ComfyUI
ComfyUI is a node-graph engine to generate images, video, 3D and audio with diffusion models.
Tested on Linux
Use it
Linux x86_64
You need first
- Runtimes:
python 3.13
Install comfy-cli via uv tool (candidate 1)
uv tool install comfy-cliClone ComfyUI source shallow
git clone --depth 1 https://github.com/Comfy-Org/ComfyUI.git ComfyUI
Check that it works
comfy --version 2>&1The output should contain “"ok": true”.
First thing to try
python3 -c "import json; d=json.load(open('ComfyUI/default_workflow.json')); print('nodes:', len(d['nodes'])); print('links:', len(d['links'])); print('version:', d.get('version')); print('has KSampler:', any(n.get('type')=='KSampler' for n in d['nodes']))"What it does
- Build workflows with visual node graphNot tested
- Generate images, videos, 3D and audioNot tested
- Run diffusion models efficiently locallyNot tested
- Save and load workflows as JSONNot shown working
How far pickfit got
Linux x86_64
- Installs
- Starts
- 0 of 4 features work
- Works offline
macOS and Windows: the project says it runs there; pickfit hasn’t tried it.
Good for
- generate images, videos, 3D models and audio
- inpaint, outpaint, upscale and edit images
- share and reuse workflows as JSON
How pickfit tested it
Each run starts from a clean machine and follows the steps above. How pickfit verifies
Linux x86_64
Its main function works
- Replayed from scratch
- Works offline
- Checked on 4 Nov 2026
- Version 1.25.0
Differences the test machine hit
- README: pip install comfy-cli
In the test: uv tool install comfy-cli into an isolated environment - README: pip install -r requirements.txt then python main.py
In the test: python3 ComfyUI/main.py --help prints full options with exit 0 and no dependency install (arg parsing runs before torch imports)