The module already has VAE. Unless you have specific coloring requirements, it is recommended to use the VAE inside the module. Due to the unique nature of v-pred, I have created a dedicated section for v-pred.(If the colors in version 2.0 are too heavy, you can switch the VAE to <a rel="ugc" href="https://civarchive.com/models/296576/sdxl-vae">SDXL</a>.)<hr />Recommended Parameters:<ul><li>Samplers: DDPM(suggest) &gt; Euler &gt; DDIM (⚠️ Other samplers will not work properly)<ul><li>DDPM<ul><li>CFG: 5.5 ( around 5.5)</li><li>Steps: 40 ( or higher)</li><li>Hi-res fix: Upscale 1.5x or higher, Denoising strength 0.15–0.45</li></ul></li><li>Euler<ul><li>CFG: 4~7</li><li>Steps: 20~35</li><li>Hi-res fix: Upscale 1.5x or higher, Denoising strength 0.15–0.45</li></ul></li></ul></li></ul><hr />Forge Configuration Guide (Update to the latest version): <img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/0eb22b5a-b791-4b93-9d50-8d25d3a1ca52/width=525/0eb22b5a-b791-4b93-9d50-8d25d3a1ca52.jpeg" />Select SDXL from FreeU dropdown menu, set the start to 0.6 and end to 0.8.( V2.0 Not recommended SelfAttentionGuidance Integrated )<img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/42f299ac-57b2-42f9-b302-d0995231ace2/width=525/42f299ac-57b2-42f9-b302-d0995231ace2.jpeg" /><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/cfbb6d68-a2ec-401f-b518-cf102ab34bf5/width=525/cfbb6d68-a2ec-401f-b518-cf102ab34bf5.jpeg" />ComfyUI : <a target="_blank" rel="ugc" href="https://huggingface.co/Laxhar/noobai-XL-Vpred-0.5/blob/main/comfy_ui_workflow_sample.png">https://huggingface.co/Laxhar/noobai-XL-Vpred-0.5/blob/main/comfy_ui_workflow_sample.png</a>For Training v-pred LoRAs : <a target="_blank" rel="ugc" href="https://civarchive.com/articles/8723/vlora-or-how-to-train-a-lora-on-v-pred-sdxl-model">https://civarchive.com/articles/8723/vlora-or-how-to-train-a-lora-on-v-pred-sdxl-model</a>Adetailer : <a target="_blank" rel="ugc" href="https://github.com/Bing-su/adetailer">https://github.com/Bing-su/adetailer</a>

Files with SHA256: 7c0fd1da0acb5aae65cddfb3514c440ffffb4734ff404e0954d75120ce48e45d