This is an attempt to produce 8 Step LoRA that produces better quality images (Compared to the various loras by Viggle and Pruna AI). When I use these three LoRAs in the Recipe together in ComfyUI, I get good quality images. However, the 8 Step LoRA I produced is not as good, but it works!<h3 id="recipe">Recipe</h3>Loras From Viggle: <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>And Pruna AI <a target="_blank" rel="ugc" href="https://huggingface.co/PrunaAI/Pruna-Qwen-Image-2.1/tree/main">https://huggingface.co/PrunaAI/Pruna-Qwen-Image-2.1/tree/main</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; 0.15Pruna AI 8 Step LoRa: p_qwen_image_2.1_8step_v0.1.safetensors -&gt; 0.2Merged, Then exported.<h3 id="caveats">Caveats</h3>Can produce anatomical errors.Can produce grid noise.

Files with SHA256: 3a18527010d95101746845d9ccf1a4bb7e5df090b144aefdaef1db6999f25f68