ModelTC / LightX2VLinks
Light Video Generation Inference Framework
☆450Updated last week
Alternatives and similar repositories for LightX2V
Users that are interested in LightX2V are comparing it to the libraries listed below
Sorting:
- https://wavespeed.ai/ Context parallel attention that accelerates DiT model inference with dynamic caching☆356Updated last month
- Radial Attention Official Implementation☆483Updated 2 weeks ago
- The official code for "MagCache: Fast Video Generation with Magnitude-Aware Cache"☆191Updated this week
- Enhance-A-Video: Better Generated Video for Free☆567Updated 5 months ago
- [ICLR 2025] FasterCache: Training-Free Video Diffusion Model Acceleration with High Quality☆242Updated 7 months ago
- Timestep Embedding Tells: It's Time to Cache for Video Diffusion Model☆1,071Updated 2 months ago
- Official repo for CFG-Zero*☆651Updated 3 months ago
- Unofficial extension implementation of Self-Forcing to support I2V && 14B training.☆125Updated last month
- Official code for AccVideo: Accelerating Video Diffusion Model with Synthetic Dataset☆257Updated 2 months ago
- HunyuanVideo Keyframe Control Lora is an adapter for HunyuanVideo T2V model for keyframe-based video generation☆158Updated 4 months ago
- Official PyTorch Implementation of "Optimal Stepsize for Diffusion Sampling".☆185Updated 4 months ago
- ☆205Updated last week
- Repo for SeedVR2 & SeedVR (CVPR2025 Highlight)☆483Updated last month
- Pusa: Thousands Timesteps Video Diffusion Model☆592Updated this week
- [ICCV2025] From Reusing to Forecasting: Accelerating Diffusion Models with TaylorSeers☆266Updated last week
- [NeurIPS 2024] Boosting the performance of consistency models with PCM!☆489Updated 8 months ago
- A novel approach to hunyuan image-to-video sampling☆305Updated 6 months ago
- ☆284Updated 7 months ago
- ☆521Updated 7 months ago
- Stand-In is a lightweight, plug-and-play framework for identity-preserving video generation.☆468Updated this week
- Official implementation of MAGREF: Masked Guidance for Any-Reference Video Generation☆251Updated last month
- (CVPR 2025) From Slow Bidirectional to Fast Autoregressive Video Diffusion Models☆875Updated 2 weeks ago
- Community trainer for Lightricks' LTX Video model 🎬 ⚡️☆294Updated last month
- Wan2.2-Lightning: Speed up wan2.2 model with distillation☆108Updated 2 weeks ago
- [NeurIPS 2024] AsyncDiff: Parallelizing Diffusion Models by Asynchronous Denoising☆203Updated 6 months ago
- Official implementation of "Normalized Attention Guidance"☆159Updated last month
- MoviiGen 1.1: Towards Cinematic-Quality Video Generative Models☆171Updated last month
- ☆150Updated this week
- Unlimited-length talking video generation that supports image-to-video and video-to-video generation☆185Updated this week
- Practice Code for text to image trainer☆402Updated this week