Free Image Colorizer
Image Colorizer adds color to black-and-white or faded photos with the DDColor AI model, keeping the original resolution and sharpness. A strength slider from 0 to 150% softens or intensifies the colors, and several photos can be downloaded together as a ZIP. Skin, sky and vegetation usually look convincing, while clothes or signs may differ from reality.
- Model:
- DDColor tiny, about 135 MB
- Strength:
- 0 to 150%
- Output:
- Full-size JPG, PNG or WebP
- Price:
- Free
- Runs:
- AI model in your browser
- Uploads:
- None: files never leave your device
- Account:
- Not needed
Quick answers
Are my photos uploaded?
No. The colorization model runs in your browser; only the model itself is downloaded from Hugging Face. Your photos never leave your device.
Will the colorized photo lose resolution?
No. The model only predicts the colors on a small copy; the lightness and all the detail come from your original, so the result has exactly the same size and sharpness.
Processed on your device: your files are never uploaded. How it works
Network activity in this tab
What this page has requested since you opened the site in this tab. An upload is any request that sends data: POST, PUT, PATCH or a request with a body.
No uploads: nothing has been sent from this page.
No network requests yet.
To see every request, open your browser's developer tools (Network tab).
How to use the Image Colorizer
- Drop one or more black-and-white or faded photos.
- Click Colorize: the first time, the AI model (about 135 MB) is downloaded and cached.
- Compare before and after with the slider and adjust the color strength.
- Download the full-resolution result as JPG, PNG or WebP, or all photos as a ZIP.
Credits & open source
Open-source AI model running in your browser. Thank you to the people who make these projects.
- ONNX Runtime WebExecutes ONNX models with WebGPU or WebAssembly (self-hosted from /vendor/ort). © Microsoft Corporation · MIT
- fflateFast ZIP compression for batch downloads. © Arjun Barrett · MIT
Web platform APIs used: Web Workers, WebAssembly, Canvas 2D, createImageBitmap, File API.
- DDColor tiny (fp16 ONNX) by Xiaoyang Kang, Tao Yang, Wenqi Ouyang, Peiran Ren, Lingzhi Li, Xuansong Xie (DDColor); ONNX export by Edge Tools (Apache-2.0) — AI model that predicts the colors
Full license texts: third-party notices · all credits
Frequently asked questions
Are the colors historically accurate?
They are the model's best guess from shapes and textures. Skin, sky and vegetation are usually convincing, while clothes, cars or signs may get different colors from the real ones.
Can I make the colors softer or stronger?
Yes. The color strength slider goes from 0% (black and white) to 150% (very vivid), and the preview updates immediately.
How long does it take?
The model runs on your processor, which gives correct colors on every device: a photo takes from a few seconds to about a minute, depending on your computer. The first time, the model download adds some time.