chriswritescode/Turbo8-LoRA-Qwen-Image-2.1
Adapter vs Qwen/Qwen-Image-2.1. chriswritescode/Turbo8-LoRA-Qwen-Image-2.1 is a LoRA adapter, not full weights: rank 128, on 0, 1, gate_layer, linear_1, linear_2, out, proj, to_k… (227 adapted matrices). It modifies Qwen/Qwen-Image-2.1 at load time.