# Anime video generation

A fine-tuned anime-style text-to-video model based on the diffusers framework, supporting English input with an output resolution of 448x384 pixels.

A text-to-video model based on diffusers, fine-tuned via ModelScope for anime-style presentation, trained at 512x512 pixel resolution.

A text-to-video model fine-tuned on the diffusers framework, featuring distinct anime visual characteristics, trained at 512x512 resolution.

This is a text-to-video model based on diffusers, fine-tuned with modelscope to achieve an anime-style appearance, supporting 448x384 resolution.