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.
Detaylı Özellikler
Genel Bakış:
Model Sağlayıcı:OTHERS
Model Türü:image-to-video
Dağıtım:Çıkarım API'si; Playground
Fiyatlandırma:$0.198
Ana Özellikler:
Boyut Sınırı:Maks genişlik × yükseklik (özel)
LoRA Desteği:Hayır
Seed Seçenekleri:N/A
