few-step
FastVideo-FastH3-4-step-Preview-v1-VSA-DataFree
Text to video model, used with diffusers.
- 345
- 767
- other
- 3 mo ago
hyperflow-h3-flash
HyperFlow H3 Flash: Video Rebirth's 13.7B, 4- to 8-step compressed MiniMax-H3 for joint video and audio generation (INT8 and GGUF)
- 242
- Python
- Apache-2.0
- 8 d ago
Qwen-Image-2.1-Uncensored-Omni-LoRA-v0.1
Text to image model, used with diffusers.
- 125
- 62k
- other
- 6 wk ago
NitroFusion2
Bringing Adversarial Loss to the Text Stream of MMDiTs
Runs in the browser on Hugging Face
- 5
- apache-2.0
- 10 d ago