optimized demos for Wan 2.2 14B models, using FP8 quantization + AoT compilation & community LoRAs for fast & high quality inference on ZeroGPU 💨 • 3 items • Updated 4 days ago • 5

LTX Video 13B and 13B distilled models for video generation by Lightricks • 5 items • Updated 20 days ago

fast & compact video generation with FramePack - a next-frame prediction neural network structure that generates videos progressively • 9 items • Updated May 26 • 6

CausVid is a distilled version of Wan 2.1 to run faster in just 4-8 steps, extracted as LoRA by Kijai and is compatible with 🧨 diffusers • 2 items • Updated May 26 • 1