Fix Wan 2.2 I2V base model detection and VRAM estimation
- Add correct base model for Wan 2.2 I2V: Wan-AI/Wan2.2-I2V-A14B-Diffuser - Add specific VRAM estimate for Wan 2.2 I2V MoE models (~14GB) - Apply more conservative VRAM calculation for models with weights/LoRAs - Fix indentation error in add_model_from_hf function
Showing
Please
register
or
sign in
to comment