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.

July 16, 2026

You Don't Need to Write Prompts. The Era of AI Image Generation by Just "Arranging Reference Images"

No Prompts RequiredAI Image GenerationIP-AdapterControlNetReference Images

Have you ever tried AI image generation and thought, "I don't know how to write prompts," or "Even if I line up some words, it doesn't turn out like the picture I imagined"? Even after reading tutorial articles for Midjourney or Stable Diffusion tools, your hands just stop when it comes time to write them yourself—this is a path many artists go down at least once.

Actually, the gateway to AI image generation isn't just "writing prompts." There is a method to use the natural workflow you already do in illustration and painting—"gathering, arranging, and combining reference images"—as the direct trigger for generation. In this article, we'll outline why prompts feel so difficult, and introduce the Ktlyst approach, which lets you generate by simply arranging reference images, while comparing it with Midjourney and Stable Diffusion tools.

Why Do AI Image Generation "Prompts" Feel So Difficult?

In Midjourney and Stable Diffusion, you need to translate everything—subject, composition, art style, lighting, etc.—into words before handing it over to the AI. However, the images in our heads are inherently "pictures," not "words." The very act of translating visual information like color, texture, and atmosphere into accurate words is the biggest hurdle in creating prompts. The sheer volume of online articles explaining "how to write prompts and tips" speaks to the magnitude of this struggle.

The Concept of "Arranging Reference Images" Instead of Text

Ktlyst adopts a design that skips this "translation into words" step entirely. The idea is simple: the act of "gathering, arranging, and combining reference images" that artists routinely perform is used directly as a substitute for a prompt.

How What You See Becomes the Prompt

On the Ktlyst canvas, you can freely place images you want to reference. By simply arranging character references, background photos, color palettes, and rough sketches by roles such as "Main," "Background," and "Composition," you are ready to generate without writing any text.

The Ktlyst canvas. Just by arranging reference images by roles like "Draft," "Sketch," and "Composition," they become the materials for the next generation.

The Ktlyst canvas. Just by arranging reference images by roles like "Draft," "Sketch," and "Composition," they become the materials for the next generation.

"Automatic Theme Detection" That Reads Common Themes from Multiple References

Ktlyst has a built-in system where, when multiple images with the same role are gathered, the AI automatically reads the visual themes common to them. For example, simply by lining up a few photos of glowing jellyfish, the system detects the subject "bioluminescent jellyfish" and automatically reflects it in the prompt for the next generation. Users don't need to put "what they want drawn" into words; the collected images themselves become the spokesperson for their intent.

Differences from Midjourney and Stable Diffusion (ComfyUI)

Tools Built on the Premise of Writing Prompts

Major AI image generation services like Midjourney and DALL-E are fundamentally designed around text prompts. Even with better language support now, getting closer to your target picture requires carefully specifying the subject, composition, art style, and lighting in words, which takes time to get used to.

ComfyUI Systems That Require Node Connections and IP-Adapter/ControlNet Setup

ComfyUI, a Stable Diffusion-based tool, is appealing for its high degree of freedom, allowing you to incorporate non-text visual controls (like character transfer via IP-Adapter, or composition and background control via ControlNet). On the other hand, it requires manually connecting nodes to build a workflow, and we often see people say it "looks too difficult" or that they "gave up." In fact, many articles and experiences dealing with the struggle of "ComfyUI is difficult" are posted online.

Ktlyst Starts from "Just Arranging"

What Ktlyst aims for is a different entry point from these text-based or node-based workflows. Instead of connecting nodes, just arranging reference images on the canvas automatically applies the same kind of technology as IP-Adapter and ControlNet internally. Even if you don't understand how the mechanics work, the intuitive operation of "gathering and arranging" will lead you to visually highly-accurate generation.

IP-Adapter and ControlNet are Working Under the Hood

Even if we say "no prompts required," it's not magic. Behind Ktlyst's ability to achieve high-accuracy generation from reference images, proven technologies in the image generation field are being used.

IP-Adapter to Inherit Characters

Reference images placed as "Main" (subject) use a technology called IP-Adapter to transfer style and character features to the new image. IP-Adapter is great at directly reading nuances like "this kind of vibe for a character"—which are hard to explain in text—straight from a single image.

ControlNet-Depth to Preserve Background Depth

Reference images placed as "Background" are replaced with a new background while preserving the depth structure using ControlNet-Depth. It has the advantage of maintaining depth and spatial consistency much easier than trying to explain the background in text.

These technologies are normally used by building nodes in tools like ComfyUI, but in Ktlyst, they can be used without worrying about the backend settings just through the operation of "placing images by role."

How to Use Ktlyst: 3 Steps

Gather reference images——Place the images you have on hand onto the canvas, such as the character you want to draw, the landscape for the background, or color references.
Assign roles——Set roles for each image, such as "Main," "Background," or "Composition" (the AI also offers automatic suggestions).
Press Catalyze (Generate)——Generation begins from the combination of images you placed, even without writing text. You can also add supplementary text if necessary.

Recommended For

For those who take a lot of time translating prompts into words, those struggling with Midjourney or DALL-E not producing the picture they envisioned, or those who felt ComfyUI's node operations were too difficult and gave up, Ktlyst's approach of just arranging reference images might be a perfect fit. Conversely, for advanced users who want to intricately fine-tune parameters with text, traditional node-based tools may be better suited in some situations.

Summary

The struggle that "AI image generation prompts are difficult" is, in other words, "the task of translating the picture in your head into words is difficult." Ktlyst is designed to skip this translation task entirely and directly turn the act of "gathering and arranging reference images"—which artists do routinely—into the prompt itself, helping even those who are bad at text to arrive at an image close to their imagination. If you are struggling with how to write prompts, why not step away from text for a bit and try starting by arranging some reference images?