#110 · Primary category: Image Generation
ComfyUI-InstantID
Unofficial implementation of InstantID for ComfyUI
Project last updated:05/22/24
GitHub Stars
1.4K
Forks
78
Contributors
1
License
Other
Why we included this project
ComfyUI users who need consistent faces across generated portraits can treat this as a workable bridge between InstantID and node-based workflows. The project repackages InstantID as a set of custom nodes: you hand it a reference face image, and it keeps that identity through the generation while an optional pose reference steers the composition. Loaders handle SDXL base models from Hugging Face or local paths, and the InsightFace, ControlNet, and IP-Adapter nodes keep the model wiring visible instead of hiding it. A bundled prompt styler offers eight preset styles, which makes it easier to produce varied portraits without writing prompt templates by hand. Since this is an unofficial port, it is worth comparing against the upstream InstantID repository for feature parity, but for a self-contained ComfyUI setup it covers the core identity-transfer pipeline well.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
stable-diffusion-webui
Stable Diffusion web UI
ComfyUI
The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.
diffusers
🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.
upscayl
🆙 Upscayl - #1 Free and Open Source AI Image Upscaler for Linux, MacOS and Windows.
InvokeAI
InvokeAI is a leading open-source creative engine for Stable Diffusion, offering an industry-leading web UI for generating and editing visual media.