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.

Подробные характеристики

Обзор:

Разработчик модели:OTHERS

Тип модели:image-to-video

Развертывание:API вывода; Playground

Цены:$0.198

Ключевые параметры:

Ограничение размера:до ширина × высота (настраивается пользователем)

Поддержка LoRA:Нет

Параметры seed:N/A

Создайте свой шедевр

Van-2.6 Text-to-video

A speed-optimized text-to-video option that prioritizes lower latency while retaining strong visual fidelity. Ideal for iteration, batch generation, and prompt testing.

$0.068/СЕК

НОВОЕ

изображение-в-видео

Van-2.6 Image-to-video

A speed-optimized image-to-video option that prioritizes lower latency while retaining strong visual fidelity. Ideal for iteration, batch generation, and prompt testing.

$0.068/СЕК