chengzeyi/Comfy-WaveSpeed
ComfyUI extension for optimized inference of diffusion models including FLUX, Wan, and Stable Diffusion.
Not currently ranked — collecting fresh signals.
star history
WaveSpeed is an all-in-one inference optimization solution for ComfyUI. It implements dynamic caching (First Block Cache) and enhanced torch.compile to accelerate diffusion model inference. The tool supports multiple model families including FLUX.1-dev, Wan 2.1 (text-to-video and image-to-video), LTXV, HunyuanVideo, and SD3.5/SDXL. It provides custom nodes and demo workflows for easy integration.
Frequently asked
- What is chengzeyi/Comfy-WaveSpeed?
- ComfyUI extension for optimized inference of diffusion models including FLUX, Wan, and Stable Diffusion.
- Is Comfy-WaveSpeed open source?
- Yes — chengzeyi/Comfy-WaveSpeed is open source, released under the MIT license.
- What language is Comfy-WaveSpeed written in?
- chengzeyi/Comfy-WaveSpeed is primarily written in Python.
- How popular is Comfy-WaveSpeed?
- chengzeyi/Comfy-WaveSpeed has 1.2k stars on GitHub.
- Where can I find Comfy-WaveSpeed?
- chengzeyi/Comfy-WaveSpeed is on GitHub at https://github.com/chengzeyi/Comfy-WaveSpeed.