<a target="_blank" rel="ugc" href="https://github.com/KohakuBlueleaf/LyCORIS">LoHa</a> of Manhattan Cafe (umamusume). Put LoHa file in your stable-diffusion-webui/models/lora folder and write LoRA notation in prompt to applying LoHa. &lt;lora:your_loha_name:weight&gt;All of my works is free. If you'd like to support me, feel free to <a target="_blank" rel="ugc" href="https://www.buymeacoffee.com/mhtLoRA">buy me a coffee</a>. 👍[2023-03-20 07:40 GMT] LoHa version added. Many costume available!Recommended options<ul><li>LoRA weight around 0.7</li><li>Trigger words<ul><li>Base<ul><li>manhattan cafe \(umamusume\)</li></ul></li><li>Racing competition costume :<ul><li>black choker, black gloves, long sleeves, collared shirt, yellow necktie, black vest, black coat, belt, black skirt, pleated skirt, black pantyhose, shoes, white footwear</li></ul></li><li>SSR Stamina :<ul><li>official alternate costume, alternate hairstyle, ponytail, single earring, long sleeves, layered sleeves, green apron, collared shirt, white shirt, sweater vest, neck ribbon, white ribbon</li></ul></li><li>Casual :<ul><li>casual, neck ribbon, black ribbon, puffy long sleeves, bracelet, yellow shirt, collared shirt, frilled shirt collar, shirt tucked in, black belt, belt buckle, green skirt, plaid skirt, long skirt, black pantyhose, black footwear</li></ul></li><li>Tracen summer uniform<ul><li>tracen school uniform, summer uniform, serafuku, puffy short sleeves, bowtie, horseshoe ornament, sailor collar, sailor shirt, frills, white skirt, purple shirt, miniskirt, zettai ryouiki, white thighhighs, brown footwear, shoes</li></ul></li><li>Other Costumes :<ul><li>New Year :<ul><li>alternate costume, alternate hairstyle, ponytail, hair flower, hair ornament, japanese clothes, black kimono, sash, obi, long sleeves, wide sleeves, floral print, fur trim</li></ul></li><li>Maid :<ul><li>maid headdress, enmaided, black choker, ascot, puffy sleeves, long sleeves, juliet sleeves, black dress, collared dress, maid apron, white apron, frilled apron</li></ul></li><li>Swimsuit :<ul><li>tracen swimsuit, blue one-piece swimsuit, competition school swimsuit, white stripes, single vertical stripe</li></ul></li></ul></li></ul></li></ul>Use a model derived from or mixed with <a target="_blank" rel="ugc" href="https://huggingface.co/a1079602570/animefull-final-pruned/blob/main/model-001.ckpt">animefull model</a>.<ul><li>Settings<ul><li><a target="_blank" rel="ugc" href="https://github.com/AUTOMATIC1111/stable-diffusion-webui">Stable Diffusion WebUI by Automatic1111</a></li><li>DPM++ Series(SDE Karras, 2M Karras, etc.)</li><li>about 20 steps, CFG scale 3.5~6.5</li><li>I recommend <a target="_blank" rel="ugc" href="https://huggingface.co/AIARTCHAN/aichan_blend/blob/main/vae/BerrysMix.vae.safetensors">kl-f8-anime2.vae</a></li><li>CLIP skip = 1</li><li>Use Hires.fix to get higher quality image<ul><li>Upscaler<ul><li>Latent, Latent (nearest-exact), Latent (bicubic antialiased) or other Latent series.</li></ul></li><li>Denoising strength 0.50~0.65</li></ul></li></ul></li></ul>LoRA training info<ul><li>trained on <a target="_blank" rel="ugc" href="https://github.com/kohya-ss/sd-scripts">sd-scripts by kohya_ss</a>.<ul><li><a target="_blank" rel="ugc" href="https://github.com/KohakuBlueleaf/LyCORIS">LyCORIS by KohakuBlueleaf</a></li><li>Thank you all a lot!</li></ul></li><li>based on <a target="_blank" rel="ugc" href="https://huggingface.co/a1079602570/animefull-final-pruned/blob/main/model-001.ckpt">Animefull-pruned model</a></li><li>235 images of<ul><li>4x low quality 75 images</li><li>8x medium quality 80 images</li><li>16x high quality 80 images</li><li>=&gt; 1 epoch = 2220 images</li></ul></li><li>replaced character feature tags with manhattan cafe \(umamusume\)<ul><li>1girl, solo, brown eyes, horse girl, yellow eyes, blue eyes, simple background, white hair, 1girl, streaked hair, bangs, very long hair, horse ears, horse tail, tail through clothes, animal ears, hair between eyes, black hair, multicolored hair, closed eyes, long hair, ahoge, long bangs, piercing, open clothes, jacket, black jacket, ear piercing, single earring,</li><li>I think these tags are<ul><li>the essentials of Manhattan Cafe</li><li>or unnecessary for training because of duplication.</li></ul></li></ul></li><li>resolution : 768x768 with aspect ratio bucketing.</li><li>other training settings is included in training_data.zip or metadata in LoRA file.</li></ul>All uploaded images are generated by <a target="_blank" rel="ugc" href="https://huggingface.co/WarriorMama777/OrangeMixs/blob/main/Models/AbyssOrangeMix3/AOM3A1.safetensors">AOM3A1</a>And, special thanks to my best friend. DH.

Manhattan Cafe (umamusume)

This is old version.LoRA of Manhattan Cafe (umamusume). Recommend options<ul><li>LoRA weight 0.5~0.65</li><li>Trigger words<ul><li>base<ul><li>manhattan cafe \(umamusume\)</li><li>(optional) white ahoge, black long hair</li></ul></li><li>Racing competition clothes :<ul><li>black coat, black shirt, black skirt, yellow necktie</li></ul></li></ul></li><li>Use animefull based model</li><li>Settings<ul><li>DPM++ SDE Karras</li><li>20 steps, CFG scale 4.5~6.5</li><li>kl-f8-anime2.vae</li><li>CLIP skip = 1</li><li>Highres<ul><li>Latent (bicubic antialiased)</li><li>Denoising strength 0.55~0.65</li></ul></li></ul></li></ul>LoRA training info<ul><li>based on Animefull-pruned</li><li>32 images of manhattan cafe<ul><li>25x low quality 12 images</li><li>50x medium quality 12 images</li><li>100x high quality 8 images</li><li>=&gt; 1 epoch = 1700 images</li></ul></li><li>rank=alpha=16</li><li>using <a target="_blank" rel="ugc" href="https://github.com/facebookresearch/dadaptation">dadaptation</a></li><li>batch size = 4, 6 epoch trained</li><li>clip skip = 1</li></ul>All uploaded images are output of AbyssOrangeMix2-nsfw, kl-f8-anime2.vae

Files with SHA256: da77a9c94b133800198c59930e574a22f9292994f177796e6222eb02ff7a46c9