FewStep RL for Wan models
Lightx2v
lightx2v
AI & ML interests
We are the Model-ToolChain team. We are interested in model compression and inference deployment for AI models.
Experience page: https://x2v.light-ai.top. Homepage: https://light-ai.top
Recent Activity
upvoted a paper 1 day ago
MeanFlowNFT: Bringing Forward-Process RL to Average-Velocity Generators new activity about 1 month ago
lightx2v/Wan2.1-T2V-1.3B-Distill-Models:what is this for? updated a collection about 1 month ago
FewStep RLOrganizations
-
lightx2v/Qwen-Image-Lightning
Text-to-Image • Updated • 418k • • 811 -
lightx2v/Qwen-Image-Edit-2511-Lightning
Image-to-Image • Updated • 334k • • 486 -
lightx2v/Qwen-Image-2512-Lightning
Text-to-Image • Updated • 77.6k • 221 -
lightx2v/Qwen-Image-Edit-Causal
Image-Text-to-Image • 20B • Updated • 2.73k • 18
Efficient autoregressive video generation (i.e., the Self-Forcing family) checkpoints.
FewStep RL for Wan models
-
lightx2v/Qwen-Image-Lightning
Text-to-Image • Updated • 418k • • 811 -
lightx2v/Qwen-Image-Edit-2511-Lightning
Image-to-Image • Updated • 334k • • 486 -
lightx2v/Qwen-Image-2512-Lightning
Text-to-Image • Updated • 77.6k • 221 -
lightx2v/Qwen-Image-Edit-Causal
Image-Text-to-Image • 20B • Updated • 2.73k • 18
Efficient autoregressive video generation (i.e., the Self-Forcing family) checkpoints.
Model collections trained with our framework: https://github.com/ModelTC/GenRL