| --- |
| license: apache-2.0 |
| tags: |
| - text-to-image |
| - lora |
| - diffusers |
| - template:diffusion-lora |
| base_model: |
| - Wan-AI/Wan2.2-I2V-A14B |
| --- |
| # Wan2.2 I2V LightX2V 2Step |
|
|
| <video controls width="100%" height="480"> |
| <source src="https://huggingface.co/rzgar/Wan2.2_I2V_LightX2V_2Step/resolve/main/video/ComfyUI_00002.mp4" type="video/mp4"> |
| Your browser does not support the video tag. |
| </video> |
| <Gallery /> |
|
|
|
|
| Fast LightX2V LoRAs for **Wan2.2 I2V** image-to-video. |
| Tuned for **2 steps high + 2 steps low** setup. |
|
|
|
|
| ___ |
| |
| |
| | File | Load on | |
| |------|---------| |
| | `Wan2.2_I2V_LightX2V_2step_high_noise.safetensors` | [High-noise](https://huggingface.co/rzgar/Wan2.2_I2V_LightX2V_2Step/resolve/main/Wan2.2_I2V_LightX2V_2step_high_noise.safetensors) | |
| | `Wan2.2_I2V_LightX2V_2step_high_noise.safetensors` | [Low-noise](https://huggingface.co/rzgar/Wan2.2_I2V_LightX2V_2Step/resolve/main/Wan2.2_I2V_LightX2V_2step_low_noise.safetensors) | |
| |
| **Strength: 1.0** on both. |
| |
| --- |
| |
| ## Why use this? |
| |
| Standard LightX2V workflows run **4 steps per stage**. These LoRAs are tuned so you can run **2 steps per stage** and still get usable motion and prompt follow at roughly half the 4Step time. |
| |
| On my hardware, 81 f/s: |
| |
| | Setup | Resolution | Steps | Avg. time | |
| |-------|------------|-------|-----------| |
| | Default LightX2V | 512×848 | 4 + 4 | ~**89 s** | |
| | **This LoRA** | 512×848 | **2 + 2** | ~**37 s** | |
| |
| The time we spend on a **512×848** clip with 4Step LightX2V is about what it needs for **720×1280** with this pair. |
| |
| Best when you need **many previews**, prompt tests, or seed hunting, and care more about iteration speed than maximum fine detail. |
| |
| --- |
| |
| ___ |
| |
| Text-to-Video style: [input image](https://huggingface.co/rzgar/Wan2.2_I2V_LightX2V_2Step/resolve/main/video/white_bg.png) | [Prompt](https://huggingface.co/rzgar/Wan2.2_I2V_LightX2V_2Step/resolve/main/video/t2v_style.txt) |
| |
| <video controls width="100%" height="480"> |
| <source src="https://huggingface.co/rzgar/Wan2.2_I2V_LightX2V_2Step/resolve/main/video/video__00138.mp4" type="video/mp4"> |
| Your browser does not support the video tag. |
| </video> |
| |
| ___ |
| ## Recommended sampling |
| |
| **Schedulers that work well** |
| |
| | Sampler | Scheduler | |
| |---------|-----------| |
| | `dpmpp_2m_sde` | `sgm_uniform` | |
| | `dpmpp_2m_sde_heun` | `sgm_uniform` | |
| | `sa_solver_pece` | `sgm_uniform` | |
| |
| **Strength:** `1.0` high · `1.0` low |
| **Steps:** `2` high · `2` low |
| |
| ### Euler / Simple |
| |
| `euler` + `simple` still works, but **reliability drops**. Expect more duds, often about **2 good out of 4** runs. Prefer the samplers above when you want fewer re-rolls. |
| |
| <img src="https://huggingface.co/rzgar/Wan2.2_I2V_LightX2V_2Step/resolve/main/video/Screenshot_2Step_KSampler.png" width="1280" height="720" /> |
| |
| --- |
| |
| ## Quality expectations |
| |
| From a small random-seed test set (**9** generations): |
| |
| | Outcome | Count | Notes | |
| |---------|-------|-------| |
| | Clean motion, on-prompt, no body deformation | **6 / 9** | Usable “hero” candidates | |
| | Mild motion issues | **1 / 9** | Often still salvageable | |
| | Strong motion error | **2 / 9** | Reroll seed | |
| |
| So: most seeds are fine, a minority will need a new seed. That trade-off is kinda acceptable for speed. |
| |
| Compared with full 4-step LightX2V you may lose some fine detail and consistency. For final hero frames, you can still switch back to a 4-step stack. |
| |
| --- |
| |
| ## 🙏 Acknowledgements |
| [LightX2V](https://huggingface.co/lightx2v) | [Wan-AI](https://huggingface.co/Wan-AI) |
