LoRA of Agnes Digital (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>. 👍Here are two LoRA of agnes digital based on same data.One is rank=16 LoRA, the other is rank=4 LoRA.See difference of two LoRAs, do you see what has higher quality?Recommend options<ul><li>rank=16. LoRA weight 0.7~0.9</li><li>rank=4. LoRA weight 0.7~1.0</li><li>Trigger words<ul><li>base<ul><li>agnes digital \(umamusume\)</li></ul></li><li>Racing competition clothes :<ul><li>single thighhighs, sleeveless, single glove, garter straps, white gloves, crop top, frills, sailor collar, multicolored skirt, multicolored clothes, layered skirt, red belt, white shirt</li><li>(optional) : glowing stick, drooling, saliva</li></ul></li><li>Halloween costume :<ul><li>twin braids, white thighhighs, double sleeves past wrists, hair bun, detached sleeves, official alternate costume, chinese clothes, jiangshi, ofuda, bloomers, hair rings</li></ul></li><li>Casual clothes:<ul><li>collarbone, casual, belt, jacket, shorts</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 3.5~6.5</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>trained on <a target="_blank" rel="ugc" href="https://github.com/kohya-ss/sd-scripts">sd-scripts by kohya_ss</a>. Thank you a lot!</li><li>based on Animefull-pruned</li><li>84 images of agnes digital<ul><li>4x low quality 28 images</li><li>8x medium quality 27 images</li><li>16x high quality 29 images</li><li>=&gt; 1 epoch = 792 images</li></ul></li><li>replaced character feature tags with agnes digital \(umamusume\)<ul><li>horse girl, horse tail, pink hair, blue eyes, etc.</li></ul></li><li>using aspect ratio bucketing</li><li>resolution : 768x768</li><li>there are two different rank models. rank=16 and rank=4<ul><li>lower rank, lower size.</li></ul></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: 5f8aa447a702993d39a75bfbd2f7cc827b8f39511e4a5200f6cf8a6dde50594b