FoxBaze/Try_On_Qwen_Edit_Lora_Alpha
Adapter vs Qwen/Qwen-Image-Edit. FoxBaze/Try_On_Qwen_Edit_Lora_Alpha is a LoRA adapter, not full weights: rank 32, on 0, 1, 2, add_k_proj, add_q_proj, add_v_proj, proj, to_add_out… (840 adapted matrices). It modifies Qwen/Qwen-Image-Edit at load time.
1 other repos hold byte-for-byte identical weight files.