# ShareGPT4Omni/ShareGPT4Video

[NeurIPS 2024] An official implementation of "ShareGPT4Video: Improving Video Understanding and Generation with Better Captions"

Repository: https://github.com/ShareGPT4Omni/ShareGPT4Video
Canonical: https://ross.abutalabs.com/products/sharegpt4video
Homepage: https://sharegpt4video.github.io/
Language: Python
License Family: other
Topics: chatgpt, gpt, gpt-4v, large-language-models, large-multimodal-models, large-vision-language-models, large-video-language-models, sora, text-to-video
Last push: 2024-10-09T20:36:13+00:00

## Health v2 (maintenance only)
Score: 24/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 58
- inputs: {"age_days": 818, "days_push": 693, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1093, forks 46 (observed 2026-08-28T04:03:33.745264+00:00)

## What it is
ShareGPT4Video is the official implementation of a NeurIPS 2024 paper providing a large-scale video-text dataset (40K GPT4V-generated captions plus millions of model-generated ones), a general video captioner (ShareCaptioner-Video), and an 8B large video-language model. It also demonstrates improved text-to-video generation using its high-quality captions.

## Use cases
- generate dense captions for videos
- train a video-language model for video understanding
- improve text-to-video generation with better captions
- caption videos of varying durations and resolutions
- build video question answering datasets

## When to choose
- you need high-quality video captions for training multimodal models
- you want a strong open video-language model or captioner
- you need a large video-text dataset for research

## When to avoid
- you need a production-ready product with support guarantees
- you lack GPU resources for large model inference or training
- you need a permissively licensed library - the repo has no license

## Facets
- artifact type: dataset
- maturity: active
- function: machine-learning, nlp, video-processing, data-generation
- domain: large-language-models, computer-vision, artificial-intelligence
- platform: python
- tags: video-captioning, video-text-dataset, multimodal, text-to-video, lvlm, gpt4v, neurips-2024, video, natural-language-processing, gpu, linux

## Member repositories
- ShareGPT4Omni/ShareGPT4Video (main) score 24

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:33.745264+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 2026-08-30T06:47:40.703124+00:00, confidence not recorded.
  - readme: https://github.com/ShareGPT4Omni/ShareGPT4Video (fetched 2026-08-28T04:03:33.745264+00:00, sha ae50d158b14d)
  - homepage: https://sharegpt4video.github.io/ (fetched 2026-08-29T12:50:43.785399+00:00, sha fb8fee908a9a)
- Data as of 2026-08-30T08:39:29.467469+00:00.