# bilibili/Index-anisora

Repository: https://github.com/bilibili/Index-anisora
Canonical: https://ross.abutalabs.com/products/index-anisora
Language: Python
License: Apache-2.0
License Family: permissive
Last push: 2026-07-16T08:14:26+00:00

## Health v2 (maintenance only)
Score: 62/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 92, release rhythm 35, longevity 44
- inputs: {"age_days": 625, "days_push": 48, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2505, forks 149 (observed 2026-08-28T04:06:57.112257+00:00)

## What it is
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
- artifact type: library
- maturity: active
- function: machine-learning, deep-learning, video-processing, image-processing, llm-inference
- domain: deep-learning, machine-learning, artificial-intelligence, media
- platform: python
- tags: anime-video-generation, image-to-video, text-to-video, diffusion-model, video-style-transfer, model-weights, bilibili, video, gpu, linux

## Member repositories
- bilibili/Index-anisora (main) score 62

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:57.112257+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T02:26:43.932291+00:00, confidence not recorded.
  - readme: https://github.com/bilibili/Index-anisora (fetched 2026-08-28T04:06:57.112257+00:00, sha 8ca73d9e233a)
- Data as of 2026-08-30T08:39:29.467469+00:00.