Lora trained on Musubi from SekireiMaster model anime: <a target="_blank" rel="ugc" href="https://civarchive.com/models/31546/based65">Based65</a>, <a target="_blank" rel="ugc" href="https://civarchive.com/models/18798/meinaunreal">meinaunreal</a>2,5D: <a target="_blank" rel="ugc" href="https://civarchive.com/models/22402/fantasticmixreal">fantasticmixReal_V30</a> (this one is also more realistic), <a target="_blank" rel="ugc" href="https://civarchive.com/models/7371/rev-animated">ReV Animated</a>negative embeddings: <a rel="ugc" href="https://huggingface.co/yesyeahvh/bad-hands-5/blob/main/bad-hands-5.pt">embedding:bad-hands-5</a>, <a rel="ugc" href="https://civarchive.com/models/4629/deep-negative-v1x">embedding:ng_deepnegative_v1_75t</a>, <a rel="ugc" href="https://huggingface.co/nick-x-hacker/bad-artist/blob/main/bad-artist.pt">embedding:bad-artist</a>, <a rel="ugc" href="https://civarchive.com/models/7808/easynegative">embedding:EasyNegative</a>Recommended settings:<ul><li>Make sure you are aware on the usage instructions of LORA</li></ul><ul><li>VAE: <a target="_blank" rel="ugc" href="https://huggingface.co/WarriorMama777/OrangeMixs/blob/main/VAEs/orangemix.vae.pt">orangemix.vae</a> (for 2,5D pictures), <a target="_blank" rel="ugc" href="https://huggingface.co/stabilityai/sd-vae-ft-mse-original/blob/main/vae-ft-mse-840000-ema-pruned.safetensors">vae-ft-mse-840000-ema-pruned</a> (for realistic models), <a target="_blank" rel="ugc" href="https://huggingface.co/hakurei/waifu-diffusion-v1-4/blob/main/vae/kl-f8-anime2.ckpt">kl-f8-anime2</a>, <a target="_blank" rel="ugc" href="https://huggingface.co/NoCrypt/blessed_vae/blob/main/blessed2.vae.pt">blessed2.vae</a> (for anime models)</li></ul><ul><li>Sampler: DPM++ SDE Karras or DPM++ 2M Karras</li><li>Steps: 20 to 35</li><li>Clipskip: 1 or 2</li><li>Upscaler : img2img in comfyui using 4x-UltraMix_Smooth</li><li>CFG Scale : 5 to 9 (mostly 7 and 8)</li><li>LORA weight for txt2img: 0.5-1 (for the examples i mostly used 0.7)</li></ul><ul><li>Denoise strength for img2img: 0.4 to 0.7</li></ul>If you want the exact same settings, just drag and drop the picture into ComfyUI because this time I included the metadata of the picturesTrained with based65 checkpointfor the pictures i used <a target="_blank" rel="ugc" href="https://github.com/comfyanonymous/ComfyUI">comfyui</a>for the most accurate pictures i would recommend using this costum node for comfyui: <a target="_blank" rel="ugc" href="https://civarchive.com/models/28295/cutoff-for-comfyui">cutoff-for-comfyui</a>or this for automatic1111: <a target="_blank" rel="ugc" href="https://civarchive.com/models/18840/no-more-color-contamination-read-description">no-more-color-contamination</a>

Files with SHA256: 8c424e4adfb1310e5b76f512057f7c93fae392bd363a017efcd120c0be5f4d65