Modified Animagine-XL for LoRA training.It reduces unintended style changes and improves quality.If you make a LoRA with this checkpoint, do not use "--noise_offset"!This is not suitable for image generation!LoRA学習用のAnimagine-XLです。意図しない画風の変化を軽減し品質を改善ます。これでLoRAを作る場合、「--noise_offset」は使用しないように！画像生成は適していません。<h2 id="training-information:-jpcspqlsm">Training information:</h2>Finetuned Animagine-XL by repeating the training and merging a DoRA 2 times with sd-scripts.sd-scriptsで二回DoRAの学習とマージを繰り返すことでファインチューンされました。Style training has not been tested, but some users reported that it can be learned successfully.画風学習は未確認ですが、問題なく学習できるという報告があります。<h2 id="dataset-information:-d406wl4mr">Dataset information:</h2>Dataset size: 5120Gelbooruから収集した5120枚の画像で学習しました。なお、以下のタグがあるか条件を満たす画像は除外しました。filetype:gif, score:&lt;0, mpixels:&lt;1048576, tagcount:&lt;16, \*_artifacts, adversarial_noise, greyscale, monochrome, digimon, photophop_(meidum), ai-generated, duplicate, bad_\*, off-topic, cropped, resized, reversed, rotated, third-party_edit, screenshot, tagme, real_life, watermark, 3d, koikatsu, mikumikudance, twitter_username<h2 id="training-script(source-code)-qn8q8imli">Training script(source code)</h2>sd-scripts( <a target="_blank" rel="ugc" href="https://github.com/kohya-ss/sd-scripts">https://github.com/kohya-ss/sd-scripts</a> )

AnyAnimagine-XL(for LoRA Training)

Base model is Animagine-XL-4.0Original filename is <code>AnyAnimagine-XL-4.0.safetensors</code>

Files with SHA256: 0a0fe6e321a21b83f0aa93049e3ad718267d5344c9e177e77ee8e0ef01634a69