#5454th of 56 in Image and videoFor image, video and design, image and design
comfyui-mixlab-nodes
ComfyUI custom node pack for prompts, layers, LLM calls and web-app export
- Stars
- 1.9k
- License
- MIT
- Last commit
- Jun 2026
- Last release
- Oct 2024
- Language
- JavaScript
1,807 on 21 Apr 20261,874 on 10 Nov 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
A ComfyUI custom node collection that adds LLM nodes (OpenAI-compatible endpoints, Siliconflow, local servers), prompt tools, image layer compositing, background removal, TripoSR 3D, and speech nodes. Its AppInfo node turns a workflow into a web app with chosen input and output nodes. It also adds screen-share input and fal.ai video generation nodes (Kling, RunwayGen3, LumaDreamMachine).
Who it is for: ComfyUI users who want LLM, prompt and web-app nodes in image workflows
Strengths
- AppInfo node publishes a workflow as a web app with selectable input and output nodes
- LLM nodes accept any OpenAI-compatible URL, including local servers and Azure OpenAI
- Includes rembg, TripoSR, LaMa inpainting and MiniCPM-V 2.6 int4 (about 7GB GPU memory)
- MIT licensed; installs by cloning into custom_nodes and running pip requirements
Weaknesses
- Last tagged release is 2024-10-14, though commits continue
- Requires a running ComfyUI install; not usable standalone
- Several models must be downloaded manually into specific models/ subfolders
- README mixes Chinese and English and has no structured docs; LaMa needs manual install
What it needs
- GPU optional
- Needs ComfyUI, Python 3.11, PyTorch 2.3.1+cu121, fal.ai API (video nodes), Siliconflow API (optional)
- Models: OpenAI-compatible LLM APIs, MiniCPM-V 2.6 int4, TripoSR, rembg models, LaMa
- port 8189
Quick answers
Is comfyui-mixlab-nodes open source?
Yes. Its code is on GitHub under the MIT license.
Does comfyui-mixlab-nodes need a GPU?
No. It runs on a CPU and can use a GPU when you have one.
Also in Image and video
See all 56| Rank | Project | Score |
|---|---|---|
| 1 | frigateLocal NVR with realtime object detection for IP cameras | 92 out of 100 |
| 2 | MoneyPrinterTurboGenerates short videos from a topic, with script, footage, voiceover and subtitles | 88 out of 100 |
| 3 | toonflow-appInfinite-canvas tool for AI short drama and comic video production | 86 out of 100 |
| #4 | ComfyUINode-graph editor for running diffusion image, video, audio and 3D workflows | 85 out of 100 |
| #5 | InvokeAIWeb UI for diffusion image generation with inpainting canvas and node workflows | 85 out of 100 |