| --- |
| license: other |
| license_name: wan-community |
| base_model: Wan-AI/Wan2.1-FLF2V-14B-720P |
| library_name: diffusers |
| tags: |
| - lora |
| - video |
| - image-to-video |
| - wan |
| - refvfx |
| --- |
| |
| # refVFX LoRA |
|
|
| LoRA adapter for [`Wan-AI/Wan2.1-FLF2V-14B-720P`](https://huggingface.co/Wan-AI/Wan2.1-FLF2V-14B-720P) trained to transfer a temporal visual effect from a *reference* video onto a separate input image or video. |
|
|
| ## Files |
|
|
| | File | Description | |
| | --- | --- | |
| | `epoch-0.safetensors` | LoRA model. | |
|
|
| ## Training |
|
|
| - **Base model:** `Wan-AI/Wan2.1-FLF2V-14B-720P` |
| - **LoRA rank:** 1024 |
| - **Target modules:** `q, k, v, o, ffn.0, ffn.2` (applied to the DiT) |
| - **Learning rate:** 4e-5, 200-step linear warmup |
| - **Frames per clip:** 33 |
| - **Max pixels:** 399,360 |
| - **Optimizer parallelism:** DeepSpeed ZeRO-1, 8 ranks |
| - **CFG dropout:** `p_drop_ref = 0.05`, `p_drop_control_video = 0.05` |
|
|
| Trained on [`maxwelljones14/refVFX_dataset`](https://huggingface.co/datasets/maxwelljones14/refVFX_dataset) (code-based edits + neural V2V edits + I2V LoRA effects, sampled as triplets). |
|
|
| ## Usage |
|
|
| Load the weights into a Wan2.1-FLF2V pipeline and inject them as a LoRA on the DiT (target modules above, `remove_prefix_in_ckpt="pipe.dit."`). See `infer_refvfx.py` in the [refVFX trainer repo](https://github.com/) for a reference implementation. |
|
|
| ## License |
|
|
| Inherits the base-model license from `Wan-AI/Wan2.1-FLF2V-14B-720P`. Use is subject to its terms. |
|
|
