Qwen Image v2.1, merged with Turbo LoRas to give a completed image in 8 or 5 Steps.<ul><li>Version 1 -&gt; Use 8 Steps</li><li>Version 2 -&gt; Use 5 Steps.</li><li>Sampler: Euler / Euler a</li><li>Scheduler: SImple / Normal</li></ul><h3 id="recipe">Recipe</h3>Loras From: <a target="_blank" rel="ugc" href="https://huggingface.co/Viggle/Qwen-Image-2.1-viggle-turbo">https://huggingface.co/Viggle/Qwen-Image-2.1-viggle-turbo</a>v0.21 LoRA: Qwen-Image-2.1-viggle-turbo-v0.2.1-6step-lora-r128.safetensors -&gt; 0.75v0.1 LoRA: Qwen-Image-2.1-viggle-turbo-4step-lora-r64.safetensors -&gt; 0.15Merged with Qwen Image 2.1 Bf16 Version. Then exported.<h3 id="caveats">Caveats</h3>Can produce anatomical errors.Can produce grid noise.

Files with SHA256: f68043f22a9dc170c012a5f91d94f3714a33524ca48e0cd424bbc3fd502cd6f9