ML-Intern-lab/Qwen-Image-2.1-doodle-in-LoRA
Adapter vs Qwen/Qwen-Image-2.1. ML-Intern-lab/Qwen-Image-2.1-doodle-in-LoRA is a LoRA adapter, not full weights: rank 32, on 0, gate_up, out, to_k, to_q, to_v (192 adapted matrices). It modifies Qwen/Qwen-Image-2.1 at load time.