wenhaochai/StableVideo

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

1439 stars · 87 forks observed · 2026-08-28

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

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

application · maturity maintenance

video-processing image-processing machine-learning stable-diffusion gui computer-vision artificial-intelligence image-processing python windows diffusion-models video-editing controlnet iccv-2023 research-code gradio text-driven-editing video gpu linux macos

Member repositories

For agents

markdown · JSON · MCP: product_card(name="wenhaochai/StableVideo")