zai-org/CogVideo
text and image to video generation: CogVideoX (2024) and CogVideo (ICLR 2023)
Official repository for LTX-Video
text and image to video generation: CogVideoX (2024) and CogVideo (ICLR 2023)
Scalable and memory-optimized training of diffusion models
A unified library of SOTA model optimization techniques like quantization, pruning, distillation, speculative decoding, etc. It compresses deep learning models for downstream deployment frameworks like TensorRT-LLM, TensorRT, vLLM, etc. to optimize inference speed.
Official implementation of AnimateDiff.
Helios: Real Real-Time Long Video Generation Model
Improved AnimateDiff for ComfyUI and Advanced Sampling Support
1 capture since 2026-05-25