---
license: apache-2.0
---

It's a merged model by me

Backed with these loras :

SVI_v2_PRO_Wan2.2-I2V-A14B_LOW_lora_rank_128_fp16

SVI_v2_PRO_Wan2.2-I2V-A14B_hIGH_lora_rank_128_fp16

lightx2v_T2V_14B_cfg_step_distill_v2_lora_rank256_bf16


Set 8 steps, cfg 2 on high noise and you'll get a nice result

Also I put a special workflow for those models and HunyuanVideoFoley to add sound towards videos