Convert your own photo into 7 illustration, anime and painting styles at once. Great for social-media avatars and profile pictures. Photos never leave your device.
The first run downloads an AI model (about 50 MB); later runs use the copy stored in your browser. Nothing but the model is transferred and your images are never uploaded.
There are two tools for turning photos into illustrations. Choose by your device and what you want. We suggest trying the lightweight one first and moving to the diffusion model if you want more.
| Criteria | Illustration & painting stylesThis page | AI illustration (diffusion) |
|---|---|---|
| Method | Lightweight GANs (AnimeGANv2 / fast-neural-style) that swap only the visual style | Diffusion model (LCM Dreamshaper v7) that repaints the photo from a prompt |
| Requirements | Works without WebGPU, including phones and older laptops | WebGPU required, 4GB+ of GPU memory (shared memory on integrated GPUs) |
| First download | About 8MB per style, about 50MB for all 7 | About 2.1GB. Currently around 10 minutes due to our server's bandwidth |
| Time per image | Under a second with WebGPU, a few seconds on CPU | 20–40 seconds on an integrated GPU, a few seconds on a discrete GPU |
| Style control | Pick from 7 fixed styles | 5 presets plus free-form English prompts |
| Result | Composition, expression and facial features stay intact; rarely fails | Richer, painterly results; higher strength drifts away from the original face |
| Best for | Quick avatars, or devices with modest specs | Gaming PCs or Apple Silicon Macs, and people who want fine control over the style |
Drop the photo you want to stylize. Portraits suit the illustration styles; landscapes suit the painting styles.
“All” generates 7 variations at once. The first run downloads each style model (about 8 MB each).
The results appear side by side. Click a thumbnail to save it, or save everything as a ZIP.
The three illustration styles use AnimeGANv2 (MIT licence): face_paint for portraits, paprika for an anime-film look including backgrounds, and celeba_distill for a sketch-like result. The four painting styles use fast-neural-style (oil paint, mosaic, pointillism, abstract) and also suit landscapes and buildings.
Each model is about 8 MB; with WebGPU a style takes under a second, and a few seconds without it. There is no free-form prompting as with diffusion models, but results are instant and the composition and expression of the photo are preserved.
No. The models are downloaded into your browser and the conversion runs on your device.
“Illustration (portrait)” is the most suited to people. “Anime (Paprika)” works when you want the background painted too; “Sketch-like” suits simple avatars.
No. It keeps the composition and facial features and changes only the rendering style; it does not produce caricatures.
The 7 styles are fixed. If you want to specify the style with a prompt, use “AI illustration (diffusion)”, which repaints the photo with a diffusion model. It needs WebGPU and a 2GB+ download, but gives far more freedom.
If a conversion fails, sending us the circumstances helps us track down the cause. Knowing which devices and formats fail most often, and how long processing takes, lets us revise the supported formats and fix the bugs behind them. If you don't mind, leaving this on is a real help.
What is sent
The tool you used and the settings you chose (output format, quality, etc.), your device specs (GPU, memory, core count), the input format with a rough size, how many files succeeded or failed and how long it took, and the error type and details when something fails.
What is never sent
The files themselves, file names, text, subtitles or prompts you add to a video, and IP addresses. The data goes only to this site's own server, never to a third-party service.