ali-vilab / TeaCacheLinks
Timestep Embedding Tells: It's Time to Cache for Video Diffusion Model
☆875Updated 2 weeks ago
Alternatives and similar repositories for TeaCache
Users that are interested in TeaCache are comparing it to the libraries listed below
Sorting:
- Official repo for CFG-Zero*☆596Updated last month
- A pipeline parallel training script for diffusion models.☆1,154Updated last week
- ☆719Updated this week
- 📹 A more flexible framework that can generate videos at any resolution and creates videos from images.☆1,106Updated this week
- Enhance-A-Video: Better Generated Video for Free☆543Updated 3 months ago
- (CVPR 2025) From Slow Bidirectional to Fast Autoregressive Video Diffusion Models☆618Updated last month
- ☆521Updated 5 months ago
- A set of ComfyUI nodes providing additional control for the LTX Video model☆494Updated 3 months ago
- [ICLR2025 Spotlight] SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models☆2,037Updated this week
- ☆1,177Updated 2 months ago
- Training-free Regional Prompting for Diffusion Transformers 🔥☆655Updated 6 months ago
- Scalable and memory-optimized training of diffusion models☆1,189Updated 2 weeks ago
- Nodes for image juxtaposition for Flux in ComfyUI☆1,342Updated 5 months ago
- ☆830Updated this week
- 🔥🔥 UNO: A Universal Customization Method for Both Single and Multi-Subject Conditioning☆1,128Updated 2 months ago
- ☆990Updated last month
- ☆1,500Updated this week
- Lumina-Image 2.0: A Unified and Efficient Image Generative Framework☆726Updated 3 weeks ago
- https://wavespeed.ai/ Context parallel attention that accelerates DiT model inference with dynamic caching☆300Updated last month
- ☆439Updated 2 weeks ago
- https://wavespeed.ai/ [WIP] The all in one inference optimization solution for ComfyUI, universal, flexible, and fast.☆1,062Updated 2 months ago
- ☆728Updated 7 months ago
- A novel approach to hunyuan image-to-video sampling☆303Updated 4 months ago
- FastVideo is a unified framework for accelerated video generation.☆1,538Updated this week
- A minimal and universal controller for FLUX.1.☆1,639Updated 2 weeks ago
- A set of nodes to edit videos using the Hunyuan Video model☆476Updated 4 months ago
- ☆786Updated 7 months ago
- Official implementation of the paper: "FlowEdit: Inversion-Free Text-Based Editing Using Pre-Trained Flow Models"☆637Updated 5 months ago
- Start and end frames video generation nodes based on the modified Kijai version Wan2.1 nodes☆351Updated 3 months ago
- ☆548Updated this week