e-n-v-y/Qwen-Image-2.1-Fix-Opinionated-v1.0
Adapter vs Qwen/Qwen-Image-2.1. e-n-v-y/Qwen-Image-2.1-Fix-Opinionated-v1.0 is a LoRA adapter, not full weights: rank 64, on 0, gate_up, out, to_k, to_q, to_v (128 adapted matrices). It modifies Qwen/Qwen-Image-2.1 at load time.