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.
Spécifications Détaillées
Aperçu :
Fournisseur du Modèle :OTHERS
Type de Modèle :image-to-video
Déploiement :Inference API; Playground
Tarification :$0.198
Paramètres Clés :
Limite de Taille :Jusqu'à Largeur × Hauteur (configurable par l'utilisateur)
Support LoRA :Non
Options de Seed :N/A
