# wenhaochai/StableVideo

[ICCV 2023] StableVideo: Text-driven Consistency-aware Diffusion Video Editing

Repository: https://github.com/wenhaochai/StableVideo
Canonical: https://ross.abutalabs.com/products/stablevideo
Homepage: https://rese1f.github.io/StableVideo/
Language: Python
License: Apache-2.0
License Family: permissive
Topics: aigc, computer-vision, diffusion-model, video-editing, controlnet
Last push: 2023-09-07T04:02:23+00:00

## Health v2 (maintenance only)
Score: 31/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 92
- inputs: {"age_days": 1291, "days_push": 1091, "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 1439, forks 87 (observed 2026-08-28T04:04:44.063924+00:00)

## What it is
StableVideo is the official ICCV 2023 implementation of text-driven, consistency-aware diffusion-based video editing built on ControlNet and neural layered atlases. It ships as a Python/Gradio app that takes a video plus a text prompt and renders an edited .mp4 with temporal consistency.

## Use cases
- edit videos with text prompts
- apply diffusion-based video editing to a clip
- change the style of a video using text
- reproduce StableVideo ICCV 2023 results
- run text-driven video editing locally with ControlNet
- edit foreground regions of a video with a mask

## When to choose
- you want research-grade text-driven video editing with temporal consistency
- you have a GPU with ~14-29GB VRAM and want to run the paper's method
- you need an editable foreground atlas with mask control
- you want a reproducible implementation of an ICCV 2023 paper

## When to avoid
- you need a polished production video editor rather than research code
- you only have a low-VRAM GPU or CPU-only machine and need fast results
- you need active updates or new feature development
- you want one-click editing without preparing NLA atlases and ControlNet checkpoints

## Facets
- artifact type: application
- maturity: maintenance
- function: video-processing, image-processing, machine-learning, stable-diffusion, gui
- domain: computer-vision, artificial-intelligence, image-processing
- platform: python, windows
- tags: diffusion-models, video-editing, controlnet, iccv-2023, research-code, gradio, text-driven-editing, video, gpu, linux, macos

## Member repositories
- wenhaochai/StableVideo (main) score 31

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:44.063924+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 2026-08-30T04:36:37.729480+00:00, confidence not recorded.
  - readme: https://github.com/wenhaochai/StableVideo (fetched 2026-08-28T04:04:44.063924+00:00, sha 13b68195e651)
- Data as of 2026-08-30T08:39:29.467469+00:00.