williamyang1991/Rerender_A_Video

Health v2 · maintenance only

Flags: no_releases no_license

Adoption not part of the score

2999 stars · 196 forks observed · 2026-08-28

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

The official PyTorch implementation of 'Rerender A Video', a SIGGRAPH Asia 2023 zero-shot text-guided video-to-video translation framework. It adapts text-to-image diffusion models to video using hierarchical cross-frame constraints and temporal-aware patch matching, without requiring training or fine-tuning.

Use cases

• translate a video into a new style using a text prompt
• apply stable diffusion styles to video with temporal consistency
• restyle video frames without training a model
• use controlnet or lora to guide video translation
• convert source video to anime or artistic style
• research code for zero-shot video-to-video translation

When to choose

• you want text-guided video restyling with temporal consistency
• you need a zero-shot approach with no training or fine-tuning
• you want to combine ControlNet or LoRA models with video translation
• you are reproducing or building on the SIGGRAPH Asia 2023 paper

When to avoid

• you need real-time video processing on consumer hardware
• you want a polished end-user product rather than research code
• you need production-grade licensing clarity (license is non-standard)
• you need fast inference on CPU-only machines

Facets

application · maturity stable

video-processing image-processing machine-learning deep-learning computer-vision artificial-intelligence image-processing python cross-platform stable-diffusion diffusion-models controlnet lora video-to-video text-guided zero-shot temporal-consistency pytorch research-paper video gpu linux

Member repositories

For agents

markdown · JSON · MCP: product_card(name="williamyang1991/Rerender_A_Video")