rzgar/Wan2.2_I2V_LightX2V_Slow-Mo_Fix

🤗 On Hugging Faceimage-to-videoapache-2.06.3 GBother✓ Checksum-verifiedupdated 0d ago
Magnet

Wan2.2 I2V LightX2V - Slow-Motion Fix

_(update: uploaded 260412 4step lora variant)_

Wan_2_2_I2V_lightx2v_Distill_260412_rank_128_fp16 originally extracted from lightx2v/Wan2.2-Distill-Models wan2.2_i2v_A14b_lightx2v_4step_720p_260412.safetensors

Rank_256 & 64

_Left: These LoRAs | Right: LightX2V 260412 rank_128_

Your browser does not support the video tag.

_Left: These LoRAs | Middle: Distill | Right: Comfy-Org (SEKO)_

Your browser does not support the video tag.

_Prompts: woman sprinting - man running_

Model description

The default ComfyUI Wan2.2 I2V workflow ships with LightX2V LoRAs that tend to turn scenes into slow motion:

These slow-mo fix LoRAs target that problem. More natural motion without breaking the 4-step LightX2V usage pattern and quality. In practice they also feel among the fastest-looking LightX2V-style pairs released for Wan2.2 I2V (less drag, less “slow-mo” pacing).

| File | Download |

|------|---------|

| wan2.2_i2v_lightx2v_motion_fix_high.safetensors | Wan2.2 I2V high noise |

| wan2.2_i2v_lightx2v_motion_fix_low.safetensors | Wan2.2 I2V low noise |

Strength: 1.0 on both · Steps: 4 (same idea as other LightX2V setups)

🙏 Acknowledgements

LightX2V

Download model

Download them in the Files & versions tab.