LoRA of Maruzensky (umamusume). Put LoRA file in your stable-diffusion-webui/models/lora folder and write LoRA notation in prompt to applying LoRA. &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>. 👍Recommend options<ul><li>LoRA weight 0.55~0.75</li><li>Trigger words<ul><li>base<ul><li>maruzensky \(umamusume\)</li></ul></li><li>Racing competition clothes :<ul><li>red thighhighs, red jacket, pleated skirt, red skirt, long sleeves, thigh strap, choker, red shirt, open jacket, white bow, miniskirt, open clothes, high heel boots</li></ul></li><li>Casual clothes :<ul><li>sleeveless dress, white dress, straw hat, floral print, flower</li></ul></li><li>Summer costume:<ul><li>swimsuit, official alternate costume, heart-shaped eyewear, eyewear on head, sunglasses, black bikini, cleavage, navel, jewelry, flower, frilled bikini, necklace, thigh strap, ponytail, bracelet, collarbone, sandals</li></ul></li></ul></li></ul>Use animefull based model<ul><li>Settings<ul><li>DPM++ Series(SDE Karras, 2M Karras, etc.)</li><li>about 20 steps, CFG scale 3.5~6.0</li><li>kl-f8-anime2.vae</li><li>CLIP skip = 1</li><li>If using highres<ul><li>Latent series</li><li>Denoising strength 0.50~0.65</li></ul></li></ul></li></ul>LoRA training info<ul><li>based on Animefull-pruned</li><li>80 images of maruzensky<ul><li>4x low quality 29 images</li><li>8x medium quality 21 images</li><li>16x high quality 30 images</li><li>=&gt; 1 epoch = 764 images</li></ul></li><li>replaced character feature tags with maruzensky \(umamusume\)<ul><li>horse girl, horse tail, brown hair, aqua eyes, etc.</li></ul></li><li>using aspect ratio bucketing</li><li>resolution : 768x768</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 epochs trained</li><li>clip skip = 1</li></ul>This LoRA may be compatible with animefull-based models (ex. AbyssOrangeMix Series...)All uploaded images are generated by AOM3A1

Files with SHA256: 4a3e92d99052f5296abc2c03afe72644c20061a5d0f26127cea2d84336d5a41b