<h3 id="this-is-a-poor-copy-of-the-following-excellent-application:">This is a poor copy of the following excellent application:</h3><a target="_blank" rel="ugc" href="https://huggingface.co/spaces/tori29umai/Qwen-Image-2509-CharacterSheet">https://huggingface.co/spaces/tori29umai/Qwen-Image-2509-CharacterSheet</a><ul><li>You can switch between FP8 and GGUF (models and clips).</li><li>The lightning 4-step is attractive, but the 8-step is more stable.</li><li>If the output is mosaic, remove the "fast" option from Comfyui's bat.</li><li>This is usually where I start organizing for a release, but I run out of energy and it ends up being shelved. So I'll upload it as is.</li></ul><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/8db822da-7aa9-43e6-978e-3a9e02814c4b/width=525/8db822da-7aa9-43e6-978e-3a9e02814c4b.jpeg" /><ul><li>I tried to make it using as many "normal" nodes as possible, but if you can't find it, please let me know.</li><li>(10/25) I tried to create a setting for 12GB of VRAM, but ended up with a setting of 6GB.</li></ul><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/9107fadf-736b-44cb-b2ec-988d198e4db0/width=525/9107fadf-736b-44cb-b2ec-988d198e4db0.jpeg" /><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/4cad90d9-5f11-4d07-aac8-00b0b2d3c572/width=525/4cad90d9-5f11-4d07-aac8-00b0b2d3c572.jpeg" /><h3 id="time-taken-on-4070tis-(second-pass)">Time taken on 4070tis (second pass)</h3>qwen_image_edit_2509_fp8_e4m3fn.safetensors (19GB)qwen_2.5_vl_7b_fp8_scaled.safetensors (9GB)Uses 15.2GB of VRAM.140sec @ 8step w/Qwen-Image-Lightning-8steps-V2.0-bf16.safetensors88sec @ 4step w/Qwen-Image-Lightning-4steps-V2.0-bf16.safetensors=====Qwen-Image-Edit-2509-Q3_K_M.gguf (9GB)qwen_2.5_vl_7b_fp8_scaled.safetensors (9GB)Uses 12.1GB of VRAM (low quality)105sec @ 4step w/Qwen-Image-Lightning-4steps-V2.0-bf16.safetensors=====Qwen-Image-Edit-2509-Q3_K_M.gguf (9GB)Qwen2.5-VL-7B-Instruct-Q3_K_M.gguf (3.5GB)Uses 13.8GB of VRAM (low quality. There is no point in using GGUF as the text encoder.)105sec @ 4step w/Qwen-Image-Lightning-4steps-V2.0-bf16.safetensors=====Qwen-Image-Edit-2509-Q5_K_M.gguf (14GB)qwen_2.5_vl_7b_fp8_scaled.safetensors (9GB)DisTorch2MultiGPU virtual vram : 10GBUses 7.1GB of VRAM.=====Qwen-Image-Edit-2509-Q4_K_M.gguf (12GB)qwen_2.5_vl_7b_fp8_scaled.safetensors (9GB)DisTorch2MultiGPU virtual vram : 10GBUses 5.2GB of VRAM. / 28GB MEM125sec @ 4step w/Qwen-Image-Lightning-4steps-V2.0-bf16.safetensors=====Qwen-Image-Edit-2509-Q3_K_M.gguf (9GB)qwen_2.5_vl_7b_fp8_scaled.safetensors (9GB)DisTorch2MultiGPU virtual vram : 10GBUses 3.1GB of VRAM. (Uses 5.2GB of VRAM @ VAE)=====

Files with SHA256: beea67d9dc04e42d01a803ca53ad1a6f3251d7c1ace042302918f892d8fa5bbe