AI & ML interests
None defined yet.
Recent Activity
View all activity
Pruned FastH3
-
FastVideo/FastVideo-FastH3-Trim-Comfy
Updated • 121k • 42 -
FastVideo/FastVideo-FastH3-Trim-8-Step
Text-to-Video • 19B • Updated • 629 • 8 -
FastVideo/FastVideo-FastH3-Trim-8-Step-NVFP4
Text-to-Video • 0.9B • Updated • 1.53k • 12 -
FastVideo/FastVideo-FastH3-Trim-8-Step-FP8
Text-to-Video • 19B • Updated • 418 • 2
FastMetal QAD INT8 text-to-video models for Apple Silicon
Four FastH3 4-Step Preview v1 T2VA checkpoints from FastVideo: VSA and dense attention, with data-free and synthetic-data recipes.
-
FastVideo/FastVideo-FastH3-4-step-Preview-v1-VSA-DataFree
Text-to-Video • 35B • Updated • 2k • 344 -
FastVideo/FastVideo-FastH3-4-step-Preview-v1-VSA-Synthetic-Step1300
Text-to-Video • 35B • Updated • 18 • 4 -
FastVideo/FastVideo-FastH3-4-step-Preview-v1-VSA-Synthetic-Step1900
Text-to-Video • 35B • Updated • 28 • 2 -
FastVideo/FastVideo-FastH3-4-step-Preview-v1-Dense-DataFree
Text-to-Video • 33B • Updated • 230 • 2
models trained with video sparse attention: https://arxiv.org/abs/2505.13389 and distillation
Pruned FastH3
-
FastVideo/FastVideo-FastH3-Trim-Comfy
Updated • 121k • 42 -
FastVideo/FastVideo-FastH3-Trim-8-Step
Text-to-Video • 19B • Updated • 629 • 8 -
FastVideo/FastVideo-FastH3-Trim-8-Step-NVFP4
Text-to-Video • 0.9B • Updated • 1.53k • 12 -
FastVideo/FastVideo-FastH3-Trim-8-Step-FP8
Text-to-Video • 19B • Updated • 418 • 2
Four FastH3 4-Step Preview v1 T2VA checkpoints from FastVideo: VSA and dense attention, with data-free and synthetic-data recipes.
-
FastVideo/FastVideo-FastH3-4-step-Preview-v1-VSA-DataFree
Text-to-Video • 35B • Updated • 2k • 344 -
FastVideo/FastVideo-FastH3-4-step-Preview-v1-VSA-Synthetic-Step1300
Text-to-Video • 35B • Updated • 18 • 4 -
FastVideo/FastVideo-FastH3-4-step-Preview-v1-VSA-Synthetic-Step1900
Text-to-Video • 35B • Updated • 28 • 2 -
FastVideo/FastVideo-FastH3-4-step-Preview-v1-Dense-DataFree
Text-to-Video • 33B • Updated • 230 • 2
FastMetal QAD INT8 text-to-video models for Apple Silicon
models trained with video sparse attention: https://arxiv.org/abs/2505.13389 and distillation