The open creative AI workspace, not just a diffusion editor.
ComfyUI is a node editor focused on Stable Diffusion and diffusion image generation, with engineer-first UX. NodeTool is the studio around it: image, video, music, and words on one canvas; a much wider model roster across providers and modalities; editing tools creatives actually use — called with your own keys at provider prices. Both are node-based and open source.
ComfyUI
Node editor for diffusion images
- Deep control over Stable Diffusion pipelines
- Engineer-first, graph-based UX
- Local model focused
- Open source community
NodeTool
The studio around the canvas
- Image, video, audio, and text on one canvas
- Every major model from every major provider
- Editing tools: masks, inpaint, relight, layers
- BYOK at provider prices — no credits, no markup
| Feature | ComfyUI | NodeTool |
|---|---|---|
| Modalities | Diffusion images | Image, video, audio, text |
| Model roster | Stable Diffusion / diffusion | Every major provider & modality |
| BYOK / provider billing | ||
| Editing tools (masks, inpaint, relight, layers) | ||
| Local models | ||
| Desktop + browser | ||
| Open source |
One canvas for everything, not just images
If your work starts and ends with Stable Diffusion images, ComfyUI gives you fine-grained control. But most creative projects span modalities — image into video, voice and music into a cut, words into everything. NodeTool keeps image, video, audio, and text on one node-based canvas with the editing tools you reach for built in: masks, inpaint, outpaint, relight, upscale, layers, and compositing. You call every major model from every major provider with your own keys at provider prices — no credits, no markup, no curated roster — and run locally too via Ollama, MLX, and llama.cpp.
Open, multimodal, and yours.
Download Studio and build across image, video, audio, and text in one place.