brand-safe” models from “slot-machine” ones. Our consistency finding puts numbers on the drift: no model holds a described character across scenes, so identity has to come from templates and editing, not from a regeneration lottery.

What to test: Variance across runs at fixed seed; character/style consistency across a set; drift on iterative edits.

11. Commercial licensing and IP safety

Why it matters: You’re selling the printed output. Commercial-use rights, training-data provenance, indemnification, and content/safety filtering are legal exposure, not fine print. A model that’s brilliant but legally murky is a non-starter for a product customers resell.

What to test: Commercial-use terms; indemnity; provenance/transparency; enterprise and data-handling terms; content-filter behavior.

The scoring rubric

Score each model 1–5 on each criterion, then weight by your use case. Suggested weights for the three most common web-to-print contexts:

Criterion	Interactive design tool	High-volume VDP / automation	Merch / POD
1. Vector / SVG output	High	Medium	Medium
2. Resolution / max size	High	High	High
3. Visual quality	High	Medium	High
4. Text rendering	Medium	High	Medium
5. Controllability / editing	High	High	High
6. CMYK-readiness	High	High	High
7. Transparency / cutout	Medium	Low	High
8. Responsiveness	High	Medium (throughput)	High
9. Cost per generation	Medium	High	Medium
10. Consistency	Medium	High	High
11. Licensing / IP	High	High	High

Scoring scale: 1 = unusable for print · 2 = weak · 3 = workable with mitigation · 4 = strong · 5 = best-in-class.

Drop your own numbers into this rubric. The measured scores in the results table later in this guide give you a starting hypothesis to test; the qualitative notes are not a substitute for your own runs on your prompts.

Models by job

New models ship faster than any ranking can keep up with, so this section is organized by job, the way you actually route requests. Models are drawn from the roster currently wired into CE.SDK’s AI plugins.

Job A: Text-to-image (generate a new asset)

Candidates: Recraft V3, Recraft 20B, Seedream V4, Nano Banana, Nano Banana Pro, GPT Image 1, Ideogram V3.

Model	Stand-out for print	Watch-outs	Benchmark
Recraft V3	The print specialist: native vector/SVG generation, strong text rendering, brand-style controls. Often the single most print-relevant text-to-image model.	Verify max raster resolution for large-format jobs.	3.29 / 5
Recraft 20B	Faster, cheaper Recraft tier. Good for interactive iteration before a final Recraft V3 render.	Quality step-down vs. V3.	not yet in the suite
Seedream V4	High visual fidelity and resolution; strong general-purpose hero imagery.	Text rendering and vector are not its strength.	3.80 / 5 (measured on Seedream 4.5)
Nano Banana / Pro	Fast, controllable, strong prompt adherence; Pro for higher quality. Good interactive default.	Confirm commercial-licensing terms for resale.	3.24 / 5 · Pro 2.55 / 5
GPT Image 1	Strong instruction-following and comparatively reliable in-image text; good for layout-aware generation.	Latency and cost on the higher side for interactive use.	3.07 / 5 (measured on GPT Image 1.5)
Ideogram V3	Built around typography and still a credible pick for poster and typographic art, but our measured text column no longer puts it on top.	Ranks twelfth of fifteen on text accuracy in our run.	2.97 / 5

Routing heuristic: logos, icons, and typographic art go to Recraft V3 (vector; the print files use case). Words-in-image goes to whichever flagship currently tops the measured text column, which in our July 2026 run means GPT Image 1.5, FLUX.2 [pro] or Nano Banana Pro rather than a typography specialist (the text-heavy designs use case). Photoreal hero imagery goes to Seedream V4 or Nano Banana Pro (the product ads use case). Fast interactive drafts go to Recraft 20B / Nano Banana.

Job B: Image editing (adapt a customer’s asset)

Candidates: Flux Pro Kontext, Flux Pro Kontext Max, Nano Banana Edit, Nano Banana Pro Edit, Qwen Image Edit, Gemini Flash Edit, Seedream V4 Edit, GPT Image 1, Ideogram V3 Remix.

Model	Stand-out for print	Watch-outs	Benchmark
Flux Pro Kontext / Max	Strong instruction-based editing with high subject preservation: change one thing without wrecking the rest. Good for generative fill/expand and targeted edits.	Max tier costs more; budget per edit.	editing suite planned
Nano Banana Edit / Pro Edit	Fast, controllable edits; good interactive default for object removal and swaps.	Verify edge quality on fine detail.	editing suite planned
Qwen Image Edit	Strong editing with good text handling during edits.	Validate commercial terms.	editing suite planned
Gemini Flash Edit	Low latency: the responsiveness pick for interactive editing.	Quality trade-off vs. heavier models.	editing suite planned
Seedream V4 Edit	High-fidelity edits matching its generation quality.	Heavier; weigh latency.	editing suite planned

The benchmark currently measures text-to-image only; the editing models above join the leaderboard when the frozen suite adds an editing track, so their cells read “editing suite planned” rather than a score.

Routing heuristic: precise “change X, keep everything else” goes to Flux Kontext. Fast interactive edits go to Gemini Flash Edit / Nano Banana Edit. Edits that must preserve in-image text go to Qwen Image Edit.

Job C: Specialized print operations

These aren’t single “models” so much as task pipelines, but they belong in the routing table:

Task	Approach / model	Note
Vectorize (raster → SVG)	Vectorize plugin / Recraft vector	The print-critical one: protects logos and PDF/X vector output.
Background removal	`@imgly/background-removal` (in-browser)	On-device, instant, privacy-preserving. Feeds cutout paths.
Image correction & DPI	Perfectly Clear plugin + DPI validation	Auto-corrects exposure, color, sharpness, and noise; validation flags undersized images. Prefer high-res native generation over upscaling.
Text generation / copy	Claude Sonnet 4.6, GPT-4.1 Nano	Headlines, rewrites, per-recipient VDP copy.
Text-to-speech / sound	ElevenLabs (where relevant)	Less common in print; relevant for multi-channel campaigns.

The quick-reference picks

If you skip the rubric and just want today’s defaults, this is the snapshot we’d start from. Treat it as the hypothesis your own benchmarks confirm or overturn, not a verdict.

Print job	Pick	Why
Logos, icons, line art, anything that must scale	Recraft V3	The only major model with native SVG/vector output. Everything else hands you pixels to trace. Vector survives into PDF/X as real paths and prints sharp at any size.
Legible text inside the image (posters, labels, packaging motifs)	GPT Image 1.5, FLUX.2 [pro], Nano Banana Pro	These three rendered every required string in our suite exactly. The typography specialists did not: Ideogram ranks twelfth of fifteen on the measured column. Still, bake text in only when you must: real type as a separate editor layer beats all of them.
Photoreal hero imagery at print size	Seedream 4.5	Resolution is the print bottleneck, and it is the one criterion where the field genuinely splits. At default parameters Seedream returns 2048px (about 6.8” at 300 DPI); most of the field returns 1024px, which is 3.4” and a bet on the upscaler.
Transparent cut-outs for stickers, die-cuts, merch	GPT Image 1.5, and a background-removal step regardless	It is the only model in our run that reliably emits a real alpha channel. Thirteen of fifteen emit none at all, so the cut-out has to be a pipeline step, not a prompt.
”Change X, keep everything else” edits	Flux Kontext Pro / Max	Best-in-class instruction-following edits with subject preservation, which is critical when the asset is the customer’s product photo and “the AI improved it” means a reprint. The Nano Banana family is the consistency pick for variants of one subject.
Interactive drafts (speed and cost)	Recraft 20B, Gemini Flash Edit, base Nano Banana	In an editor, a 20-second generation is a bounce. Draft cheap and fast, then re-render the final with the heavyweight. The customer never needs to know two models were involved.
Data sovereignty / self-hosting	Qwen-Image / Qwen Image Edit	Apache 2.0 open weights. For European operators and government buyers who won’t send customer uploads to a US API, “we can run it ourselves” beats a quality delta.
VDP copy and headlines	Claude Sonnet 4.6	Cheap enough per recipient at 100k-mailer volume, and strong at length-constrained rewriting: the “fit this text frame” problem.

Three of those rationales carry more weight than the rest.

Vector is the criterion that decides printability. Screen products never need vector, so general models never optimized for it, and Recraft sits almost alone on the one measure that determines whether a logo prints cleanly at size. If you adopt a single routing rule from this guide, make it this one.

Resolution and color are pipeline problems the model can only start. No model outputs CMYK; every one generates sRGB. “CMYK-readiness” is really about how hard a model’s palette clips on conversion, and your ICC and soft-proofing pipeline owns the rest. Same with DPI: pair every generation path with validation and a dedicated upscaler rather than trusting native output. You can swap the model whenever you want; the print-correctness layer around it has to stay put.

Transparency is not a model feature you can shop for. When we asked every model for a transparent background and measured the alpha channel that came back, thirteen of fifteen returned none, and a few painted a checkerboard into the pixels instead. If your product sells stickers, die-cuts, or anything composited onto a garment, budget for background removal and edge cleanup as a permanent pipeline stage. Choosing a different model does not remove that stage.

One roster note: Adobe Firefly isn’t wired into CE.SDK’s plugin roster today, but for licensing-sensitive enterprises its trained-on-licensed-content and indemnification story is the strongest answer to criterion 11. Include it in your own evaluation if criterion 11 dominates your weighting.

A worked decision: which model wins for your product?

The rubric resolves to a different answer per context. Three quick reads:

Interactive design tool (non-designers personalizing templates). Weight responsiveness, controllability, and vector. Likely stack: Recraft 20B / Nano Banana for fast generation, Recraft V3 for final vector, Gemini Flash Edit for interactive edits. The customer iterates fast and the final asset is print-clean. See the in-app UGC use case for how the benchmark weights this context.
High-volume VDP / automation (100k personalized mailers). Weight cost, throughput, consistency, and licensing. Likely stack: a cost-efficient generation model at high concurrency, Claude Sonnet 4.6 for per-recipient copy, seed-locked for repeatability, all run headless. Per-unit cost dominates the decision. See the personalization-at-scale use case for the weighted read.
Merch / POD (user art on physical products). Weight transparency/cutout, resolution, and quality. Likely stack: background removal plus cutout for subjects, upscaling for resolution, Seedream V4 / Nano Banana Pro for generated designs, with hard licensing checks because the output is resold. See the merch and stickers use case, where the transparency gap decides the stack.

In every case, the conclusion is the same: no one model wins all three. The advantage is in being able to route each task to the model that wins it, and to swap models as better ones appear, without re-architecting your editor.

What makes per-job routing practical: native plugins + the AI Gateway

A criteria-driven, route-per-job strategy only works if switching models is cheap. If wiring in a new model means a new API integration, new auth, new key management, new error handling, and new billing plumbing every time, you’ll quietly standardize on whatever you integrated first, and inherit its weaknesses on every job it loses.

CE.SDK is built to avoid that:

Every image model in this guide is natively supported as an AI plugin. Text-to-image and image editing run as drop-in providers inside the editor, not bespoke integrations you build and maintain. Background removal, vectorization, and image correction (Perfectly Clear) ship as their own plugins, and text generation routes through built-in Anthropic and OpenAI providers. Adopting Recraft for vector, Ideogram for text, and Flux Kontext for edits is configuration, not three separate engineering projects.
The AI Gateway gives you one unified surface to every model. Instead of stitching together a dozen provider APIs, key schemes, and rate-limit behaviors, you call models through a single managed layer. That’s what turns “route each task to the best model” from an architecture diagram into a one-line config change, and what lets you swap a model the day a better one ships, without touching your editor or your print pipeline.
Outputs land inside the print pipeline, not beside it. Whatever model produces the asset, it flows into locked templates with bleed, safe-area, and DPI constraints, then through CMYK / spot-color / PDF/X-3 export. The model is interchangeable; print correctness is not. Print-on-demand company The Print Bar and direct-mail platform PostBuddy both built on this pipeline, embedding CE.SDK rather than maintaining their own print editor.

So the “best model” question is no longer a one-time, high-stakes bet on a single provider; it’s an ongoing optimization. The benchmark scores below tell you which model to route each job to today, and the native-plugin and Gateway architecture is what lets you act on that answer and revisit it when the scores change next quarter.

The IMG.LY GenAI benchmark: measured results

IMG.LY’s GenAI benchmark now scores these models on print-representative prompts, and the results are live and explorable at img.ly/ai-benchmarks. The table below is the top-line read for the text-to-image models in this guide: the overall score out of 5, the four print-critical criteria (each out of 5), list price per image, and median (p50) latency. All numbers are from the pilot-0 dataset (July 2026); scores are sorted by overall.

Model	Overall	Text	Color	Transparency	Resolution	$ / image	p50
Nano Banana 2 Lite	3.87 / 5	4.9	2.9	0.0	3.0	$0.02	4.0s
Seedream 4.5	3.80 / 5	4.9	2.9	0.0	5.0	$0.048	12.4s
FLUX.2	3.64 / 5	4.9	2.8	0.0	2.0	$0.013	2.0s
FLUX.2 Turbo	3.61 / 5	4.9	2.7	0.0	2.0	$0.015	2.0s
Gemini 2.5 Flash Image	3.60 / 5	5.0	1.7	0.0	3.0	$0.039	7.4s
Recraft V3	3.29 / 5	4.0	1.9	2.0	3.0	$0.04	7.4s
Nano Banana 2	3.24 / 5	5.0	3.2	0.0	3.0	$0.10	13.2s
FLUX.2 Pro	3.23 / 5	5.0	2.3	0.0	2.0	$0.04	11.5s
Qwen-Image	3.21 / 5	4.8	2.0	0.0	2.0	$0.03	6.9s
GPT Image 1.5	3.07 / 5	5.0	3.4	4.2	3.0	$0.12	34.0s
Ideogram 3.0	2.97 / 5	4.7	2.8	0.0	3.0	$0.06	17.9s
Nano Banana Pro	2.55 / 5	5.0	3.7	0.0	3.0	$0.36	23.3s

Measured on the pilot-0 suite (July 2026): 37 prompts times 3 seeds per model, every image scored 0 to 5 per criterion by an automated vision judge. Two models carry newer versions than the guide names them by: Seedream V4 is measured as Seedream 4.5, and GPT Image 1 as GPT Image 1.5. The suite also covers Seedream 5.0 Lite, Luma Photon, and Stable Diffusion 1.5, which this guide’s roster does not name; their scores are on the rankings page. The overall column is an unweighted blend, so read it alongside the per-use-case weighting, not as a single leaderboard: the cheap fast model tops the raw average while the priciest lands last. Full methodology is at img.ly/ai-benchmarks/methodology, and every model, prompt, and generated image is explorable at img.ly/ai-benchmarks.

A few things the numbers make plain, and that the criteria above predicted. Transparency is close to unsolved: 13 of 15 tested models emit no real alpha channel at all (the transparency finding), and GPT Image 1.5 is the only one that scores meaningfully on it. Brand color is broadly weak: measured with CIEDE2000, no model reliably hits an exact hex (the brand-color finding). Text is the one column where the field mostly clears the bar: on our per-required-string measure several general-purpose flagships render every string in the suite exactly, while the model with the biggest reputation for text, Ideogram, actually lands near the bottom of the column, not the top (the text-reliability finding). The gaps open exactly where print work gets hard. Averaged across the field, the neon sign in Japanese scores 3.91 and the dense packaging label 4.40, against 4.91 for a greeting-card cover. Latin headlines are close to solved; small type and non-Latin scripts are not.

The same numbers, weighted for print

The overall column is the wrong lens for a print product, which is the whole reason the benchmark carries use-case weights. Reweighted for print files (resolution 35%, color 30%, text 15%, transparency 10%), Seedream 4.5 leads at 3.64, ahead of Seedream 5.0 Lite at 3.50 and GPT Image 1.5 at 3.45: native output size at default parameters does most of the work, and the two models that return 2048px start the job at twice the printable width of the 1024px field.

Reweight again for merch and stickers, where alpha carries 35%, and the order breaks completely: GPT Image 1.5 wins at 3.72, nearly a full point ahead of Recraft V3 at 2.78, because it is the only model that reliably returns a real alpha channel. Same measurements, different job, different answer. That inversion is the argument for routing per job rather than standardizing on one provider.

The gated report is coming to subscribers first. AI Image Models for Print Production: The Benchmark Report packages the weighted per-use-case totals, the full test set, and the print-specific analysis into one PDF. Subscribe to get it before it is public.

The criteria and the routing logic above stand on their own. The scored numbers are what the suite adds: a measured, repeatable answer for each cell, refreshed as models change. For why the benchmark is built this way, and what else the run turned up, see Introducing IMG.LY AI Benchmarks.

Bottom line

Pick criteria before you pick models. For web-to-print, the criteria that screen benchmarks ignore (vector output, print resolution, CMYK behavior, text legibility, licensing) are exactly the ones that decide whether a beautiful generation is a sellable print. Score the current models against those criteria for your context, route each job to the model that wins it, and run it all through CE.SDK’s native AI plugins and AI Gateway so re-routing tomorrow, after the next leaderboard reshuffle, is a config change rather than a rebuild.

Companion piece: How to Leverage Generative AI in Web-to-Print covers the use cases, integration patterns, and print-specific pitfalls behind these model choices.

How to Leverage Generative AI in Web-to-Print

Jan — Fri, 26 Jun 2026 00:00:00 GMT

Web-to-print sells self-service: your customer designs a postcard, a flyer, a t-shirt, a packaging label in the browser and orders it without a designer in the loop. For years, though, the self-service stopped at the hard part. Someone still had to supply a usable image. Someone still had to know what 300 DPI meant. When they didn’t, the file landed on a prepress desk to be fixed by hand.

One operator we spoke to put it bluntly: his designers spend roughly 40% of their time fixing customer artwork rather than creating templates. Tom Rowe of The Print Bar described what that looks like at the design step: “Our brand didn’t match our experience. You could see it in our bounce rates.”

Generative AI changes the economics of that hard part. It can turn a prompt into a usable asset, lift a 72-DPI logo to something printable, and strip a background in the browser before a human ever sees the file, removing the specific friction that kept self-service from being self-service in the first place.

It can also go wrong: aimed carelessly, the same models produce beautiful screen images that fall apart on press. This post is about the difference between the two: the use cases worth building, and the print-specific realities you have to design around.

The shift: from “upload a print-ready file” to “describe what you want”

The old web-to-print contract asked the customer to arrive with a finished, technically correct asset. That filter excluded most of the market: the CRM manager, the franchise owner, the small-business buyer who “knows Canva because they make their wedding invitations on it” but has never opened InDesign and never will.

Generative AI moves the burden of production off the customer. Instead of “upload a 300 DPI CMYK image with 3mm bleed,” the ask becomes “type what you want on the card.” The editor, not the customer and not your prepress team, becomes responsible for turning intent into a production-safe file.

That principle runs through everything below: AI is most valuable in web-to-print where it removes a step the customer was never qualified to do. The closer a use case sits to it, the more it returns.

The use cases worth building

1. Generate on-brand imagery from a prompt (text-to-image)

This is the most obvious win. A customer needs a hero image, a background, a seasonal motif, or a product scene, and doesn’t have one. Text-to-image generation lets them describe it and get options in seconds, without a stock-photo license hunt or a design request ticket.

In a print context the point is unblocking the order, not novelty for its own sake. The customer who would have abandoned at “I don’t have a good image” now keeps going. Models like Recraft V3, Seedream V4, Ideogram V3, and the Nano Banana family each have different strengths here (covered in depth in the companion guide, The Best GenAI Models for Web-to-Print), but the integration pattern is the same: generation feeds a placeholder inside a locked template, so the output lands inside your bleed, safe-area, and brand constraints automatically.

Watch out: generated images are usually delivered at screen resolution, often around 1024px. That’s fine for a business card photo, marginal for an A4 flyer, and unusable for large-format. Pair generation with upscaling (below) and size validation before you let it reach export. Native output sizes vary widely by model: the measured native output in the model rankings (pilot-0 dataset, July 2026) shows some models topping out near 1024px while others generate at 2K.

2. Adapt and extend customer-supplied images (image-to-image, generative fill/expand)

Customers rarely arrive with an asset that fits your canvas. It’s the wrong aspect ratio, it has the wrong background, or it’s a portrait crop where you need a landscape banner. Image-to-image editing and generative expand (outpainting) solve the most common case: extending an image to fill bleed or a different SKU’s dimensions instead of stretching or letterboxing it.

This is quietly one of the highest-value print use cases, because aspect-ratio and bleed mismatches are a top source of prepress rework. Generative fill also handles object removal (“take the coffee cup off the desk”), background swaps, and clean-up: the edits a non-designer can’t do in any tool they own.

Watch out: outpainting invents pixels. On a brand asset or a product photo, “invented” can mean “wrong.” Keep generative expand to backgrounds and ambient areas. Never let it reconstruct a logo, a face, or a product the customer is actually selling.

3. Background removal and cutouts for mockups and merch

Background removal is the workhorse, and it has to be a pipeline step because the models won’t do it for you: our transparency finding shows 13 of 15 tested models emit no real alpha channel at all. For merch and print-on-demand it’s the difference between a customer’s snapshot and a clean subject that drops onto a t-shirt, mug, or sticker. IMG.LY runs this in the browser (via the open-source @imgly/background-removal package), which matters for two reasons: it’s instant enough for an interactive editor, and the customer’s image never has to leave the device.

Paired with the cutout plugin, background removal also feeds the literal cut lines for die-cut stickers, labels, and packaging, turning a removed background into a production path.

Watch out: browser-based removal is excellent on clear subjects and struggles on hair, glass, and fine fringes. For a print product that will be inspected up close, expose a manual refine step rather than trusting the mask blindly.

4. Vectorize raster art into print-scalable graphics

This is the use case print people care about most and screen-first builders forget. A customer uploads a logo as a small, jagged PNG. Printed at size, it’s mush. Vectorization (AI raster-to-SVG) traces it into clean, resolution-independent paths that scale to any output size and reproduce crisply on press.

Vectorize is also how you get logos and simple graphics into a state your PDF/X pipeline can preserve as vector, instead of rasterizing everything and throwing away the scalability you vectorized for. Recraft V3 is notable here because it can generate natively vector output rather than only tracing after the fact.

Watch out: vectorization is great for logos, icons, and flat art. It’s the wrong tool for a photograph. Detect the asset type and route photos to upscaling, not tracing.

5. Resolution and image quality: upscaling, correction, and DPI repair

The single most common web-to-print failure is a low-resolution image: the 72-DPI photo that looks fine on screen and prints as a blurry mess. Two different AI operations fix it, and it pays to keep them straight, because they solve different problems.

Upscaling (super-resolution) raises the actual pixel count, reconstructing detail to lift a small image toward a printable size. It’s a generative step you route to a dedicated model, the same way you route a text-to-image prompt; the strong upscalers can take a 1024px generation to 4K. Reach for it when the source is simply too small for its placed size.

Image correction is the other half, and it ships in CE.SDK today as the Perfectly Clear plugin. It auto-corrects exposure, contrast, color, tint, sharpness, and noise in a single pass. It won’t add pixels, but it gets the most printable result out of the pixels you have, which is what a dim, soft phone photo usually needs more than raw resolution.

Tie both to your DPI validation. When the editor detects an image below your minimum threshold for its placed size, offer to correct or upscale it instead of just blocking export. You convert a dead end into a one-click fix, the kind of “they don’t need to know what DPI is” experience operators are chasing.

Watch out: upscaling fabricates detail. It rescues marginal images; it can’t conjure a sharp 4-megapixel product shot from a thumbnail, and correction can’t add resolution at all. Set honest thresholds, and still warn when the source is hopeless.

6. Copy and variable text generation (text + VDP at scale)

Generative text earns its place in two spots. First, as a writing aid inside the editor: headline options, a tagline, a “make it shorter / more formal / fit this space” rewrite for the non-writer staring at an empty text box. Second, and more powerfully for print, in Variable Data Printing: generating or localizing per-recipient copy across thousands of personalized postcards, mailers, or labels from a single template.

VDP is the highest-leverage place to use generative text: generate the variants, merge them into print-ready files in headless mode, and run the batch.

Watch out: generated copy needs guardrails. Length limits so it doesn’t overflow the text frame, tone and brand constraints, and a human-review gate for anything legally sensitive: pricing, claims, regulated industries.

7. Template adaptation and auto-resize across SKUs

A print catalog is the same design across many sizes and substrates: the same campaign as a postcard, a flyer, a poster, a social tile. AI-assisted resize and re-layout adapt one master design to every SKU’s dimensions, reflowing content intelligently instead of scaling it blindly. Combined with locked templates, you expand SKUs without re-authoring each one.

Watch out: reflow decisions still need brand rules. Lock what must stay fixed (logo size, safe area, mandatory legal text) so the AI rearranges within your constraints, not over them.

8. Guided prepress correction

Instead of rejecting a bad file after the fact, use AI to catch and fix problems inside the editor: flag the low-res image and offer to upscale it, detect text outside the safe area and nudge it in, notice a near-white “white” that won’t print and correct it. The same problems your prepress team used to fix by hand get caught here, before the order is placed.

Watch out: auto-correction must be transparent and reversible. Show the customer what changed and let them undo it. Silent “helpful” edits to someone’s artwork erode trust fast.

9. Localization and market variants

For franchise networks and multi-market brands, AI translation plus regeneration of localized imagery and copy turns one approved master into 12 market versions, each print-ready and on-brand, without a translation agency or 12 design tickets. A 200-location franchise can ship 200 localized flyers with the same brand guideline enforced by the editor on every one.

Watch out: machine translation in regulated or legal copy needs human sign-off, and text expansion (German runs roughly 30% longer than English) will break tight layouts unless your template frames can flex.

10. Realistic product previews

Generative and 3D-assisted mockups show the design on the actual product: the shirt, the mug, the folded brochure, the box, not an abstract artboard. Operators consistently tie this to higher conversion and fewer “will this look right?” support tickets, because the preview matches what arrives on the doorstep.

Watch out: a preview that’s prettier than the print sets up a disappointed customer and a reprint. Calibrate mockups to real output, including substrate color and finish.

The print-specific realities

Most generative models are built for screens. Print adds requirements the web doesn’t have, and the ones below are where projects most often break.

Resolution and DPI

Generated images typically arrive at around 1024px. At 300 DPI that’s about a 3.4-inch image: fine for a business card, not for a poster. Always validate output resolution against placed size, and route undersized assets through upscaling before export. Treat raw generation resolution as a starting point, not a deliverable. Native output size is one of the axes we measure: see the measured native output per model to know which models start closer to print size and which need the most upscaling.

Color: sRGB in, CMYK out

Models generate in RGB. Print is CMYK, plus spot colors. The vivid blues, greens, and oranges that look great on screen sit outside the CMYK gamut and will shift on press. And even inside RGB, hitting an exact brand hex is hard: our brand-color finding measures color accuracy with CIEDE2000 and no model reliably lands the color in your brand book, which is one more reason correction belongs on the canvas. Your pipeline, not the model, owns this: convert with the right ICC profile, validate against the print provider’s color requirements, and preserve named spot colors through to the PDF/X. Show the customer a soft-proof so the shift isn’t a surprise on delivery.

Vector vs. raster (and the “everything got rastered” trap)

Most models output raster. For logos, type, and line art that need to scale and print crisply, raster is the wrong format, and a PDF that rasterizes all text and vectors is, in one operator’s words, “death for the printer.” Use vector-native generation (e.g. Recraft) and vectorization for the elements that need it, and make sure your export keeps vector and text as vector with CMYK values preserved (PDF/X-3), not flattened to pixels.

Text rendering inside images

Generative models have a reputation for garbling text inside images, and our text-reliability finding shows the top of the field has largely fixed it: a handful of flagships now render every required string in our suite exactly. The catch for print is that reputation and measurement no longer line up. Ideogram, the model best known for typography, ranks twelfth of fifteen on the measured column; several general-purpose flagships beat it. Reach for a specialist on reputation and you can end up with worse type than the default model you already route to. Put every model on the same wordmark prompt to see the spread. For anything that must be readable in print, don’t bake text into a generated image. Generate the imagery, then set real, editable, vectorizable type as a separate layer in the editor. If you must bake text in, pick the model from the measured column rather than from the marketing; the companion guide has the current ranking.

Brand safety and guardrails

Let customers generate anything and you lose brand control. Box generation inside locked templates instead: it fills a defined placeholder, within fixed margins, alongside a logo and palette the customer can’t move. A franchisee can change the headline and the photo; the logo size, position, and safe area stay locked. AI expands what the customer can create without expanding what they can break.

Commercial and licensing rights

A web-to-print product is sold. That makes the IP status of generated assets a question you have to answer before you ship. Does your model provider grant commercial-use rights to outputs? Are there indemnities? Does training-data provenance create exposure for a customer reselling the printed product? Pick models and providers whose commercial terms you’ve actually read, and surface usage terms where they matter.

Cost and latency (the unit economics)

Every generation costs money and time. In an interactive editor, a 30-second generation is a broken experience. In a high-volume VDP run, a few cents per asset multiplied by 100,000 recipients is a real line item. The spread is not small: the measured $/image and p50 latency in the model rankings run from a fraction of a cent to tens of cents, and from a couple of seconds to over thirty. Match the model to the job: a fast, cheap model for interactive iteration, a higher-quality (slower, pricier) model for the final render, and use the compare tool to weigh the trade-off head-to-head. Cache aggressively. The companion guide scores models on that trade-off.

Data privacy and sovereignty

Customer-uploaded images can be sensitive: faces, IDs, confidential product designs. Browser-based processing (background removal, some editing) keeps data on-device. API-based generation sends it to a third party, which has GDPR and data-residency implications, especially for European customers and government buyers who “prioritize a European vendor for data sovereignty.” Be explicit about what runs locally vs. in the cloud, and choose providers accordingly.

Hallucination and consistency

Generative output is non-deterministic. The same prompt yields different results, and details drift. Our consistency finding measures the worst of it: no model holds a described character across scenes, so series work needs identity as a reusable asset, not a regeneration lottery. For brand assets, product likenesses, and anything a customer will compare against reality, constrain hard (reference images, seeds, image-to-image rather than free generation) and keep a human gate on the outputs that matter.

How IMG.LY approaches it

All of these constraints point the same way: AI is a step inside a print pipeline, not a feature bolted onto an editor. A few principles shape how CE.SDK handles it:

Model-agnostic by design. The AI plugins connect to any third-party model or API: bring your own model. You’re not locked to one provider’s quality, price, or licensing terms. You route each task to the model that wins it, and swap models as better ones ship every few weeks.
The AI Gateway provides managed access to models for editors, so you’re not stitching together a dozen API integrations and key-management schemes yourself.
Generation lands inside the print pipeline. Outputs flow into locked templates with bleed, safe areas, DPI thresholds, and brand constraints already enforced, then through a CMYK / spot-color / PDF/X-3 export that keeps vectors and text as vectors. The model never gets to bypass print correctness.
Drop-in generative features. Background removal, generative fill, image-to-image, vectorize, and text-to-image are available as plugins, so you adopt the use cases above incrementally rather than rebuilding your editor.
Headless mode runs the same generation and export server-side for batch and variable-data runs.

The result is the experience operators actually want to sell: the customer describes what they want, the AI does the part they were never qualified to do, and the file that reaches the press is print-correct because the pipeline enforced it, not because the customer got lucky. For the product-level view of this stack, see AI for Print on Demand.

What customers are doing with it

High-volume print and direct-mail platforms are already building on this foundation. IMG.LY powers print and personalization workflows for operators including Postbuddy (personalized direct mail), Swiss Post, Digitas, and HP, alongside hundreds of smaller print, merch, and franchise platforms.

The pattern that recurs in those conversations is narrow and specific: AI removed a bottleneck. The prepress team that fixed 40% of incoming files now lets the editor catch problems upstream. The customers who bounced at “I don’t have a good image” finish the order. The franchise network that needed a designer for every local variant generates them inside guardrails. It comes back to the point from the top: AI pays off where it deletes a step the customer couldn’t do and the operator didn’t want to.

Where to start

You don’t need all ten use cases on day one. The highest-ROI starting points, in order:

Background removal: instant, in-browser, immediately useful for any merch or photo product.
Image correction and DPI validation: catches and cleans up weak uploads before they ever reach the printer.
Generative expand / fill: kills aspect-ratio and bleed rework.
Text-to-image into locked placeholders: unblocks the “I don’t have an image” abandoner.
Vectorize: rescues logos and protects your PDF/X output.

Each one removes a documented source of friction or rework. Add them inside locked templates and a real CMYK/PDF/X pipeline, and self-service web-to-print finally works the way it was always sold: the customer really can do it themselves.

Next: which models to actually use. See the companion guide, The Best GenAI Models for Web-to-Print: A Buyer’s Guide, for a criteria-based comparison across output quality, vector/SVG support, text rendering, color, responsiveness, and cost. For the measured evidence behind these pitfalls, see the IMG.LY GenAI Benchmarks: every model on the same prompts, scored per criterion, with the method and headline results written up in Introducing IMG.LY AI Benchmarks.

13 Questions Teams Ask Themselves Before Choosing IMG.LY

Marc — Fri, 19 Jun 2026 09:00:00 GMT

Most teams evaluating an in-app editor arrive with the same shortlist of questions. These are the 13 that come up most across 600+ customers and 28 structured interviews, each answered straight, with the numbers behind it.

Why integrate an editor instead of building our own?

A production-ready SDK turns months of editor engineering into a couple of weeks of integration. Building an equivalent editor in-house runs 6 to 12 months and ties up two or three senior developers. The median IMG.LY customer reaches production within just 14 days, roughly 13× faster than the in-house route. For fast-moving companies especially, staying on your core is what pays off. Time spent on the editor is time not spent on what actually sets your product apart.

Can’t we just use an open-source library like Fabric.js or Konva?

You can, and some companies do. The problems start once you need more than a drawing surface. Open-source canvas libraries give you that surface and little else, no text on a path, no video timeline, no background removal, no cross-platform parity, and no ready-made UI. You build all of that yourself, and then you own the maintenance forever. The library is free, the year of senior engineering it takes to reach production quality is not.

It was very buggy, lack of features, not looking good, and we decided to not go deeper.

Engineering lead at a company that evaluated open source before CE.SDK

CE.SDK gives you the engine and the UI in one SDK, with the same rendering across web, iOS, and Android. If you want the full breakdown, we put open source next to building and buying in our Fabric.js comparison.

How fast can we realistically be in production?

A working prototype usually takes about two days, and a production-ready integration around two weeks. That time goes into wiring the existing SDK and API into your product and styling it to fit. Our AI developer tooling accelerates the process even more, giving your AI coding assistant full CE.SDK context for the integration. For fast-moving companies, this can be a real booster. Plai went from deal to live in about a month, then quickly scaled to thousands of ad campaigns with the new editor in place.

Every design edit request lands on my team. How do we scale that?

You stop being the bottleneck. Instead of your team producing every asset, users edit themselves inside your product, so output scales with your user base, not your headcount.

When you're dealing with a graphic designer who has a queue of work, you usually need to wait.

Product lead at an IMG.LY customer

The digital agency Digitas built its dealer portal on CE.SDK, and removing that bottleneck led to 85% of videos being created fully in-app, with active users making 3× more than before. None of that work routes through a design team.

The same engine also scales without anyone editing at all. Run it headless and it generates assets automatically. One template plus your data renders thousands of on-brand variants through the API. PostBuddy, for example, does exactly this. Its users choose a template, upload a CSV, and the engine auto-generates thousands of personalized, print-ready postcards, with no one editing a single one. Self-serve covers the one-offs, automation covers the scale.

Our users aren’t designers. How do we keep results on-brand without manual review?

With guardrails you set. Templates, locked brand elements, and constraints let a non-designer produce polished, on-brand work by default, because the editor only exposes what you allow. The output can even beat the professionals.

I built a better-looking asset in the portal than the agency ever did.

Martin Röhr — Senior Project Manager, Digitas

Nobody has to check the output later, because the guardrails already did.

We already have an editor. Is replacing it worth the costs?

The editing experience is part of the sale. When the flow is smooth, more users finish what they start, and completion is conversion. A clunky editor quietly costs you sales.

"Our brand didn't match our experience. You could see it in our bounce rates," says Tom Rowe, and the difference is easy to spot: "you can tell when competitors are using the old platform just by looking at it."

Tom Rowe — Product & Engineering, The Print Bar

When the status quo quietly costs deals, the editor should not be treated as a nice-to-have, but as an essential.

Will it match our product’s look and feel?

Yes, and that fit is exactly what an SDK gives you. The UI is fully customizable. You can theme it, restyle it, or drive the engine from your own interface in a headless setup. It acts as a native part of your product instead of a third-party tool bolted on. Swiss Post, which runs over a million personalized postcards a year on it, confirms this, calling CE.SDK “the only solution allowing a specialized, on-brand UI.”

We ship on web, iOS, and Android. Do we need three different tools?

No. One creative engine renders identically across web, iOS, and Android, so a template built on one platform looks the same on every other and your team keeps one mental model instead of maintaining three separate integrations. You build once instead of rebuilding the editor per OS.

Our users want AI features. Do we have to build those too?

AI editing ships inside the editor, not as a separate project. Background removal and generative tools like text-to-image and image-to-video are ready to use, and CE.SDK is bring-your-own-model, so you plug in the providers you want instead of running inference yourself. That can move the top line on its own.

We are seeing a 10x increase in new signups month over month in May — that was due to the fact that you can now auto-generate really beautiful-looking ads from scratch.

Hikari Senju — Founder & CEO, Omneky

Where does our users’ data actually go?

By default, processing happens client-side, in the browser or on the device, so images and video never touch our servers. For customers with strict data-security requirements that is often a deciding factor, and it is increasingly named as a must-have in AI-driven research. Nothing leaves the user’s machine unless you deliberately choose a server-side workflow. And since IMG.LY is based in Germany, GDPR compliance and EU data residency come built in.

If we build on this, are we locked in?

It is a fair concern, and a different one from whether the vendor sticks around. Your designs and templates stay yours. You can export both your scenes and the rendered output, as PNG, JPEG, PDF, and the scene file itself, and you can run the engine on your own infrastructure, fully headless if you want. You are integrating a component, not handing your data model to someone else, and switching the component out later is possible.

Can we depend on this provider when it matters?

IMG.LY is an established company based in Germany, with a real team of people behind the product rather than a side project that could disappear next quarter. 600+ organizations, from startups to large global enterprises and government agencies, run the SDK in production, together generating around 500 million creations a month. Names on that list include Mercedes-Benz, Lufthansa, SAP, Polaroid, and Ticketmaster. You also get a dedicated contact who stays reachable when you need help, not an anonymous ticket queue, and the SDK keeps shipping new capabilities release after release, so the foundation you build on only gets stronger.

How do we know it’ll work before we’re all in?

You don’t have to trust the pitch, you can prove it yourself. The trial is self-serve. A developer can spin up an account and start building with the real SDK without going through sales, then judge the integration and the docs firsthand. It doesn’t need to take long either, thanks to the AI developer tooling that helps your assistant generate accurate integration code. That’s how most teams who picked IMG.LY decided, because seeing it run in your own stack removes the guesswork before you commit.

Recognize a few of these?

These are exactly the questions a careful team should ask before building on someone else’s technology. If you’re working through them, we’re glad to help: try the SDK yourself or contact our team. Reaching out is no commitment, and we’re happy to dig into your specific case. And to see how it played out for other companies, our case studies offer interesting insights.

CE.SDK v1.76 Release Notes

Neslihan — Fri, 05 Jun 2026 15:17:25 GMT

With this release, the mobile video timeline gets a meaningful upgrade, background removal comes to Android, and a set of engine improvements tighten text, shape, and font-size handling across platforms.

Let’s jump in!

Edit Multi-Clip Timelines on iOS and Android

The mobile video timeline now supports multiple clips per foreground track. Long-press any clip to drag it within a track, across tracks, or into a gap to create a new track. Split, trim, and move are all gap-aware and respect locked clips.

For your product, this means: users can manage their video edit the way they’d expect, organizing clips in a single track instead of working around single-clip limitations.

→ Video Editor Starter Kit – iOS
→ Video Timeline Docs – iOS

→ Video Editor Starter Kit – Android
→ Video Timeline Docs – Android

Remove Backgrounds on Android

The Background Removal plugin is now available for Android. Users can remove backgrounds from images directly in the editor, without leaving the app or sending images to an external server.

For your product, this means: Android users get the same background removal capability that was already available on web, closing a gap for teams building cross-platform photo editing experiences. Users stay in your app for design tasks.

→ Android Background Removal Docs

New Plugin: Turn PDFs into Editable Designs

A new plugin and demo lets you import PDF documents directly into CE.SDK and turn them into fully editable designs.

With that, users can bring existing PDF assets into your editor without rebuilding them from scratch, opening up workflows around template reuse, document personalization, and print editing.

→ Try the Demo

Improvements

Set Font Sizes in Pixels or Points
v1.76 adds per-scene font-size unit control. Choose pixels or points for a scene, and CE.SDK font-size APIs and editor UI follow that unit across all platforms.

Set Different Line Spacing Per Paragraph
Each paragraph in a text block can now have its own line spacing, instead of every paragraph sharing the same setting.

Add Precise Strokes to Texts

Style text outlines down to the last detail! The same controls you’d expect on any shape, now on text and captions too.

Tweak stroke position (inner, outer, center), dash patterns, cap styles, and corner joins directly on text and caption blocks.
→ Text Effects Docs

Draw Better Lines
Lines are now true line shapes. You can control how the ends of lines and dashes are styled (round, flat, or square), instead of working around lines behaving like thin rectangles.

Control Where Images Sit Inside a Block
New APIs let you control how image fills align inside a block when using Contain or Cover fill modes. Useful for templates where the inserted image’s aspect ratio is unknown. Also available for cropping in the web editor.

Changelog

v1.76 includes a significant number of improvements across platforms. See the full changelog for the complete list.

Thank you for building with IMG.LY.

CE.SDK v1.75 Release Notes

Neslihan — Fri, 22 May 2026 12:18:08 GMT

v1.75 is an engine release. Four new capabilities across media support, color workflows and smarter canvas and selection behaviors.

Let’s dive in!

Import Animated PNGs

CE.SDK now supports APNG import. Animated PNG files load and behave in line with GIF import, giving you a second animated format to work with in your editor.

→ Supported File Formats Docs

Pull Dominant Colors from Images on the Canvas

The engine can now extract the most prominent colors from an image already placed on the canvas. The data is available programmatically, ready to feed into palette suggestions.

→ Colors in CE.SDK Docs

Control How Far Elements Can Move

Define how far elements can be dragged beyond a page or parent boundary. This is now fairly simple with new movement constraint APIs.

Allow partial overflow where it makes sense while keeping content inside the intended editable area everywhere else.

This means more precise control over template behavior. Useful for any use case where content boundaries need to be enforced.

→ Movement Constraints API Docs

Improvements

Reach Elements Hidden Behind Transparent Images

Clicks now pass through transparent image areas to the element underneath. Selecting stacked elements just got easier.

Instead of selecting the top image, the click passes through to the element below. Now, users can reach and select elements from overlapping images without trouble.

Changelog

v1.75 includes bug fixes across the engine, web, iOS, and Android. See the full changelog for the complete list.

CE.SDK v1.74 Release Notes

Neslihan — Fri, 08 May 2026 08:53:50 GMT

v1.74 is a web-focused release. Color and Gradient editing gets a full rebuild, closing gaps with popular editors. And PDF export takes a meaningful step forward for professional print workflows.

Edit Gradients with Full Control

The color input system in the web editor has been rebuilt. The user-facing result: gradient editing now works the way you’d expect it to.

Create and edit linear, radial, and conical gradients
Add and remove gradient colors, and switch between gradient types without losing the colors. Color picking now works consistently across all contexts: fill, stroke, shadow, and text.

Build and refine complex gradients entirely within your editor, without relying on external tools.

→ Explore Gradients Documentation

Export Print-Ready PDFs Without Extra Steps

Professional print workflows have a high bar for color fidelity. v1.74 raises CE.SDK’s output to meet it.

Spot colors are written as device CMYK in the exported file, matching what professional print pipelines expect.
Overprint on text is preserved correctly.
You can now opt out of ICC profile embedding in the print-ready PDF plugin when your workflow doesn’t need it.

Take exported PDFs directly into production with less manual intervention, making CE.SDK a stronger fit for workflows where color fidelity is a real purchasing factor.

→ Print-Ready PDF Plugin Documentation
→ Export to PDF Documentation

Improvements

Edit Vectors with Precision

Vector editing now feels more precise and easier to control, with better bend handles, live corner rounding, mirrored handles for new points on curved paths, new anchor snapping, and clearer tooltips throughout the editing flow.

Align Elements with Snapping Guides

Snapping guides have been refined to better show what is being aligned, using bounded guide segments, clearer visual distinctions, and new anchor-to-anchor feedback, making object placement and path editing more predictable and easier to understand.

Developer Experience

Web Demos Are Now Starter Kits

Every web demo is now a Starter Kit. That means 46 fully-fledged, clonable app templates. Starter Kits are production-ready configurations complete with the toolbars, behaviors, and workflows a real product needs.

Clone it, run it, build from there.

Whether you need the core Design, Photo, and Video Editors (and their powerhouse Advanced variants), specialized industry kits for Apparel, or AI-optimized workflows for generative assets, there is now a clonable app for every use case.

→ Explore Web Editor Demos
→ Starter Kit Documentation

Changelog

v1.74 includes fixes across the engine and web editor. See the full changelog for the complete list.

How 600+ Teams Shipped Creative Editing in 14 Days

Jan — Tue, 28 Apr 2026 21:15:17 GMT

The IMG.LY Impact Report

Based on a self-reported customer survey, 28 structured customer interviews, and IMG.LY’s published customer case studies. External benchmarks cited in context.

600+ companies from startups, over Fortune 500s to government organizations run creative editing on IMG.LY, collectively producing 500 million creations every month. The median customer goes from first SDK access to a working prototype in 2 days and a production-ready feature shipped inside a single 14-day sprint. Those self-reported medians run roughly 13× faster than the 6-month industry baseline for building an equivalent editor in-house, and around 6× faster than stitching together an open-source toolkit.

The time-to-market number is the entry ticket. What those 600+ customers do after shipping, how the editor changes their pricing, funnel, team velocity, and competitive position is what this report is about.

Methodology note. Time-to-prototype and time-to-MVP figures are self-reported by IMG.LY customers in a recent customer survey. All named customer outcomes are drawn from IMG.LY’s published case studies, where the customer has reviewed and approved the specific figures cited. Quantitative ranges and anonymous quotes come from 30 structured customer interviews (2024–2026); individual customers are not identified.

What Customers Unlock

1. Ship in days, not quarters

A working prototype takes an average of two days, a production feature often just a single sprint. Customer interviews put the alternative, an in-house build, at 6–12 months with 2–3 senior developers, consistent with the cost bands documented in IMG.LY’s Build vs. Buy guide and independently with the Standish Group CHAOS Report, which finds only 31% of software projects succeed on time, on budget, and with full scope… and under 10% for large projects.

Plai went live in about a month where their founder had estimated “months and months” for an in-house build. Optimizely, serving 1,000+ enterprise customers, described the integration as “one of the quickest projects we’ve worked on.”

Time to a production-ready MVP

14 days vs. 6 months: how long it takes to ship creative editing

Median time from project start to a production-ready creative editor, by integration path.

Sources. CE.SDK figure (14 days) is the self-reported median from an IMG.LY customer survey; individual results vary with scope and team. In-house (180 days) and open-source (90 days) figures are midpoints of the ranges documented in IMG.LY's Build vs. Buy guide, cross-referenced with customer interviews (N=28).

2. Open new pricing and market tiers

Embedding an editor changes the customer’s own unit economics. It unlocks a self-serve tier where users previously needed a designer in the loop, lowers the price floor, and opens markets where manual production was the binding constraint.

Plai doubled annual revenue and now generates 30,000+ ad creatives monthly on the platform. Postbuddy measured a 4× A/B-test improvement after moving direct-mail creation in-app, a lift that funded expansion into Sweden and Norway. In an anonymized interview, one customer described the change plainly: “We can lower our prices for the base product, it’s cheaper for clients who can use self-service.”

3. Lift your own conversion and engagement

In-context editing keeps users inside the product, shortens time-to-value, and removes the “export to Photoshop” detour that quietly leaks trials. The effect shows up directly in sign-up and trial-to-paid numbers.

Omneky recorded a 10× month-over-month increase in new sign-ups after embedding CE.SDK. In a separate interview, one customer described 400–500 organic trials per month with roughly $65–70K of opportunity evaporating at an 8% trial-to-paid rate tied largely to editor friction, the number that made their own build-vs-buy case close itself.

4. Free your design, marketing, and support teams

The cost saved by an editor isn’t only on the engineering line. It shows up in designer queues that disappear, support tickets that drop, and marketing teams that stop waiting on the bottleneck.

ImageBank X compressed a recurring asset-prep task from 15 minutes to 2 minutes, an 87% reduction per task. Halio.ai enables financial advisors to produce 30 days of branded content in 30 minutes. Interview customers describe the same pattern in plainer language: “happier marketing teams,” and, of the post-launch support burden, “the things the sales team had to deal with all day are just gone.”

5. Compound instead of freeze

This is where the engineering-economics story earns its keep. An in-house editor is a snapshot: the team ships what’s feasible in the window, then expends time and money just to keep it alive. Atlassian’s 2024 State of Developer Experience Report (N=2,100+) found 69% of developers lose eight or more hours per week to inefficiencies (about 20% of their time) with technical debt as the primary cause. Stack Overflow’s 2024 Developer Survey (N=65,437) independently found 62% of developers rank technical debt as their single biggest frustration.

CE.SDK customers don’t pay that tax. New capabilities such as AI background removal, text-to-image, object add/remove, style transfer arrive as modular plugins, not re-architectures. One interviewed customer, who had spent a year building their own editor before switching, described maintaining it as “a full-time job and our main product isn’t editing.” Every month an in-house team spends on maintenance is a month IMG.LY customers get new capabilities shipped to them. The feature gap widens, not narrows.

Editor capability over 24 months

In-house builds freeze. CE.SDK customers compound.

An in-house editor ships at the snapshot the team can afford and then plateaus under the weight of maintenance. CE.SDK customers absorb new capabilities (AI background removal, text-to-image, object remove, automatic subtitles) as modular plugins each quarter.

Build in-house

CE.SDK customer

Illustrative. The CE.SDK trajectory reflects the cadence of major capability releases shipped to customers without re-architecture. The in-house trajectory reflects the typical build-then-maintain pattern documented in customer interviews and corroborated by the Atlassian 2024 State of Developer Experience Report (69% of developers lose 8+ hours per week to inefficiencies, primarily technical debt).

6. Become deal-eligible and privacy-credible

Some categories require an editor to win the deal at all. One interviewed customer received a written RFP rejection that read: “the other provider has an editor, you don’t.” That single moment approved their budget to buy.

For regulated buyers, fintech, healthcare, government, enterprise, client-side processing is a procurement requirement, not a feature. CE.SDK’s default client-side execution means customer data never leaves the browser, which makes the editor defensible in categories where server-side alternatives are blocked.

Swiss Post producing 1 million+ personalized postcards annually on the platform described CE.SDK as “the only solution allowing a specialized, on-brand UI.”

The economics, in one table

The cost gap between building and buying isn’t just wider on day one, it widens over time. Every month an in-house team spends maintaining the editor is a month IMG.LY customers compound new capability on top of what’s already shipped. The table below summarizes the 3-year picture. For the full cost methodology, including the open-source path and the senior-developer rate assumptions, see IMG.LY’s Build vs. Buy guide.

	Build In-House	Open Source + Glue	CE.SDK
Working prototype	2–6 months	1–2 months	2 days (self-reported median)
Production MVP	6–12+ months	3–6 months	14 days (self-reported median)
Team required	3–5 senior developers	1–2 senior developers	1 developer for integration
Year-1 development cost	$100K–$500K+	$150K–$400K	License + integration
Annual maintenance	$75K–$125K (15–25%)	$50K–$100K	Included
3-year TCO	$525K–$1.4M+	$300K–$700K+	Fraction of build cost
Cross-platform parity	Build per platform	Typically web-only	Web, iOS, Android, Desktop, Server

Source for build and open-source cost bands: IMG.LY’s Strategic Guide to Creative Editing: When to Build, When to Buy. Cross-referenced against BLS May 2024 wage data - median software-developer wage $133,080, 90th percentile $211,450 - and aggregated maintenance benchmarks (Pegotec, 2026). Time-to-prototype and time-to-MVP for CE.SDK are self-reported medians from an IMG.LY customer survey; individual results vary with scope, team, and platform target.

When building in-house still makes sense

This report defends one conclusion, so here is the honest counterweight.
Build your own creative editor if all of the following are true:

Creative editing is your core product, and your unique IP lives inside the editing experience itself.
Your requirements are genuinely non-standard, i.e. no off-the-shelf SDK supports your rendering or interaction model.
You have surplus senior engineering capacity that isn’t needed on differentiated work elsewhere.
Time-to-market is not competitive in your category, nobody else is shipping similar capability.

If any one of these is false, the economics above generally make buying both cheaper and faster.

Methodology

Time-to-prototype and time-to-MVP (2 days, 14 days) are self-reported medians from an IMG.LY customer survey. Individual results vary with team experience, integration scope, and platform target.

In-house and open-source timeline ranges are drawn from 28 structured customer interviews conducted between 2024 and 2026, cross-referenced against IMG.LY’s Build vs. Buy guide. Interview customers are not identified; quantitative ranges reflect the distribution of answers across the set.

Named customer outcomes (Plai, Omneky, Optimizely, Swiss Post, ImageBank X, Halio.ai, Postbuddy) come from IMG.LY’s published case studies, where the customer has reviewed and approved each cited figure.

External benchmarks are drawn from:

U.S. Bureau of Labor Statistics, Occupational Outlook Handbook, Software Developers (May 2024)
Atlassian State of Developer Experience Report (2024) (N = 2,100+ developers and engineering leaders, in partnership with DX and Wakefield Research)
Stack Overflow 2024 Developer Survey (N = 65,437 developers across 185 countries)
Standish Group CHAOS Report
Aggregated software-maintenance benchmarks from Gartner, IEEE, and industry practitioners, summarized in Pegotec (2026) and Vention Teams.

Frequently asked questions

How long does it take to integrate CE.SDK?
The median customer in our survey reports a working prototype within 2 days and a production-ready MVP within a single 14-day sprint. Self-reported; varies with scope and team.

What do IMG.LY customers unlock beyond faster shipping?
Five additional outcomes: new pricing and market tiers enabled by self-serve editing; lifted trial-to-paid and sign-up conversion; reduced design, marketing, and support load; a roadmap that compounds instead of freezes as AI features ship as plugins; and deal eligibility in procurement categories that require an embedded editor or client-side processing.

Can AI coding agents like Claude Code accelerate CE.SDK integration further?
Yes. IMG.LY publishes a set of specialized CE.SDK Agent Skills portable knowledge packs that give AI coding assistants expert-level understanding of the SDK before they write a line of code. The skills cover framework-specific documentation lookup (React, Vue, Svelte, Angular, Next.js, Nuxt.js, SvelteKit, Electron, Node.js, Vanilla JS), feature implementation (/cesdk:build), conceptual explanations (/cesdk:explain), and a builder agent that autonomously scaffolds complete CE.SDK applications from a natural-language description.

How much does it cost to build a creative editor in-house?
Published industry benchmarks and customer-reported estimates converge on $100K–$500K+ initial development over 6–12 months with 3–5 senior developers, plus 15–25% of that cost annually in maintenance. 3-year TCO typically lands between $525K and $1.4M. See our Build vs. Buy guide for full methodology.

What percentage of developer time is spent on maintenance?
Atlassian’s 2024 State of Developer Experience Report found 69% of developers lose 8+ hours per week to inefficiencies, about 20% of their time, primarily to technical debt. Gartner reports that 55–80% of corporate IT budgets go to maintaining existing systems.

What is the failure rate of custom software projects?
The Standish Group CHAOS research finds only 31% of software projects succeed (on time, on budget, full scope); 50% are challenged, 19% cancelled outright. For large projects specifically, success rates fall below 10%.

Custom software project outcomes

Only 31% of custom software projects succeed

Across tens of thousands of tracked projects, the Standish Group CHAOS research finds the majority of custom software is late, over budget, reduced in scope, or cancelled outright.

31%

Successful

On time, on budget, with full scope.

50%

Challenged

Delivered late, over budget, or with reduced features.

19%

Failed

Cancelled before delivery.

~25% of IMG.LY customers failed at building a creative editor in-house

In our customer interviews (N=28), roughly one in four customers had attempted to build a creative editor in-house (or stitch one together from open-source), and abandoned the attempt before adopting CE.SDK.

Source. Standish Group CHAOS Report. For large projects specifically (the size band most in-house creative-editor builds fall into), success rates drop below 10%. IMG.LY customer figure is drawn from 28 structured customer interviews conducted between 2024 and 2026.

How many companies use IMG.LY CE.SDK?
600+ customers including startups, Fortune 500 companies, and government organizations collectively produce 500 million creations per month on the platform.

What platforms does CE.SDK support?
Web (React, Angular, Vue, Svelte, Next.js, Nuxt.js, SvelteKit, Vanilla JavaScript, Electron), Mobile (iOS/Swift, Android/Kotlin, React Native, Flutter, Ionic, Cordova), and Server (Node.js headless mode for batch automation).

Starter Kits: A New Way to Use and Configure Our Editor

João — Wed, 22 Apr 2026 17:14:54 GMT

When we built the first version of CE.SDK’s mobile editors, we optimized for speed and ease of integration. We designed a set of ready-made solution editors: Photo, Design, Video, Postcard, and Apparel Editor. Each is built around the use cases we believed would meet the needs of most of our customers. With one component and a license key, you had a full creative editor running in your app. That approach got products to market fast, and for many teams it was exactly the right starting point.

But products evolve, and so do the needs around it.

As integrations matured, teams needed deeper configuration, more granular control, and the ability to shape the editor into something uniquely theirs. What starts as “give us a working photo editor” becomes “give us our photo editor.”

That’s why, starting with CE.SDK v1.73 on iOS and Android, CE.SDK evolves from a set of preconfigured solution editors into a single, flexible Editor foundation paired with Starter Kits: complete, working editor projects that you own, customize, and control entirely.

Here’s what that means and why it’s worth it.

What changed

Previously, you integrated CE.SDK by dropping in a solution-specific component: PhotoEditor, DesignEditor, VideoEditor, ApparelEditor and PostacardEditor. Each came with built-in UI, default behaviors, and preconfigured toolbars. You could adjust some of it through configuration APIs, but the foundation was managed internally by our SDK.

With v1.73, those components are replaced by a single Editor entry point that starts minimal without any configuration and a set of Starter Kits that provide the full experience you’re used to.

Each Starter Kit matches a previous solution: Photo, Design, Video, Postcard, and Apparel. You download it, drop it into your project, and you have the same editor as before.

With Starter Kits, the setup becomes explicit and lives in your own codebase. Instead of relying on built-in defaults inside a prebuilt solution, you start from a ready-made configuration structure that you can inspect, own, and change directly.

And if none of the starter kits match your needs, you can build your own editor from scratch using our configuration directly.

Before, you were always starting from one of the predefined solutions and trying to bend it to fit your use case, which was limited and often frustrating. Now, the building blocks are there for you to assemble however you want.

What are the benefits?

The full picture in one place

Configuration used to be spread across multiple APIs and documentation pages. It wasn’t always clear what you could customize, where to find the right setting, or whether a particular behavior was even exposed for modification.

With a starter kit, the configuration is the documentation. Open the configuration file, and you see every callback, every toolbar item, every setting, the complete scope of what the editor does.

This also makes production behavior safer. Critical parts of the editor setup are now explicit in your code rather than implied by SDK defaults. Your team can see exactly what is configured, why, and review changes through your normal development process.

More control and capability over your editor

Starter kits unlock customizations that were simply not possible before: restructure how the editor initializes; inject custom logic between loading phases; defines layouts from the ground up; build workflows that are unique to your product; and more.

The old configuration APIs drew a line between “customizable” and “not customizable.” Starter kits erase that line. If you can see it in the code, you can change it.

In simple terms, you can now adapt the editor to your product, instead of adapting your product to the editor, and this was one of our main drivers.

Opt in, never opt out

Until now, an SDK update could introduce visible changes to your editor, like a new toolbar button, a different menu option, a changed default, without you asking for it. Your release process had to account for UI changes that came from a dependency, not from your team.

With CE.SDK v1.73, that dynamic is reversed. SDK updates bring new features, engine improvements, performance gains, and bug fixes. But your editor UI stays exactly as you left it. New features and components become building blocks you adopt on your own schedule, documented, with examples, and ready when your implicit decide to add them. Nothing shows up in your product unless you put it there.

Two paths, your choice

Start from a Starter Kit
Download the one that matches your use case, run it, and customize from there. Each kit is a proven, production-ready structure that handles the complexity of editor setup so you don’t have to figure it out from scratch. Most teams will take this path.

Build from scratch
If you have very specific requirements or prefer to architect everything yourself, the Editor view accepts raw configuration directly. The starter kits serve as comprehensive, living reference implementations. Even if you never use them directly, they show you exactly how every piece fits together.

The engine you rely on hasn’t changed

It’s worth saying clearly: the core of CE.SDK, the rendering engine, export pipeline, asset handling, performance characteristics, and everything that powers the creative experience is unchanged. We improved how you configure and integrate the editor, not what powers it.

The Tradeoff

The old one-component integration was genuinely convenient for getting started. With starter kits, you have a small module in your project, a handful of well-organized files that you own and maintain.

We believe this is the right tradeoff for any team building a real product. The moment you need to customize anything you’ll be able to clearly structured and to modify without limits.

At its core, this change is about moving from implicit behavior to explicit control, and we believe that is the better long-term contract with our customers. Your editor should not change in meaningful ways unless you decide it should. Your upgrade path should be predictable. And your team should be able to understand the integration by reading its own code.

Getting Started

We’ve written detailed migration guides that walk through every change with before-and-after examples. Each guide also links to the starter kit repositories for your platform:

	iOS	Android
Migration Guide	Upgrading to v1.73	Upgrading to v1.73
Photo Editor	GitHub	GitHub
Design Editor	GitHub	GitHub
Video Editor	GitHub	GitHub
Postcard Editor	GitHub	GitHub
Apparel Editor	GitHub	GitHub

We’re here to help with the transition. If you have questions, reach out to our support team or open an issue on the starter kit repositories.

CE.SDK v1.73 Release Notes

Neslihan — Tue, 21 Apr 2026 13:29:35 GMT

v1.73 is a mobile-focused release. The main act is our new architectural foundation for iOS and Android: Starter Kits give you full ownership of your editor configuration. On the engine side, CE.SDK now supports SVG export across all platforms.

Own Your Mobile Editor — Not Just the Config

The old model was simple: drop in a solution component (PhotoEditor, VideoEditor, DesignEditor), pass a license key, ship. For most teams, that was exactly the right starting point. Fast to integrate, zero configuration overhead, a full editor running in your app within hours.

As products matured, though, teams needed more. Deeper customization. Granular control over behaviors. An editor that felt like theirs.

That’s what Starter Kits for Mobile addresses.

The prebuilt solution components are replaced by a single Editor entry point and a set of Starter Kits: complete, working editor projects for each use case that live in your codebase, not ours. Set it up in minutes.

For your product, this means: you can adapt the editor to fit your product, not the other way around.

Everything Is In Your Code Now
Each Starter Kit is a real editor project, not a thin config wrapper. Every toolbar item, every callback, every loading phase is written out explicitly in files you own.

That means your team can read the integration, review changes to it, and understand exactly what the editor does and why. No more hunting through SDK internals to figure out why something behaves the way it does.

SDK Updates Stop Touching Your UI
Previously, updating CE.SDK could introduce new buttons, changed defaults, or different menus without you asking for them. Your QA had to catch it.

That dynamic is reversed now. Engine improvements, bug fixes, and performance gains come through updates as before. But your editor UI stays exactly where you left it. New features arrive as optional building blocks, documented and ready when you want them.

No More Customization Ceiling
The old configuration APIs had a line between what you could change and what you couldn’t. Starter Kits remove that line entirely. You can restructure initialization, inject custom logic between loading phases, and build workflows specific to your product.

If you can see it in the code, you can change it.

If none of the five kits match your needs, the Editor view accepts raw configuration directly.

Migration

This is a breaking change on both iOS and Android. Migration guides cover every change with before-and-after examples.

→ Android Migration Guide
→ iOS Migration Guide

Starter Kit Repositories

Editor	iOS (Swift)	Android (Kotlin)
Photo	GitHub	GitHub
Design	GitHub	GitHub
Video	GitHub	GitHub
Postcard	GitHub	GitHub
Apparel	GitHub	GitHub

Export Vector Designs as SVG

Until now, users working with vector content in CE.SDK had no path to get that content out as a vector file. CE.SDK v1.73 adds SVG export via the image/svg+xml MIME type.

Text is exported as vector paths for consistent rendering across environments regardless of font availability. Drop shadows, blur, effects, and embedded raster images are rasterized and included as embedded images within the SVG output.

→ Exporting Blocks Engine Guide

Changelog

See the full changelog for the complete list.

Thanks for building with IMG.LY.

Join 3,000+ creative professionals who get early access to new features and updates. Subscribe.

PowerPoint Online: Native PPTX Editing in the Browser with CreativeEditor SDK

Klaudia — Fri, 17 Apr 2026 11:21:14 GMT

Organizations can now create workflows where presentations stay editable inside their own platforms: content management systems, collaboration tools, educational platforms, and SaaS applications, without switching to external editing software each time.

PowerPoint Import Capabilities

IMG.LY SDK enables importing PPTX files directly into browser-based workflows.

Import functionality
Existing PowerPoint files can be loaded directly into CE.SDK. The importer interprets the PPTX structure (text, images, shapes, and formatting), and converts each slide into an editable CE.SDK scene. Files can come from uploads or your own storage systems.

Editing interface
Once imported, slides become CE.SDK design scenes. Users can change content freely using CE.SDK’s editor, which keeps the structure intact, including text hierarchies and slide ordering.

What gets preserved: Text formatting (font families, sizes, colors, bold, italic), shapes (rectangles, ellipses, custom vector shapes), images, gradient fills, shadow effects, gradient backgrounds, groups, z-order, and theme colors are all carried over from the original PowerPoint file.

Editing Capabilities for Presentation Workflows

The browser-based editor includes the essential features needed for everyday presentation updates:

Text editing: Change text and adjust typography: fonts, colors, alignment, sizes, etc.
Visual element manipulation: Move, resize, rotate, and reorder shapes, images, and text boxes
Layer management: Adjust stacking order to control which content appears on top
Slide navigation: Rearrange slide order and quickly move between slides
Content addition: Add new images, shapes, or text elements when needed
Styling options: Edit fills, borders, and other visual properties

This helps teams refresh outdated content, localize presentations, update brand assets, or adapt a single deck to many different use cases, all without leaving the platform.

What’s Not Supported

The importer focuses on the most common presentation elements. Some PowerPoint features don’t carry over:

Tables — Table content is skipped on import; a workaround is to ungroup tables in PowerPoint before importing
Charts — Chart visualizations are not imported
SmartArt — Diagram graphics are not imported
Animations and transitions
Slide masters and layouts
Audio and video
Comments and notes
Background images — solid colors and gradients are supported, but image backgrounds are not

For presentations that rely heavily on these elements, it’s worth reviewing the output after import and making adjustments in CE.SDK.

Workflow Improvements with PowerPoint on the Web

Why this matters for real workflows:

Less switching between tools: Users can make changes right inside the system where the presentation is stored. It’s faster and reduces confusing file versions.

Accessible anywhere: Works on any modern browser, making editing possible on devices without native PowerPoint support.

Lower dependency on desktop software: Teams don’t always need Microsoft PowerPoint licenses just to update a slide or fix small mistakes.

Faster corrections: Updates become quick tasks. Improving slides doesn’t need to slow things down, especially for marketing or sales content.

Aligned with existing processes: Versioning, commenting, and permissions stay right where the content lives, which really simplifies collaboration.

Browser-Based Editing vs. Desktop PowerPoint

The browser-based editor covers the most common editing needs. PowerPoint on desktop still handles specialized features the importer doesn’t cover.

Capability	Browser-Based Editor	Desktop PowerPoint
Installation requirement	None — opens in the browser	Requires installation
Platform compatibility	Works on any device with a modern browser	Windows, macOS
Core content editing	Yes, for supported elements	Fully supported
Advanced features	Tables, charts, SmartArt, animations not supported	Complex animations, transitions, macros, advanced design
Integration	Easy embedding into web apps	Requires file transfer flow
Access speed	Instant, no launch time	Depends on local system
File compatibility	Imports PPTX; outputs CE.SDK scenes	Native PPTX with extended features
Collaboration	Connects with existing web-based systems	Microsoft ecosystem required
Network requirement	Can be edited offline	Can be offline

For straightforward content updates (text changes, image swaps, visual tweaks), the browser-based workflow handles most everyday needs. For presentations that rely on tables, charts, animations, or other advanced PowerPoint features, desktop PowerPoint remains the right tool.

Technical Implementation for Developers

The SDK handles PPTX parsing and slide rendering in the browser as CE.SDK scenes.

Fast integration: Setup usually takes hours or days, not months, since all the hard parts are already covered by the SDK.

Customizable interface: Developers can enable or disable features, apply brand styling, and connect to authentication and storage systems already in use.

Platform-agnostic: The package works in both browser and Node.js environments with no file system dependencies, using pure ArrayBuffer handling.

Controlled infrastructure: Everything runs where your platform runs, and you keep full control of data processing and access.

Use Cases Across Industries

EdTech: Students edit presentations directly in learning platforms without software installation.

CMS platforms: Teams update brand assets and sales decks in the same place they manage all other content.

Collaboration tools: Everyone works on the same version of a file without downloading and re-uploading.

SaaS products: Presentations become part of the workflow, not a separate step.

Creative agencies: Client slides can be adjusted quickly without leaving project management systems.

Getting Started

Try PowerPoint editing in the browser using our demo, or get started with CreativeEditor SDK to explore the full feature set.

CE.SDK v1.72 Release Notes

Neslihan — Fri, 03 Apr 2026 10:47:49 GMT

CE.SDK v1.72 is a massive design and creative capabilities release: Edit vector paths in your web editor. Generate AI images on mobile. Record voiceovers on iOS and Android, and format text with lists, underline, and strikethrough across every platform. Design and video scenes unify into a single editing surface on Web.

Let’s take a look!

Edit Vectors with Precision on the Web

CE.SDK now lets users edit any shape at the path level.

Select a shape and enter Edit Path mode. Manipulate individual anchor points and curves. Move nodes, bend segments, add or remove points. Lastly, apply fills, gradients, and colors.

In this example, we build our figure from a simple polygon shape:

Build custom icons, illustrations and detailed layouts directly in the web editor, without leaving your app.

→ Explore Vector Path Editing Documentation

Design and Video Editing In One Editor

Web users can now work across design and video in a single scene. Everything you can do in design mode, you can do in video mode too.

For your product, this means a simpler, more coherent editing experience for users who work across both formats.

Note: The feature toggle shown in the video is coming to our demos soon. It is not part of the default CE.SDK setup.

→ Visit CE.SDK 1.72 Migration Guide

Generate AI Images on Android and iOS

The AI image generation plugin now ships on iOS and Android.

This is the first mobile AI plugin for CE.SDK. Users can generate images directly inside the mobile editor through custom plugin panels, without leaving the creative workflow.

For your product, this means: you can now deliver AI-powered creative features on mobile with the same plugin architecture already available on web. One capability, every platform.

→ Try Android Mobile Demo
→ Try iOS Mobile Demo

Record Voice-Overs on Android & iOS

Tell your story by giving your videos a voice. iOS and Android users can now record their voice directly over video clips.

Layer multiple voiceover tracks on the timeline. Perfect to record engaging videos, like creators work in TikTok and Reels.

→ Try Android Mobile Demo
→ Try iOS Mobile Demo

Decorate Text On All Platforms

Updates for text editing land simultaneously across platforms:

Use Bullet and Numbered Lists to structure text with ordered and unordered lists. Underline and strike text, including custom underline colors.

Improvements

Rename Pages with Double Click
Web users can now rename pages directly on the canvas with a double click, without navigating to a separate settings panel.

Place Elements Anywhere with Infinite Canvas
Web Users can now place elements outside page boundaries. The canvas extends beyond the page, giving users a flexible workspace to park assets, build off-canvas elements. Work more freely without being constrained to the page frame.

Changelog

See the full list of fixes and breaking changes in the v1.72.0 Changelog and 1.72.0 Migration Guide.

Thank you for building with IMG.LY.

AI Design Agents and Creative Automation: How to Ship a Full Campaign Without a Designer

Klaudia — Wed, 01 Apr 2026 10:14:03 GMT

You have your files, hooks, Google Ads data but still can’t actually launch a campaign because you have to go to a designer for the final assets.

That gap is exactly where campaign momentum dies. Not at the strategy stage or in copy but at the last mile, when everything is ready except the thing people will actually see.

Luckily, it no longer has to.

The AI Marketing Stack Has a Design-Shaped Hole in It

Most marketing workflows have been quietly transformed over the last two years. Copy generation, audience segmentation, keyword research, performance analysis - all of it runs faster now, with less manual input. A solo marketer can do what used to require a team. Except for one part.

Design hasn’t moved. The workflow is still: write a brief, hand it to a designer, wait, review, revise, wait again. Then do the same thing in three more formats because the 1:1 you approved doesn’t fit Stories, Display, or LinkedIn. That loop can take days. And it doesn’t matter how good your AI-generated copy is if it’s sitting in a doc waiting for someone to have bandwidth.

This isn’t a resourcing problem. Hiring more designers doesn’t fix the structural issue; it just adds capacity to a fundamentally slow process. The problem is that the tools built for design weren’t designed for the workflow a modern marketer actually runs. They expect a designer at the keyboard. They don’t expect a marketer with a campaign brief and a conversation window.

The result: campaigns that are otherwise fully automated still stall before they ship. The bottleneck moved from copy to creative. And most teams haven’t noticed yet, because design delays feel normal. They’ve always been there.

What an AI Design Agent Actually Changes

An AI design agent is an autonomous AI system, not a prompt-response tool. It plans, reasons, and executes design tasks independently. Given a goal, it breaks that goal into steps, uses the tools available to it, retains context across the session, and can self-correct when the output isn’t right. That’s the category: a system that drives the workflow rather than waiting for instruction at each step.

Most design agents deliver speed. The handoff that used to take days can happen in minutes. But the output is still a deliverable: a file you receive, use as-is, or move somewhere else. Most operate inside existing tools or generate assets you work with elsewhere. The speed is real, the editability usually isn’t. If something needs to change, you’re back to prompting from scratch.

CoDesign sits differently. It doesn’t hand you a finished asset. It gives you a working starting point on a real canvas. Layers, text boxes, placeholders - real assets you can continue to work with, in the same conversation, without leaving the session.

Brand consistency gets handled at the foundation. Load your brand kit once, including colors, fonts, logo, and layout rules, and every output that session respects those constraints. You’re not eyeballing hex codes or hoping the font looks right. The rules are applied from the start, not checked at the end.

Multi-format adaptation is where the time savings become concrete. A campaign that runs across Instagram, Google Display, LinkedIn, and print doesn’t produce four separate briefs and four separate rounds of designer revisions. You describe the formats you need, and the agent adapts the work. The campaign stays consistent across all of them.

The biggest shift isn’t speed, though that’s real. It’s that you stay in creative control throughout. There’s no handoff moment where you lose the thread and have to re-explain the brief to someone else. The context lives in the conversation.

How to Run a Campaign Production Session with CoDesign

This is the actual sequence. Walk through it once and the workflow becomes repeatable.

1.Start with the brief. Open CoDesign and describe the campaign in plain language. Audience, objective, platform, tone, any constraints. The more specific you are here, the less iteration you’ll need later. Treat it like briefing a senior designer who hasn’t worked with your brand before.

2.Generate copy variations before you open the canvas. Use whichever AI writing tool you already work with (ChatGPT, Claude, or whatever is in your stack) to produce multiple copy directions: headline hooks, body copy, CTAs. Get four or five versions per element. Copy and design are separate steps that feed into each other. Having real options ready before you start the design session means CoDesign has something specific to work with, not a blank brief waiting to be interpreted.

3.Feed the brief to the AI design companion. With copy variations ready, ask CoDesign to generate initial ad designs. Describe the format, the hierarchy you want, any layout preferences. You’ll get structured, editable designs on the canvas. Not a rendered image, but a working starting point with real layers.

4.Apply your brand kit. If you haven’t already, load your brand assets: logo, color palette, type system, approved imagery. The agent applies these rules to the designs. Every output from this point respects your brand standards automatically.

5.Adapt across formats. Tell the agent which formats you need. The social variant, the display variant, the vertical for Stories, the square for feed. Watch the layouts adapt to each context, maintaining the campaign idea and brand consistency across dimensions. If the hierarchy needs adjusting for a specific format, describe what’s not working and the agent fixes it in conversation.

6.Refine in conversation. This is where the canvas-based approach earns its value. You’re not generating new versions from scratch. You’re iterating on what’s already there, in the same session. “Move the logo to the bottom right. Try the headline in the lighter weight. Swap this layout for something with more white space.” Each exchange builds on the last, so the conversation stays grounded in what’s on the canvas rather than starting over from a new prompt.

7.Export and ship. When the designs are approved, export in the formats your media plan requires. The session context lives with the file, so if something needs to change post-launch, you’re not starting from zero.

One honest note: the quality of the output is proportional to the quality of the brief. Vague prompts produce generic starting points. Teams that invest two minutes in a specific, structured brief consistently get more usable first outputs than teams that describe the campaign in one sentence and expect the agent to fill in the gaps.

This Is What Closing the Loop Actually Looks Like

Design agents don’t replace designers. They remove the bottleneck that sits between strategy and execution.

The marketer who used to wait three days for ad assets can now produce a full campaign set in a single session. The designer who spent half their week on format resizes and small-copy tweaks can spend that time on the work that genuinely requires their judgment. That means brand-defining creative, campaign concepts, and anything where taste and experience are the actual input.

It was never about willingness to collaborate. The tools just didn’t allow for anything else. Every design change, no matter how small, had to go through a handoff. A headline adjustment on a banner resize does not need a creative director. A resize from 1:1 to 9:16 does not need a brief, a Slack message, and a 48-hour turnaround.

Thanks to design agents conversation shifts. It moves from “can you make this” to “how should this look.” And that’s a way more interesting conversation.

Interested in trying IMG.LY CoDesign? Reach out to our team.

What Is an AI Design Agent?

Klaudia — Mon, 30 Mar 2026 04:52:01 GMT

The phrase “design agent” is being used in two completely different ways right now, and the confusion is worth clearing up before either meaning becomes the default. Search for it today and you’ll mostly find AI design agencies - services firms that use AI in their process. That’s a reasonable business, but it has nothing to do with what this article is about.

The second meaning, a design agent as a category of AI tool, is the one that matters for product builders, developers, and creative teams trying to understand where AI-assisted design is actually going. That’s what we’re defining here: what it is, how it works, how it differs from tools you already know, and why the distinction matters if you’re building or evaluating creative software in 2026.

First, What an AI Design Agent Is Not

An AI design agency. This is a services firm that uses AI tools in its creative process. It’s a completely different category - a service, not a tool - and it’s the most common result you’ll find when you search “design agent” right now.

An AI image generator. Midjourney, DALL-E, and similar tools produce images from text prompts. They generate a single output from a single instruction.

An AI feature inside a design tool. Figma’s AI suggestions, auto-layout assistance, and background removal are AI features. They augment a manual workflow making specific tasks faster.

A design automation pipeline. Server-side systems that batch-generate assets from templates are automation, not agency. They’re fast and scalable, but they don’t converse, can’t interpret an ambiguous brief, and don’t refine their output in response to feedback. The confusion here is understandable: modern automation systems use AI models internally and can produce polished, varied-looking results that are easy to mistake for something more intelligent. But give one an ambiguous brief and it either fails or produces something technically correct that misses the point entirely. Give a design agent the same brief and it asks a question. That distinction - executing a fixed process versus reasoning about intent - is what separates the two categories.

The distinction matters because “design agent” is becoming a meaningful category term, and what it actually describes is different enough from all of the above that collapsing the distinctions creates real confusion, both for people evaluating tools and for people building products.

AI Design Agent - a Working Definition

There is no settled definition of an AI design agent yet, the term is still early. Based on what we see in the tools that genuinely deliver on the promise, three properties distinguish a real design agent from something that merely resembles one:

1. Autonomy. The agent takes multi-step actions without requiring a human instruction at each step. Given “create a five-page product catalog in a Scandinavian minimal style,” it works out the layout, typography, and image placement independently and produces the result.

2. Conversational interface. The agent communicates in natural language. It can ask clarifying questions, explain what it’s done, and accept follow-up instructions. The interaction feels like briefing a designer, not operating software.

3. Refinement loop. The agent takes feedback across multiple conversation turns: “make the typography lighter,” “apply the brand’s warm color palette”, and updates the design accordingly. This iterative loop is what separates a design agent from a one-shot generation tool.

A tool that has all three of these properties is a design agent. A tool that has one or two is something else; probably useful, but in a different category. IMG.LY CoDesign is built against exactly this bar: it takes a brief, works through the layout on its own, and refines the result in conversation.

How an AI Design Agent Works in Practice

An abstract definition only takes you so far. Here’s what a fully implemented design agent workflow actually looks like, drawn from a real demo of IMG.LY CoDesign. CoDesign runs as a design MCP server, which means the same agent can also work from Claude, Cursor, or any other MCP client, not just a built-in chat panel.

Step 1. The user opens CoDesign. The agent interface - a chat panel - sits alongside the canvas. They’re in the same window.

Step 2. The user types a brief: “Here’s a CSV of five products from our furniture brand. Generate one landscape catalog page per product — two-column grid, full-bleed photo left, typography-led layout right. Clean, minimal. Think Hay, Muuto, Frama.”

Step 3. The agent processes the brief, the data, and any brand context it has access to. It generates a five-page catalog in the editor: product names, descriptions, prices, photo placeholders, layout structure consistent across all five pages.

Step 4. The user reviews the output and follows up in the chat: “Nice. Pre-fill the photo placeholders with black-and-white product photography, soft contrast.”

Step 5. The agent updates the design. The user manually adjusts one headline, corrects a price, and exports.

The full workflow, from brief to print-ready output, took minutes rather than hours. The user never left the tool. The agent handled all structural and stylistic decisions. The human handled final judgment and small corrections.

But generating layouts from a brief is only part of what a design agent can do. In the same chat interface, the agent can build functional decision-making tools directly inside the editor. Ask it to create a Color Themes panel, and it produces a working component: five named presets, each one applying a complete color theme across the entire design in a single click. The user doesn’t switch to a settings screen or manually update individual elements. The agent has built the control they need, right where they need it, as part of the same conversation. That’s a meaningfully different capability: not just producing a designed output, but constructing the tools that let the user make better decisions about that output as they finalize it.

This table is meant as a fair comparison, each column represents how these tool categories actually behave today:

Capability	AI Image Generator	AI Design Features	Design Agent
Takes a brief	Prompt only	No	Yes
Produces editable layouts	No	Partial	Depends on a tool
Multi-step autonomy	No	No	Yes
Conversational refinement	No	Limited	Yes
Brand / context awareness	No	Partial	Yes
Iterative across a session	No	No	Yes

The pattern here isn’t that design agents are better at everything - it’s that they operate at a different level of the workflow. Image generators and AI design features are task-level tools. A design agent is a workflow-level tool.

There’s one adjacent term worth separating out too: vibe design, the workflow where you describe what you want instead of building it manually. A design agent is one way to run a vibe design workflow, but the tools behind it differ a lot in what they hand back. We’ve compared the AI design tools built around this workflow if you want to see how they stack up.

Agentic Design vs. AI Design Agents: What’s the Difference?

“Agentic design” and “AI design agent” look interchangeable, and they’re starting to get used that way, but they describe different things.

Agentic design is a practice: the set of patterns and decisions involved in building systems where an AI acts with some autonomy. How much the agent does before checking in, when it asks a clarifying question, how it surfaces what it changed - these are agentic design questions, and they apply to coding agents and support agents just as much as to creative tools.

An AI design agent is a product: a tool that applies that practice to design work specifically. The autonomy slider in the next section is a good example of the overlap. Deciding where that slider sits is agentic design; the tool you move it in is a design agent. If you’re evaluating tools, you’re shopping for a design agent. If you’re building one, you’re doing agentic design.

Creative Agents: The Wider Category

Zoom out one level and design agents sit inside a wider family: creative agents. A creative agent is any AI agent that produces creative output autonomously - copy, video, music, imagery, or design. Design agents are the branch of that family that works in layouts, typography, and brand systems.

The defining properties carry across the family: autonomy over multi-step work, a conversational interface, and a refinement loop. What changes is the medium and the tooling around it - an agent cutting video needs a timeline the way a design agent needs a canvas. Keeping the levels straight helps when you’re mapping the space: the creative agent is the category, the design agent is its design-specific branch, and the products above are competing to define what that branch looks like.

The Autonomy Slider: Why Human Control Still Matters

One of the most important design decisions when building or evaluating a design agent is how much autonomy the AI exercises by default.

Full autonomy is fast. The agent makes all decisions and presents a finished output. But it can produce results that don’t match the user’s actual intent, especially when the brief is ambiguous or the stakes are high.

Minimal autonomy is safe. The agent only suggests, the human decides everything. But at that point, you’ve lost much of the value of having an agent in the first place.

The best implementations give users what you might call an autonomy slider: the ability to let the agent run with full independence on some tasks, take targeted direction on others, and step aside entirely when the user wants to edit manually. The right level of autonomy depends on the task and the user’s confidence, not a fixed setting applied uniformly across every interaction.

For any design agent, this means the interface needs to let the user reach in and adjust manually, mid-workflow, without losing what the agent has already done. The agent and the editor have to exist in the same environment. Separate windows with an export step between them break the loop entirely.

Where AI Design Agents Create the Most Value

Not every creative workflow benefits equally from an AI agent. The scenarios where design agents consistently create the most value tend to fall into three categories:

High-volume, high-variation creative production. Marketing teams producing dozens of ad variants, e-commerce teams generating product imagery at scale, publishers creating template-based content in bulk. A team can brief the agent once: brand colors, copy, format specs, and get 40 properly formatted variants back in the time it would have taken to manually produce three, each one consistent with the last.

Non-designer users who need professional results. Not everyone who needs to produce a designed output is a designer. Marketers, retailers, operations teams, small business owners - they know what they want but don’t have the tools or time to build it manually. A design agent gives them a way in that doesn’t require either.

Expert designers who want to explore faster. Experienced designers using the agent to generate starting points, explore multiple directions quickly, or offload the time-consuming production work while retaining full control over the final result. A designer can spend 20 minutes reviewing six distinct layout directions the agent generated from a single brief, rather than a full afternoon building each one from scratch.

These aren’t exhaustive categories, but they represent the use cases where the workflow-level shift actually changes what’s possible, not just what’s faster.

A Different Kind of Design Tool

A design agent makes creative work faster and more accessible. For designers who want to explore more directions in less time, and for non-designers who have always known what they wanted but lacked the tools to build it.

That’s what IMG.LY CoDesign is built around: editable designs straight from your agent, inside a fully featured design editor. The local MCP server is free to install and run, or get in touch if you want to talk it through with the team.

Frequently Asked Questions

What is an AI design agent?

An AI design agent is an AI tool that takes a design brief in natural language, produces an editable design on its own, and refines it through conversation. Three properties define the category: multi-step autonomy, a conversational interface, and a refinement loop. A tool that has all three is a design agent; a tool with one or two belongs to a different category.

How is an AI design agent different from an image generator?

An image generator produces a single flat image from a single prompt. A design agent works at the workflow level: it interprets a brief, makes multi-step layout and typography decisions, produces structured output you can edit element by element, and takes feedback across a session.

Do AI design agents replace designers?

No. The most effective setups keep a human in charge of direction and final judgment. Non-designers use agents to reach professional results they couldn’t build manually; experienced designers use them to explore more directions in less time while keeping full control over the result.

Are AI design agents free?

It varies by tool. Google Stitch is free during its beta with monthly generation limits, Figma Make requires AI credits, and IMG.LY CoDesign’s local design MCP server is free to install and run, with no account needed to start.