Prism
+833We propose Prism, a dynamic sparse attention framework for natively training joint video-audio generation models at 2K.
diffusion-models
Chủ đề #diffusion-models trên GitHub — repository trong kho Beeknoee có gắn topic này.
- Repository
- 53
- Tổng sao
- 193k
- 24 giờ
- +0.1%
- 7 ngày
- +1%
- 30 ngày
- +1.7%
Repository trong #diffusion-models
FreeVideo
+203Make videos on the computer you already own. FreeVideo runs MiniMax H3 in as little as 8 GB of VRAM and 16 GB of RAM, and adapts its acceleration path to your hardware.
verl-omni
+67Multimodal RL training framework for diffusion & omni models
FastVideo
+74A unified inference and post-training framework for accelerated video generation.
DiffusionART
+34Official Implementation of "DiffusionART: Efficient, Stable and Scalable Reinforcement of Diffusion Models"
DiffusionOPSD
+74🔥 On-Policy Self-Distillation in Diffusion Models
openvino
+43OpenVINO™ is an open source toolkit for optimizing and deploying AI inference
LightX2V
+30Lightweight Image Video Action Generation Inference Framework
SolarWM
+24Open data and scalable training for long-horizon video world models.
Chủ đề khác
Các chủ đề phổ biến khác trong kho Beeknoee
