--- license: apache-2.0 library_name: diffusers pipeline_tag: image-to-video tags: - normal-estimation - video - diffusion - svd --- # NormalCrafter — Video Normal Map Estimation Mirror of [Yanrui95/NormalCrafter](https://huggingface.co/Yanrui95/NormalCrafter) hosted by [AEmotionStudio](https://huggingface.co/AEmotionStudio) for use with [ComfyUI-FFMPEGA](https://github.com/AEmotionStudio/ComfyUI-FFMPEGA). ## Model Description NormalCrafter generates **temporally consistent surface normal maps** from video using a Stable Video Diffusion (SVD) backbone fine-tuned for normal estimation. Unlike image-based methods (e.g., Marigold), NormalCrafter operates natively on video sequences, producing smooth frame-to-frame normals without flickering. ## Key Features - **Video-native**: Processes temporal sequences for coherent normals across frames - **SVD backbone**: Built on `stabilityai/stable-video-diffusion-img2vid-xt` - **High resolution**: Supports up to 1024px inference - **Apache-2.0 Licensed**: Free for commercial and personal use ## Model Files | File | Size | Description | |------|------|-------------| | `unet/diffusion_pytorch_model.safetensors` | 3.05 GB | Fine-tuned UNet for normal estimation | | `image_encoder/model.fp16.safetensors` | 1.26 GB | CLIP image encoder (fp16) | | `vae/diffusion_pytorch_model.safetensors` | 196 MB | VAE decoder | ## Usage in ComfyUI-FFMPEGA NormalCrafter is available as: - **Standalone skill**: `normalcrafter` in the FFMPEGA agent - **No-LLM mode**: Select `normalcrafter` in the agent node dropdown - **AI Relighting**: Enable "Use NormalCrafter" in the Video Editor's Relight panel for physically-based relighting ## Citation ```bibtex @article{normalcrafter2024, title={NormalCrafter: Learning Temporally Consistent Normals from Video Diffusion Priors}, author={Yanrui Bin and Wenbo Hu and Haoyuan Wang and Xinya Chen and Bing Wang}, year={2024} } ``` ## License - **Model weights** (this repo): **Apache-2.0** — matching the upstream [Yanrui95/NormalCrafter](https://huggingface.co/Yanrui95/NormalCrafter) HuggingFace repo. See [LICENSE](LICENSE). - **Source code**: **MIT** — as published at [Binyr/NormalCrafter](https://github.com/Binyr/NormalCrafter) on GitHub. Both licenses are permissive and allow commercial use. ## Links - **Paper**: [NormalCrafter](https://github.com/Binyr/NormalCrafter) - **Upstream weights**: [Yanrui95/NormalCrafter](https://huggingface.co/Yanrui95/NormalCrafter) - **ComfyUI-FFMPEGA**: [AEmotionStudio/ComfyUI-FFMPEGA](https://github.com/AEmotionStudio/ComfyUI-FFMPEGA)