Ktlyst is a web-based reference canvas for concept artists, illustrators, and visual creators. You gather references on one canvas — drag in images, GIFs, or video frames, or import a whole Pinterest board in one click — and Ktlyst explores new concept directions guided only by the references you chose (a feature called Catalyze). It runs in any modern browser on desktop and tablet, with cloud sync and a free plan.

What is the best PureRef alternative for iPad and tablet?

Ktlyst is a web-based reference board that runs in any browser — including Safari on iPad — with cloud sync so your boards follow you between desktop and tablet automatically. Unlike PureRef, which has no iOS or iPad app, Ktlyst is designed for cross-device creative workflows from the ground up. No installation needed.

Is there a PureRef that works on iPad?

PureRef does not have an official iOS or iPad app. Ktlyst fills that gap: it runs in any browser, syncs your reference boards to the cloud, and works on iPad, tablet, and desktop with the same canvas — so your references are always with you wherever you create.

How does Ktlyst compare to PureRef?

PureRef is a desktop-only overlay tool for keeping reference images visible while you paint or model in other apps. Ktlyst is a cloud-synced, browser-based alternative that adds: iPad and tablet support, Pinterest board import in one click, smart organisation with tagging and collections, freehand sketching overlaid on references, the ability to grab specific frames from videos and GIFs, and a concept-exploration layer (Catalyze) that explores new directions guided by your own references. No installation required — it works in any modern browser.

Do I need to learn prompts or any special tools?

No. You work the way you already do — gather references, sketch, note what you're after. Ktlyst handles the rest behind the scenes, so you stay focused on the vision, not on tooling.

Is this just an image generator?

No. Ktlyst is a reference-driven canvas for clarifying YOUR direction — built around how you already work, collecting references and browsing Pinterest. What it surfaces is an exploration of your own references, for you to take forward.

Can I bring in my Pinterest boards?

Yes. Connect Pinterest and pull an entire board onto a canvas in one move — every pin laid out and ready, instead of saving and re-uploading each one. (Free: 1 board · Pro: unlimited.)

Can I use videos or GIFs as references?

Yes. Drop an MP4, WebM, MOV, M4V, or OGV video — or a GIF — and a frame picker opens so you can scrub through and grab the exact frames you want. Only the frames you pick are saved as reference images; the source video or GIF never leaves your device. (Frame-by-frame GIF picking needs a recent browser; older ones add the first frame instead.)

Can I reuse the same character or element across projects?

Yes. Distil a group of references into one clean, typed element (a character, a costume, a prop), then save it to your Elements library. Drag it onto any canvas to reuse it, merge it with other elements, or paint it into a composition sketch — build it once, use it everywhere.

Can I correct a generated image?

Yes, with Redline (a Pro feature): draw your corrections in red straight on the image — arrows, circles, and handwritten notes — and Ktlyst applies them beside the original, non-destructively, so your original stays put.

Who owns what I create?

Ktlyst claims no ownership over your canvases or the directions you explore — they're yours to take forward into your own work. You're responsible for clearing any rights you need before using output commercially. (How copyright applies to generated images varies by country, so we don't make legal guarantees about that.)

Do you use my images or art to train AI?

No. Ktlyst never uses your uploads, canvases, or prompts to train AI models, and never sells them. Your references and prompts are sent to our AI providers only to generate or analyse images at your request. OpenAI does not use data submitted through its API to train its models; fal.ai processes your content under its own terms to run the generation.

Does it work on tablet?

Yes. Your canvas is cloud-synced, so you can collect on desktop and refine on tablet — or anywhere you work.

What devices and browsers does Ktlyst support?

Editing works on tablets and desktops (iPad, Windows, Mac) in recent versions of Chrome, Edge, Safari and Firefox. Phones get a view-only experience. Ktlyst runs in the browser and needs an internet connection.

Is there a free plan?

Yes — the free plan gives you 5 canvases (each with as many references as you like) and 15 Catalyze runs a month. No credit card required.

August 17, 2026

No-Prompt AI Art Generators in 2026: Whisk, Atomm AI, Freeform Diffusion, and Ktlyst Compared

no-prompt ai generatorprompt-free ai artreference image aiai moodboardconcept art toolsai image generation without text

If you'd rather not write a paragraph of prompt engineering just to get a usable image, you have real options now. Whisk (Google's remix tool, now folded into Google Flow) builds a single image from a Subject, Scene, and Style photo. Atomm AI generates quick variations of one uploaded photo. Freeform Diffusion, part of Playform, learns the shared style across a batch of references and generates new images in that style. And Ktlyst turns a whole board of references into a starting point for concept art — without ever asking you to type a sentence.

They're all "no-prompt," but they're built for different jobs. This guide breaks down how each one actually works, so you can tell the difference between a party trick and a tool that fits into a real creative workflow.

Why "no prompt" is suddenly everywhere

Text-to-image tools made prompting a skill in itself — and for a lot of visual thinkers, that was the wrong interface from the start. If you already have a folder of references, a Pinterest board, or a wall of mood images, describing what you want in words means translating something visual into language and back again. That translation loses nuance every time.

The tools below all try to skip that step by letting an image — or a set of images — do the talking instead of a prompt. Where they differ is what they do with those images once you hand them over.

How each tool actually works

Whisk (now part of Google Flow)

Whisk launched as a standalone Google Labs experiment built around three image slots — Subject, Scene, and Style — which Gemini captions and Imagen then turns into a new single image in under a minute. Google has since merged Whisk's core remixing feature into Google Flow, its unified AI video and image platform, so Whisk is no longer a separate destination. The workflow is still no-prompt in spirit (you pick images, not words), but it's built for fast one-off remixes, not for managing an evolving set of references over a project.

Atomm AI (Image Variations)

Atomm's Image Variations tool is a free, browser-based utility: upload one photo, and it generates a batch of alternate takes with different lighting, color, or style while keeping the subject and composition intact. It's genuinely no-prompt and fast, but it's a single-image variation generator — there's no concept of a project, a growing reference board, or reusable characters and props. It's closer to a quick remix button than a workspace.

Freeform Diffusion (Playform)

Freeform Diffusion is closer in spirit to what concept artists actually do: you upload a collection of images — sketches, references, or finished work — and a lightweight model extracts the shared aesthetic across all of them, then generates new images in that style. Like Ktlyst, it treats a group of references as the input rather than a single photo. The difference is in what it's optimized for: Freeform Diffusion is positioned for bulk, on-brand content generation (thumbnails, product shots, marketing visuals), not for the iterative, "what if I pushed this direction further" process of concept art and visual development.

Ktlyst

Ktlyst starts from the same instinct artists already have: gather your references onto one board. Drop in images, GIFs, or video frames, or pull in a whole Pinterest board in one move, and group them into Sections — one mood, one idea, one place. Ktlyst's Auto essence extraction reads what's common across the images you've collected, and you can distill any section into a reusable, typed element — a character, a costume, a prop — that carries forward into your next canvas. When you're ready, one click of Catalyze explores a new concept guided only by what you gathered, and a Floating reference window keeps it open on top of whatever painting or modeling tool you're actually working in.

The important distinction: Ktlyst isn't trying to hand you a finished image. It's built to speed up the ideation stage — the part where you're still figuring out direction — not to replace the judgment calls that come after. As Ktlyst's own homepage puts it: you stay the artist, it just helps you see where your references are headed. We covered the broader shift away from typing prompts in our earlier look at prompt-free AI image generation, and how that same "essence extraction" idea plays out for style consistency in our guide to AI mood boards for concept artists.

Side-by-side comparison

	Whisk / Google Flow	Atomm AI	Freeform Diffusion	Ktlyst
Input	3 images (Subject/Scene/Style)	1 image	Batch of images	Full reference board, grouped into Sections
Output	One remixed image	Batch of variations on one photo	Batch of new images in a shared style	A new concept to react to, plus reusable elements
Reusable characters/props	No	No	No	Yes (typed elements, Collections)
Pinterest import	No	No	No	Yes, one move
Built for	Fast single remixes	Quick photo variation	Bulk on-brand content	Iterative concept art & visual development
Standalone product	Folded into Google Flow	Yes	Yes (part of Playform)	Yes

Which one should concept artists actually use?

If you need one quick remix of a single photo, Atomm AI or the remix feature inside Google Flow will get you there fastest. If you're generating batches of on-brand marketing images from a style reference, Freeform Diffusion is built for that job.

But if your work looks like most concept art and illustration workflows — a growing pile of references, a character or environment you're developing over weeks, a direction that needs to stay consistent across dozens of pieces — none of the single-shot tools really fit. That's the gap Ktlyst is built for: a place to keep collecting references the way you already do in PureRef or Pinterest, and a way to turn that collection into a next direction without losing the thread — or handing over the creative decisions. See how that comparison holds up more broadly in Ktlyst vs Ideogram Character.

FAQ

Do any of these tools require writing a prompt? No — all four are built around images rather than text. Whisk/Flow needs three reference images, Atomm AI needs one, Freeform Diffusion and Ktlyst both work from a collection of references you gather yourself.

Is Ktlyst just another AI image generator? No. Ktlyst is a reference board first — closer to PureRef or a moodboard tool — with a generation step (Catalyze) built in to help you explore a direction from what you've already collected. The output is a starting point to react to and refine, not a finished piece, and the creative decisions stay with you.

Can I reuse a character or prop I've already created in these tools? Not in Whisk/Flow, Atomm AI, or Freeform Diffusion — each generation is a one-off. Ktlyst lets you save a reference group as a typed element or a Collection so it carries into your next canvas.

None of this replaces your eye. These tools generate a starting point; you're still the one deciding what's worth pushing further, what's off, and what actually belongs in the final piece. If your process already starts with gathering references, try Ktlyst free and see what a board built for that process actually feels like.