| --- |
| license: apache-2.0 |
| datasets: |
| - KlingTeam/MultiCamVideo-Dataset |
| - KlingTeam/SynCamVideo-Dataset |
| base_model: |
| - alibaba-pai/Wan2.1-Fun-V1.1-1.3B-Control-Camera |
| base_model_relation: finetune |
| pipeline_tag: video-to-video |
| tags: |
| - pytorch |
| --- |
| |
| This model was presented in [FlashRender: Few-Step Generative Rendering via Camera-Controlled Video MeanFlow](https://huggingface.co/papers/2609.03563). |
|
|
| Please refer to the [Github](https://github.com/byeongjun-park/FlashRender) README for usage. |
|
|
| ## Checkpoints |
|
|
| | Stage | File | Sampling | |
| |:---:|---|---| |
| | 1 | `epoch_20.safetensors` | 50 steps, `inference_mode=mul` | |
| | 2 | `meanflow_epoch_20.safetensors` | 4 steps, `inference_mode=any` | |
| | 3 | `onpolicy_epoch_5.safetensors` | 4 steps, `inference_mode=any` | |
|
|
| **`onpolicy_epoch_5.safetensors` is the final model** and the default in `configs/base.yaml`. |
|
|
| Each file stores only the **trainable parameter subset**, not a stand-alone diffusers/transformers |
| checkpoint. Weights are `bfloat16`, except the relative-pose tokens and the per-block RoPE phase MLPs |
| (`rel_pose_{src,tgt}_token`, `self_attn.rope_phase_{qk,vo}`), which are stored in `float32`. |
| They are loaded with `strict=False` onto the base Wan DiT after it is patched by |
| `flashrender_utils.model_utils.adjust_to_FlashRender`, so use the code repository: |
|
|
| ```python |
| from huggingface_hub import snapshot_download |
| |
| snapshot_download( |
| repo_id="byeongjun-park/FlashRender", |
| local_dir="models/checkpoints", |
| allow_patterns=["*.safetensors", "config.json"], |
| ) |
| ``` |
|
|
