kijai/ComfyUI-FramePackWrapper

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

1686 stars · 124 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

A ComfyUI custom node wrapper for FramePack, enabling next-frame video generation from images using HunyuanVideo-based diffusion models. It supports native text encoders, VAE, and SigCLIP models with automatic model downloading.

Use cases

• generate videos from a single image in ComfyUI
• run FramePack image-to-video models as ComfyUI nodes
• create long videos with next-frame prediction
• use HunyuanVideo FramePack models with fp8 quantization
• build video generation workflows in ComfyUI

When to choose

• you already use ComfyUI and want FramePack video generation
• you want node-based workflows for image-to-video generation
• you want faster FramePack inference with fp8 model support

When to avoid

• you need a standalone video generation app without ComfyUI
• you need production-stable, fully supported software
• you don't have a GPU or the required VRAM for diffusion models

Facets

plugin · maturity active

video-processing image-processing machine-learning llm-inference machine-learning artificial-intelligence python cross-platform comfyui custom-nodes framepack hunyuan-video image-to-video diffusion-models video-generation video gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="kijai/ComfyUI-FramePackWrapper")