| base_model: Wan-AI/Wan2.1-T2V-1.3B | |
| pipeline_tag: video-to-video | |
| tags: | |
| - video-relighting | |
| - portrait-relighting | |
| - pytorch | |
| - arxiv:2611.06355 | |
| # FlashRelight | |
| Official inference checkpoints for **FlashRelight: Portrait Video Relighting with Dynamic Lighting** (NeurIPS 2026). [Paper](https://arxiv.org/abs/2611.06355) · [Code](https://github.com/vivoCameraResearch/FlashRelight) | |
| FlashDelight suppresses the original lighting in a portrait video. FlashRelight uses the delighted clip to synthesize lighting from an HDR environment map or a reference video. Text control works best with lighting descriptions similar to the training captions. The released models process 49 frames at 480 × 832 pixels. | |
| | Checkpoint | Size | Use | | |
| | --- | ---: | --- | | |
| | `flashdelight_rank0_full.pt` | 6.93 GB | First stage. Use it on its own for delighting or as the first step in relighting. | | |
| | `flashrelight_rank0_full.pt` | 7.04 GB | Second stage. Use it with FlashDelight for relighting. | | |
| ## Download | |
| From the FlashRelight code repository, download both checkpoints to the `weights` directory. | |
| ```bash | |
| hf download JiahuiSheng/FlashRelight flashdelight_rank0_full.pt flashrelight_rank0_full.pt --local-dir weights | |
| ``` | |
| For standalone delighting, download only `flashdelight_rank0_full.pt`. Both modes also use the shared Wan2.1 configuration, VAE, text encoder, and tokenizer. [Wan2.1 base files](https://huggingface.co/Wan-AI/Wan2.1-T2V-1.3B) | |
| <details> | |
| <summary>SHA-256 checksums</summary> | |
| ```text | |
| 04925b6ca8a4b537685a2791be65d0a51d2025fba8d2cb4ae17d4bf9530c1f5c flashdelight_rank0_full.pt | |
| 8b9989cdebd2d9815f3678baf4493fbf7c0ae65fe2c74756769e4f4df1c226d7 flashrelight_rank0_full.pt | |
| ``` | |
| </details> | |