Open and Advanced Large-Scale Video Generative Models.
Framepack
FramePack is a next-frame (next-frame-section) prediction neural network structure that generates videos progressively.
FramePack compresses input contexts to a constant length so that the generation workload is invariant to video length.
FramePack can process a very large number of frames with 13B models even on laptop GPUs.
FramePack can be trained with a much larger batch size, similar to the batch size for image diffusion training.
Specifications in Depth
Overview:
Model Provider:OTHERS
Model Type:image-to-video
Deployment:Inferencing API; Playground
Pricing:$0.198
Key Specs:
Size Cap:up to width × height (user-configurable)
LoRA Support:No
Seed Options:N/A
