#4848th of 75 in Image and videoFor image, video and design, video and animation
openjutsu
Next.js front end for swapping characters and objects in video via ComfyUI
- Stars
- 2.2k
- License
- MIT
- Last commit
- Oct 2026
- Language
- TypeScript
144 on 27 Oct 20262,243 on 10 Nov 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
Openjutsu replaces the main person in a video with a character from a photo, or edits hair, clothes and objects, while keeping camera, cuts, motion and soundtrack. It is a small Next.js app over ComfyUI workflows that use MiniMax H3 for video, SAM 3.1 for tracking and Qwen3-VL 8B for describing frames. Modes include simple and multi-person swap, object change/remove/add, picture-based relighting, face fixing and colour grading.
Who it is for: Self-hosters with an NVIDIA GPU and ComfyUI who want local video character swaps
Strengths
- Covers single and multi-person swap, object edit, face fix and colour grading in one UI
- Check mask previews SAM tracking in about a minute before a full render
- Pre-flight check lists missing custom nodes and model files with destinations
- Runs on open weights locally; tested on a 16 GB RTX 4060 Ti
Weaknesses
- Needs about a dozen ComfyUI custom node packs plus many large model files
- Slow: a 6 s clip at 480p takes about 6-13 minutes on a 4060 Ti
- Mirrors and reflections do not work; the original person leaks into the result
- Requires ComfyUI 0.41.2+, an NVIDIA GPU and 64 GB RAM in the tested setup
What it needs
- RAM ≥ 64 GB
- GPU required
- Needs ComfyUI 0.41.2+, comfy-api-proxy 0.1.6, Node.js 22.6+, Python, ComfyUI custom node packs (SolarRenderer, KJNodes, VideoHelperSuite, comfyui-h3-oneclick-swap and others)
- Models: MiniMax H3, SAM 3.1, Qwen3-VL 8B INT8, Qwen3-VL 4B FP8, Gemma 4 E2B INT8
- port 3000
Also in Image and video
See all 75| Rank | Project | Score |
|---|---|---|
| 1 | frigateLocal NVR with realtime object detection for IP cameras | 93 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 | 87 out of 100 |
| #4 | InvokeAIWeb UI for diffusion image generation with inpainting canvas and node workflows | 86 out of 100 |
| #5 | ComfyUINode-graph editor for running diffusion image, video, audio and 3D workflows | 85 out of 100 |