# stepfun-ai/Step-Video-T2V

Repository: https://github.com/stepfun-ai/Step-Video-T2V
Canonical: https://ross.abutalabs.com/products/step-video-t2v
Language: Python
License: MIT
License Family: permissive
Last push: 2025-03-17T03:26:54+00:00

## Health v2 (maintenance only)
Score: 25/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 11, release rhythm 35, longevity 40
- inputs: {"age_days": 571, "days_push": 534, "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 3187, forks 340 (observed 2026-08-28T04:07:48.064308+00:00)

## What it is
Step-Video-T2V is an open-source text-to-video generation model from StepFun, released with inference code and pretrained weights (including a Turbo variant). It generates videos from text prompts using a deep generative model.

## Use cases
- generate videos from text prompts
- run a text-to-video diffusion model locally
- download open-source video generation model weights
- build an image-to-video pipeline
- experiment with state-of-the-art video synthesis models

## When to choose
- you need a self-hosted text-to-video model with open weights
- you want an MIT-licensed video generation model to fine-tune or extend
- you need fast inference via the Turbo variant

## When to avoid
- you lack a high-VRAM GPU for inference
- you need a hosted API rather than running models yourself
- you need video editing rather than generation

## Facets
- artifact type: library
- maturity: active
- function: video-processing, machine-learning, deep-learning, llm-inference
- domain: artificial-intelligence, deep-learning, image-processing
- platform: python
- tags: text-to-video, video-generation, diffusion-model, generative-ai, model-weights, video, gpu, linux

## Member repositories
- stepfun-ai/Step-Video-T2V (main) score 25

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:48.064308+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 2026-08-30T07:24:59.340252+00:00, confidence not recorded.
  - readme: https://github.com/stepfun-ai/Step-Video-T2V (fetched 2026-08-28T04:07:48.064308+00:00, sha ffbe044b3281)
- Data as of 2026-08-30T08:39:29.467469+00:00.