Hugging Face's logo
Efficient-Large-Model 's Collections
Sol-H3
Long-WAM
LongLive-Plug
SoL-Refiner
SANA Streaming
SANA-WM
SANA-Video
Fast-dLLM
NVILA
NVILA (HuggingFace)
LongAI
SANA-1.5
SANA-Sprint
Sana
VILA: On Pre-training for Visual Language Models
VILA-1.5-checkpoints-intermediate

Sol-H3

MiniMax-H3 video with sound on one RTX 5090 or DGX Spark. Code: github.com/NVlabs/Sana/tree/sol-engine/models/minimax_h3