Image generation
IllusionDiffusion
Make images with a hidden picture that appears when you squint
★ 5.4k
May 2026
OpenRAIL
Image generation
What it does
Generates artwork with text or a shape concealed inside it: up close you see a landscape or pattern, but step back or squint and the hidden word emerges. You supply a description of the scene plus a high-contrast black-and-white image of what to hide. Thin lines and intricate lettering do not survive the process, so keep the hidden shape bold. The model's OpenRAIL++ licence allows commercial use but forbids certain applications.
Summary based on the project's own description. The Japanese page has a fuller beginner guide: setup difficulty, what to prepare, and a step-by-step start.
Screenshots & visuals
Before you start
- Setup difficultyEasy to start
- Command lineNot required
- API keyNot required
- Sends data onlineYes
Judged automatically from the project's own metadata. Always confirm on the official page.
IllusionDiffusion FAQ
- Do I need to install anything or write code to use IllusionDiffusion?
- No install needed — it runs in the browser.
- Does IllusionDiffusion work on a phone?
- No. It needs a computer.
- Can I use IllusionDiffusion commercially?
- The licence is OpenRAIL. Read the licence text before using it commercially.
How it compares
The conditions that decide whether you can actually use it, side by side.
| Tool | Command line | API key | Sends data out | Phone | Commercial use |
|---|---|---|---|---|---|
| IllusionDiffusion (this page) | Not needed | Not needed | Yes | No | With conditions |
| flux-style-shaping | Not needed | Not needed | Yes | Yes | With conditions |
| ComfyUI | Not needed | Not needed | No | No | Yes |
| Upscayl | Not needed | Not needed | No | No | Yes |
"Sends data out" means your input is uploaded to someone's server. Pick "No" when the material cannot leave your organisation.