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>

Indigo Void Furry Vpred / Furry NoobAI V-pred - v2.0

indigoVoidFurryVpred_v20.safetensors

v2.0

beta

Update: Uploaded v2 fp32(labeled as just v2, use that one) and v2 fp16 if anyone wants to download from here since it would be faster than downloading from civit. Note from mel: probably one if not the best v-pred model I've seen, even though the focus is bara but it's just as good at doing anything else.Original Description: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.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>

Files with SHA256: bd859e510b312543ff0d7ec10f452c17be48286f361d0c06e41d19e88d3209a8