<h2 id="nunchaku-z-image_to_sdxl">nunchaku-Z-image_to_SDXL</h2>The purpose of this workflow is to mix ZIT's excellent prompt tracking and high image quality with illustrious-SDXL's vast AGC character resources.In other words, characters that ZIT has not yet learned can be expressed using illustrious-SDXL's learned resources without using Lora.It combines nunchaku-Z-image-turbo and SDXL for extremely fast generation speeds.This is how I use it, but it's up to you to use it in your own way.<hr /><a target="_blank" rel="ugc" href="https://huggingface.co/nunchaku-tech/nunchaku-z-image-turbo">SVDQ Nunchaku-Z Image Turbo</a> with SDXL WorkflowVery faster generation speed compared to <a target="_blank" rel="ugc" href="https://civarchive.com/models/2192578?modelVersionId=2468770">Z-image-Turbo to SDXL (workflow)</a>RequirementsComfyUI ver. 0.6 or higherInstall or Updated to <a target="_blank" rel="ugc" href="https://github.com/nunchaku-tech/nunchaku/releases">Nunchaku version 1.1.0</a>Install or Updated to <a target="_blank" rel="ugc" href="https://github.com/nunchaku-tech/ComfyUI-nunchaku">ComfyUI-nunchaku version 1.1.0</a>Models<a target="_blank" rel="ugc" href="https://huggingface.co/nunchaku-tech/nunchaku-z-image-turbo">nunchaku-z-image-turbo </a>or<a target="_blank" rel="ugc" href="https://huggingface.co/nunchaku-tech/nunchaku-z-image-turbo"> </a><a target="_blank" rel="ugc" href="https://civarchive.com/models/2169712?modelVersionId=2549032">Z-Image Turbo - Quantized for low VRAM</a>Illustrious Model<a target="_blank" rel="ugc" href="https://civarchive.com/search/models?baseModel=Illustrious&amp;modelType=Checkpoint&amp;sortBy=models_v9&amp;query=Illustrious">Civitai | Share your models Illustrious Checkpoint</a>also recommend my merge model<a target="_blank" rel="ugc" href="https://civarchive.com/models/2259766/lucmeqemeqe">Luc_meqemeqe - v1.0 | Illustrious Checkpoint</a>DMD2 Speed LoRA<a target="_blank" rel="ugc" href="https://civarchive.com/api/download/models/1820705?type=Model&amp;format=SafeTensor">dmd2_sdxl_4step_lora_fp16</a> or <a target="_blank" rel="ugc" href="https://civarchive.com/api/download/models/1820946?type=Model&amp;format=SafeTensor">dmd2_sdxl_4step_lora_fp32</a><a target="_blank" rel="ugc" href="https://civarchive.com/models/2169712?modelVersionId=2549032">Here is a great explanation by Simplesmente</a>Thank you very much, Simplesmente!This official workflow must work before it can be used.<a target="_blank" rel="ugc" href="https://nunchaku.tech/docs/ComfyUI-nunchaku/workflows/zimage.html#nunchaku-z-image-turbo-json">https://nunchaku.tech/docs/ComfyUI-nunchaku/workflows/zimage.html#nunchaku-z-image-turbo-json</a><hr />I use ComfyUI 0.6.0 from <a target="_blank" rel="ugc" href="https://github.com/LykosAI/StabilityMatrix">Stability Matrix</a>Install ComfyUI anewPytroch 2.9.1+cu130 (December 30, 2025)<img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/29ab6378-8f80-49c1-97f7-ace8fe151184/width=525/29ab6378-8f80-49c1-97f7-ace8fe151184.jpeg" />Install ComfyUI-nunchaku with Manager and restart<img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/93222774-f46d-4806-8427-35edc4acb029/width=525/93222774-f46d-4806-8427-35edc4acb029.jpeg" />Nunchaku Installer<img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/1e017510-2885-4550-acdc-8abc0cd6a25a/width=525/1e017510-2885-4550-acdc-8abc0cd6a25a.jpeg" /><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/0c749eec-2314-474e-b241-3155305d5fd6/width=525/0c749eec-2314-474e-b241-3155305d5fd6.jpeg" />add Preview as Text<img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/9f0c9e24-b120-4b65-b4bb-be9579045170/width=525/9f0c9e24-b120-4b65-b4bb-be9579045170.jpeg" />connection<img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/3f630fb2-197a-4402-a732-09e7480d41c1/width=525/3f630fb2-197a-4402-a732-09e7480d41c1.jpeg" />mode: Select update node and run<img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/4c0d7c0c-5959-455a-b7af-a6ee70a4724f/width=525/4c0d7c0c-5959-455a-b7af-a6ee70a4724f.jpeg" />Follow the text press "R"<img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/6644a2ea-e7fb-4b69-ba4b-7f292dc5884a/width=525/6644a2ea-e7fb-4b69-ba4b-7f292dc5884a.jpeg" />verson : 1.1.0mode : installThen RUN<img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/84fbe484-89a7-442c-9c4f-ba89dced9709/width=525/84fbe484-89a7-442c-9c4f-ba89dced9709.jpeg" />Success! Installed<img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/20c32146-8b6f-436f-a5db-e55326d8fbf0/width=525/20c32146-8b6f-436f-a5db-e55326d8fbf0.jpeg" />Restart ComfyUI<img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/30a1c266-5cc2-4a70-894c-5ca7a09bae54/width=525/30a1c266-5cc2-4a70-894c-5ca7a09bae54.jpeg" />Download this workflow and drag and drop it.<a target="_blank" rel="ugc" href="https://raw.githubusercontent.com/nunchaku-tech/ComfyUI-nunchaku/refs/heads/main/example_workflows/nunchaku-z-image-turbo.json">raw.githubusercontent.com/nunchaku-tech/ComfyUI-nunchaku/refs/heads/main/example_workflows/nunchaku-z-image-turbo.json</a>This dialog box will appear, so download each model to the designated folder.<img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/9a786680-8ef3-4323-af1c-6f9d3f6a6220/width=525/9a786680-8ef3-4323-af1c-6f9d3f6a6220.jpeg" /><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/72c3e7b3-cd11-41c5-934c-dca3c7946386/width=525/72c3e7b3-cd11-41c5-934c-dca3c7946386.jpeg" />Download nunchaku-z-image-turbo to " diffusion_models " folder(.\StabilityMatrix\Data\Packages\ComfyUI\models)<a target="_blank" rel="ugc" href="https://huggingface.co/nunchaku-tech/nunchaku-z-image-turbo/tree/main">nunchaku-tech/nunchaku-z-image-turbo at main</a>RTX50xx is fp4, RTX40xx, 30xx is int4<img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/2fe5fcac-bbb5-4721-acb7-67a086eb1271/width=525/2fe5fcac-bbb5-4721-acb7-67a086eb1271.jpeg" />I have an RTX5060Ti 16GB so I chose fp4_r128Download the model and place it in the designated folder. Press "R" to update the model."RUN"<img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/160079ce-bbcb-47c2-9259-77d07a5a8c7c/width=525/160079ce-bbcb-47c2-9259-77d07a5a8c7c.jpeg" /><hr />Similarly, drag and drop this workflow "nunchaku-Z-image_to_SDXL.json"Missing nodes are installed from the Manager's Missing Custom Nodesrestart<img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/3e2c9424-d3bb-4361-aec0-a9ebfc2e6592/width=525/3e2c9424-d3bb-4361-aec0-a9ebfc2e6592.jpeg" />Checkpoints folder contains the Illustrious Checkpoints of your choice.DMD2 Speed ​​LoRA to the loras folder<a target="_blank" rel="ugc" href="https://civarchive.com/api/download/models/1820705?type=Model&amp;format=SafeTensor">dmd2_sdxl_4step_lora_fp16</a> or <a target="_blank" rel="ugc" href="https://civarchive.com/api/download/models/1820946?type=Model&amp;format=SafeTensor">dmd2_sdxl_4step_lora_fp32</a><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/f61c0762-4502-47c9-96ee-c61bf8c0a00a/width=525/f61c0762-4502-47c9-96ee-c61bf8c0a00a.jpeg" />Download the model and place it in the designated folder. Press "R" to update the model."RUN"<img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/c41268d4-a941-4d25-ac7c-df1f8ac5a28f/width=525/c41268d4-a941-4d25-ac7c-df1f8ac5a28f.jpeg" />If you want to use Lora with nunchaku-z-image-turbo,Install the following custom node:<a target="_blank" rel="ugc" href="https://github.com/ussoewwin/ComfyUI-QwenImageLoraLoader">https://github.com/ussoewwin/ComfyUI-QwenImageLoraLoader</a>

Files with SHA256: 8213dbc3926110c634ab31adbd3a35790b9224ff88cc0b2a027823cc7dc38812