metadata
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 · Code
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.
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
SHA-256 checksums
04925b6ca8a4b537685a2791be65d0a51d2025fba8d2cb4ae17d4bf9530c1f5c flashdelight_rank0_full.pt
8b9989cdebd2d9815f3678baf4493fbf7c0ae65fe2c74756769e4f4df1c226d7 flashrelight_rank0_full.pt