This was originally intended to be an update of <a target="_blank" rel="ugc" href="https://civarchive.com/models/208491/mfcg-doll-mix">another mix of mine</a>, but I thought it ended up being unique enough to maintain as its own thing.It is prone to generating provocative women.Images generated using <a target="_blank" rel="ugc" href="https://huggingface.co/AIARTCHAN/aichan_blend/blob/main/vae/Berry's%20Mix.vae.safetensors">Berry's Mix VAE</a> and <a target="_blank" rel="ugc" href="https://huggingface.co/konohashinobi4/4xAnimesharp/blob/main/4x-AnimeSharp.pth">4X AnimeSharp Upscaler </a>at Clip Skip 2VAE is already baked inMy typical settings for images:<ul><li>Sampler - DPM++ 2M SDE Karras / Euler a</li><li>Sampling Steps - 35 to 40</li><li>HiRex Fix - Upscaled by 2 at 15 to 20 steps, 0.35 Denoising Strength</li><li>Dimensions - 512x512, 512x768, or 768x512</li><li>CFG Scale - 5.5 to 7</li><li>Two passes of ADetailer<ol><li>1st pass: face_<a target="_blank" rel="ugc" href="http://yolov8n.pt">yolov8n.pt</a></li><li>2nd pass: mediapipe_face_mesh_eyes_only or hand_<a target="_blank" rel="ugc" href="http://yolov8n.pt">yolov8n.pt</a></li></ol></li></ul>See images for examples of how I prompt. I prefer short, simple, tag-based prompts, but there is probably a lot of room for flexibility/improvement here

MFCG Midway Mix

mfcgMidwayMix_v10.safetensors

v1.0

This merge is created with the primary goal of generating pretty ladies in NSFW situations.This was originally intended to be an update of <a target="_blank" rel="ugc" href="https://civitai.com/models/208491/mfcg-doll-mix">another mix of mine</a>, but I thought it ended up being unique enough to maintain as its own thing.Images generated using <a target="_blank" rel="ugc" href="https://huggingface.co/AIARTCHAN/aichan_blend/blob/main/vae/Berry's%20Mix.vae.safetensors">Berry's Mix VAE</a> and <a target="_blank" rel="ugc" href="https://huggingface.co/konohashinobi4/4xAnimesharp/blob/main/4x-AnimeSharp.pth">4X AnimeSharp Upscaler </a>at Clip Skip 2VAE is already baked inMy typical settings for images:<ul><li>Sampler - DPM++ 2M SDE Karras / Euler a</li><li>Sampling Steps - 35 to 40</li><li>HiRex Fix - Upscaled by 2 at 15 to 20 steps, 0.35 Denoising Strength</li><li>Dimensions - 512x512, 512x768, or 768x512</li><li>CFG Scale - 5.5 to 7</li><li>Two passes of ADetailer<ol><li>1st pass: face_<a target="_blank" rel="ugc" href="http://yolov8n.pt/">yolov8n.pt</a></li><li>2nd pass: mediapipe_face_mesh_eyes_only or hand_<a target="_blank" rel="ugc" href="http://yolov8n.pt/">yolov8n.pt</a></li></ol></li></ul>

Files with SHA256: d66aed42bd93d74c224ec3cd490937ec375bba1ad774b7bb3613aaec33fa936d