LoRA trained on Bayonetta 1 2 3bayonetta1, 1girl, bodysuit, cleavage cutout, elbow gloves, makeup, jewelry, lipstick, hair ribbon, glassesbayonetta2, 1girl, bodysuit, makeup, lipstick, short hair, jewelry, glasses, amulet, elbow glovesbayonetta3, 1girl, long hair, glasses, makeup, twin braids, lipstick, jewelry, elbow gloves, bodysuitI know there are many on this site already. Just wanted to work on a larger project with a character that has a decent dataset to work with :)anime: <a target="_blank" rel="ugc" href="https://civarchive.com/models/6174?modelVersionId=162557">DivineEleganceMix v7</a>, <a target="_blank" rel="ugc" href="https://civarchive.com/models/184377/ritium-reverie">Ritium Reverie - v1.0</a>, <a target="_blank" rel="ugc" href="https://civarchive.com/models/9139?modelVersionId=182252">YesMix - v3.5</a>2,5D: <a target="_blank" rel="ugc" href="https://civarchive.com/models/142185/irrealitium?modelVersionId=157631">irRealitium</a>, <a target="_blank" rel="ugc" href="https://civarchive.com/models/107842?modelVersionId=152549">Aniverse</a>, <a target="_blank" rel="ugc" href="https://civarchive.com/models/48671/dark-sushi-25d">Dark Sushi 2.5D</a>, <a target="_blank" rel="ugc" href="https://civarchive.com/models/36520/ghostmix">GhostMix - v2.0</a>better hands LoRA: <a target="_blank" rel="ugc" href="https://civarchive.com/models/47085?modelVersionId=55199">EnvyBetterHands LoCon - beta2</a>negative embeddings: <a target="_blank" rel="ugc" href="https://civarchive.com/models/58726?modelVersionId=205764">Async's Negative - v11-light</a>, <a target="_blank" rel="ugc" href="https://civarchive.com/models/11772/verybadimagenegative">veryBadImageNegative</a>, <a target="_blank" rel="ugc" href="https://civarchive.com/models/5224?modelVersionId=6056">Bad artist</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/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 &amp; 2,5D), <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(euler a for img2img upscaling) from time to time im also using <a target="_blank" rel="ugc" href="https://civarchive.com/models/35966/dpm-2m-alt-karras-sampler">DPM++ 2M alt Karras</a></li><li>Steps: 20 to 35</li><li>Clipskip: 2</li><li>Upscaler : <a target="_blank" rel="ugc" href="https://github.com/pkuliyi2015/multidiffusion-upscaler-for-automatic1111">GitHub - pkuliyi2015/multidiffusion-upscaler-for-automatic1111</a> <a target="_blank" rel="ugc" href="https://mega.nz/folder/qZRBmaIY#nIG8KyWFcGNTuMX_XNbJ_g/file/vRYVhaDA">4x-UltraSharp(for 2,5D &amp; realistic)</a>, <a target="_blank" rel="ugc" href="https://huggingface.co/konohashinobi4/4xAnimesharp/tree/main">4xAnimesharp</a>, <a target="_blank" rel="ugc" href="https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.2.4/RealESRGAN_x4plus_anime_6B.pth">RealESRGAN_x4plus_anime_6B.pth</a></li><li>CFG Scale : 5 to 9 (mostly 7)</li><li>LORA weight for txt2img: 0.5-1 (for the examples i mostly used 0.8 and 1)</li></ul><ul><li>Denoise strength upscaling: 0.3 to 0.55</li></ul>If you want to autocomplete the tags &amp; trigger im using, I recommend using <a target="_blank" rel="ugc" href="https://github.com/DominikDoom/a1111-sd-webui-tagcomplete">Booru style tag autocompletion for AUTOMATIC1111's Stable Diffusion web UI</a>For full body shots i recommend using: <a target="_blank" rel="ugc" href="https://civarchive.com/models/33192/comfyui-impact-pack">ComfyUI Impact Pack</a>or the a1111 alternative <a target="_blank" rel="ugc" href="https://github.com/Bing-su/adetailer">GitHub - Bing-su/adetailer</a>

Bayonetta | Bayonetta 1 2 3

Files with SHA256: 74ab5df49f391e0d9350edc9d0e63bc7b2b627e1ed389115dcf88e22f476431c