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.
Spesifikasi Lengkap
Gambaran Umum:
Penyedia Model:OTHERS
Tipe Model:image-to-video
Deployment:API Inferensi; Playground
Harga:$0.198
Spesifikasi Utama:
Batas Ukuran:hingga lebar × tinggi (dapat dikonfigurasi pengguna)
Dukungan LoRA:Tidak
Opsi Seed:N/A
