mit-han-lab / nunchaku
[ICLR2025 Spotlight] SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models
☆1,463Updated this week
Alternatives and similar repositories for nunchaku:
Users that are interested in nunchaku are comparing it to the libraries listed below
- Timestep Embedding Tells: It's Time to Cache for Video Diffusion Model☆687Updated this week
- A pipeline parallel training script for diffusion models.☆909Updated this week
- Nodes for image juxtaposition for Flux in ComfyUI☆1,253Updated 3 months ago
- ☆1,470Updated 2 months ago
- ☆968Updated last month
- https://wavespeed.ai/ [WIP] The all in one inference optimization solution for ComfyUI, universal, flexible, and fast.☆969Updated 3 weeks ago
- FastVideo is a lightweight framework for accelerating large video diffusion models.☆1,337Updated this week
- ☆703Updated this week
- 📹 A more flexible framework that can generate videos at any resolution and creates videos from images.☆892Updated last week
- Quantized Attention that achieves speedups of 2.1-3.1x and 2.7-5.1x compared to FlashAttention2 and xformers, respectively, without lossi…☆1,329Updated this week
- Official repository of In-Context LoRA for Diffusion Transformers☆1,809Updated 4 months ago
- ☆703Updated 2 weeks ago
- ☆275Updated 3 months ago
- Enhance-A-Video: Better Generated Video for Free☆504Updated last month
- ☆564Updated this week
- ☆671Updated 5 months ago
- Memory-optimized training library for diffusion models☆1,048Updated last week
- Training-free Regional Prompting for Diffusion Transformers 🔥☆617Updated 4 months ago
- ☆775Updated 5 months ago
- LTX-Video Support for ComfyUI☆990Updated this week
- ☆602Updated 6 months ago
- A minimal and universal controller for FLUX.1.☆1,457Updated last week
- Various custom nodes for ComfyUI☆1,229Updated last week
- Lumina-Image 2.0: A Unified and Efficient Image Generative Framework☆642Updated 3 weeks ago
- ☆515Updated 3 months ago
- Official repo for CFG-Zero*☆434Updated last week
- 🔥🔥 UNO: A Universal Customization Method for Both Single and Multi-Subject Conditioning☆775Updated this week
- ☆369Updated this week
- ☆2,051Updated this week
- ComfyUI nodes to use segment-anything-2☆858Updated last month