T

EvanYu 81c84baab0 Merge pull request #14 from ComfyNodePRs/publish

Add Github Action for Publishing to Comfy Registry

2025-01-13 11:52:01 +08:00

.github/workflows

chore(publish): Add Github Action for Publishing to Comfy Registry

2025-01-11 01:28:15 +00:00

assets

main

2025-01-10 19:35:00 +08:00

examples

main

2025-01-10 19:35:00 +08:00

__init__.py

first commit

2025-01-07 17:06:20 +08:00

LICENSE

main

2025-01-08 14:32:48 +08:00

nodes.py

main

2025-01-10 19:35:00 +08:00

README.md

main

2025-01-11 13:51:45 +08:00

README.md

ComfyUI-TeaCache

Introduction

Timestep Embedding Aware Cache (TeaCache) is a training-free caching approach that estimates and leverages the fluctuating differences among model outputs across timesteps, thereby accelerating the inference. TeaCache works well for Image Diffusion models, Video Diffusion Models, and Audio Diffusion Models.

TeaCache has now been integrated into ComfyUI and is compatible with the ComfyUI native nodes. ComfyUI-TeaCache is easy to use, simply connect the TeaCache node with the ComfyUI native nodes for seamless usage.

Updates

Jan 10 2025: ComfyUI-TeaCache supports LTX-Video:
- It can achieve a 1.4x lossless speedup and a 1.7x speedup without much visual quality degradation.
- Support Text to Video and Image to Video!
Jan 9 2025: ComfyUI-TeaCache supports HunyuanVideo:
- It can achieve a 1.6x lossless speedup and a 2x speedup without much visual quality degradation.
Jan 8 2025: ComfyUI-TeaCache supports FLUX:
- It can achieve a 1.4x lossless speedup and a 2x speedup without much visual quality degradation.
- Support FLUX LoRA!
- Support FLUX ControlNet!