JoyFusionAI/Qwen-Image-2.1-Uncensored-LoRA
Adapter vs Qwen/Qwen-Image-2.1. JoyFusionAI/Qwen-Image-2.1-Uncensored-LoRA is a LoRA adapter, not full weights: rank 16, on 0, to_k, to_q, to_v (128 adapted matrices). It modifies Qwen/Qwen-Image-2.1 at load time.