bilibili/Index-anisora

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

2505 stars · 149 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

Index-AniSora is Bilibili's open-source anime video generation model, capable of creating video shots in diverse anime styles from images, text, or masks. It ships model weights (V3/V3.1/V3.2) with support for arbitrary-frame inference, character 3D video generation, video style transfer, and low-VRAM inference.

Use cases

• generate anime video clips from a single image
• create animation shots in different anime styles
• convert live-action video to anime style
• generate VTuber or manga-adaptation style footage
• run anime video generation on a 12GB VRAM GPU
• control animation motion with spatial and temporal masks

When to choose

• you need open-source anime/animation video generation with permissive Apache-2.0 weights
• you want image-to-video or style-transfer tuned specifically for anime aesthetics
• you have a GPU and want controllable generation via masks and motion scores

When to avoid

• you need photorealistic video generation rather than anime styles
• you have no GPU or limited VRAM for diffusion model inference
• you need a polished end-user application rather than model weights and inference code

Facets

library · maturity active

machine-learning deep-learning video-processing image-processing llm-inference deep-learning machine-learning artificial-intelligence media python anime-video-generation image-to-video text-to-video diffusion-model video-style-transfer model-weights bilibili video gpu linux

Member repositories

For agents

markdown · JSON · MCP: product_card(name="bilibili/Index-anisora")