Modified Illustrious-XL for LoRA training.It reduces unintended style changes.If you make a LoRA with this checkpoint, do not use "--noise_offset"!Note: This model is not suitable for image generation. The model tends to generate ugly images.LoRA学習用のIllustrious-XLです。意図しない画風の変化を軽減し、精度も改善します。これでLoRAを作る場合、「--noise_offset」は使用しないように！また、noise offsetの効果を打ち消したため、マージ用途の使用は推奨しません。<h2 id="training-information:">Training information:</h2>Finetuned Illustrious-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。Training parameters(do not use):<ul><li>Optimizer: AdamWScheduleFree</li><li>Resolution: 1024(w/ bucketing)</li><li>LR: 0.0005</li><li>LR Scheduler: Constant with warmup(warmup=100)</li><li>Batch size: 2</li><li>Epoch: 1</li><li>Rank/Alpha: 16/8</li><li>Conv Rank/Alpha: 2/0.5</li><li>Debiased Estimation: True</li></ul><h2 id="dataset-information:">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_(medium), mikumikudance, twitter_username<h2 id="training-script(source-code)">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> )<h2 id="notice:">Notice/おしらせ:</h2>This model is licensed under Fair AI Public License 1.0-SD( <a target="_blank" rel="ugc" href="https://freedevproject.org/faipl-1.0-sd/">https://freedevproject.org/faipl-1.0-sd/</a> ).If you make modify this model, you must share both your changes and the original license.このモデルはFair AI Public License 1.0-SD( <a target="_blank" rel="ugc" href="https://freedevproject.org/faipl-1.0-sd/">https://freedevproject.org/faipl-1.0-sd/</a> )でライセンスされています。このモデルを改変する場合、変更点および元のライセンスを明記する必要があります。

AnyIllustrious-XL(for LoRA training)

anyillustriousXLFor_v011.safetensors

v0.1.1

2.0.0

1.1.0

1.0.0 v0.1

Modified Illustrious-XL for LoRA trainingThis model reduces unintended style changes and improves accuracy. If you create a LoRA with this checkpoint, do not use --noise_offset.Note: This model is not suitable for image generation, as it tends to generate ugly images. Also, since the effect of noise offset has been canceled out, its use for merging is not recommended.Training InformationIllustrious-XL was finetuned by repeating the training and merging a DoRA twice with sd-scripts.Style training has not been tested, but some users have reported that it can be learned successfully.Training Parameters (do not use)<ul><li>Optimizer: AdamWScheduleFree</li><li>Resolution: 1024 (w/ bucketing)</li><li>LR: 0.0005</li><li>LR Scheduler: Constant with warmup (warmup=100)</li><li>Batch size: 2</li><li>Epoch: 1</li><li>Rank/Alpha: 16/8</li><li>Conv Rank/Alpha: 2/0.5</li><li>Debiased Estimation: True</li></ul>Dataset InformationThe model was trained on a dataset of 5120 images.It was trained with 5120 images collected from Gelbooru. Images that met the following conditions or had the following tags were excluded:filetype:gif, score:&lt;0, mpixels:&lt;1048576, tagcount:&lt;16, artifacts, adversarialnoise, 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_(medium), mikumikudance, twitter_usernameTraining script (source code)sd-scripts ()NoticeThis model is licensed under the Fair AI Public License 1.0-SD ().If you modify this model, you must share both your changes and the original license._______________________________________________________________Illustrious-XL modificado para entrenamiento LoRAEste modelo reduce los cambios de estilo no deseados y mejora la precisión. Si vas a crear un modelo LoRA con este punto de control, no utilices --noise_offset.Nota: Este modelo no es adecuado para la generación de imágenes, ya que tiende a generar imágenes de mala calidad. Además, como se ha neutralizado el efecto del noise offset, no se recomienda su uso para combinar con otros modelos.Información de entrenamientoSe ha ajustado Illustrious-XL mediante la repetición del entrenamiento y la combinación de un DoRA dos veces con sd-scripts.Aunque el entrenamiento de estilos no se ha probado, algunos usuarios han informado que se pueden entrenar con éxito.Parámetros de entrenamiento (no los utilices)<ul><li>Optimizador: AdamWScheduleFree</li><li>Resolución: 1024 (con bucketing)</li><li>Tasa de aprendizaje (LR): 0.0005</li><li>Planificador de tasa de aprendizaje (LR Scheduler): Constante con warmup (warmup=100)</li><li>Tamaño del lote (Batch size): 2</li><li>Época (Epoch): 1</li><li>Rank/Alpha: 16/8</li><li>Conv Rank/Alpha: 2/0.5</li><li>Debiased Estimation: True</li></ul>Información del conjunto de datosEl modelo se entrenó con 5120 imágenes del conjunto de datos.Se entrenó con 5120 imágenes recopiladas de Gelbooru. Se excluyeron las imágenes que cumplían las siguientes condiciones o que tenían las siguientes etiquetas:filetype:gif, score:&lt;0, mpixels:&lt;1048576, tagcount:&lt;16, artifacts, adversarialnoise, 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_(medium), mikumikudance, twitter_usernameScript de entrenamiento (código fuente)sd-scripts (<a target="_blank" rel="noopener noreferrer nofollow" href="https://github.com/kohya-ss/sd-scripts">https://github.com/kohya-ss/sd-scripts</a>)AvisoEste modelo está licenciado bajo la Fair AI Public License 1.0-SD (<a target="_blank" rel="noopener noreferrer nofollow" href="https://freedevproject.org/faipl-1.0-sd/">https://freedevproject.org/faipl-1.0-sd/</a>).Si modificas este modelo, debes compartir tanto los cambios que realices como la licencia original.

Modified Illustrious-XL for LoRA training



This model reduces unintended style changes and improves accuracy. If you create a LoRA with this checkpoint, do not use --noise_offset.

Note: This model is not suitable for image generation, as it tends to generate ugly images. Also, since the effect of noise offset has been canceled out, its use for merging is not recommended.



Training Information



Illustrious-XL was finetuned by repeating the training and merging a DoRA twice with sd-scripts.

Style training has not been tested, but some users have reported that it can be learned successfully.



Training Parameters (do not use)







Optimizer: AdamWScheduleFree



Resolution: 1024 (w/ bucketing)



LR: 0.0005



LR Scheduler: Constant with warmup (warmup=100)



Batch size: 2



Epoch: 1



Rank/Alpha: 16/8



Conv Rank/Alpha: 2/0.5



Debiased Estimation: True



Dataset Information



The model was trained on a dataset of 5120 images.

It was trained with 5120 images collected from Gelbooru. Images that met the following conditions or had the following tags were excluded:

filetype:gif, score:<0, mpixels:<1048576, tagcount:<16, artifacts, adversarialnoise, 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_(medium), mikumikudance, twitter_username



Training script (source code)



sd-scripts ()



Notice



This model is licensed under the Fair AI Public License 1.0-SD ().

If you modify this model, you must share both your changes and the original license.



_______________________________________________________________





Illustrious-XL modificado para entrenamiento LoRA



Este modelo reduce los cambios de estilo no deseados y mejora la precisión. Si vas a crear un modelo LoRA con este punto de control, no utilices --noise_offset.

Nota: Este modelo no es adecuado para la generación de imágenes, ya que tiende a generar imágenes de mala calidad. Además, como se ha neutralizado el efecto del noise offset, no se recomienda su uso para combinar con otros modelos.



Información de entrenamiento



Se ha ajustado Illustrious-XL mediante la repetición del entrenamiento y la combinación de un DoRA dos veces con sd-scripts.

Aunque el entrenamiento de estilos no se ha probado, algunos usuarios han informado que se pueden entrenar con éxito.



Parámetros de entrenamiento (no los utilices)







Optimizador: AdamWScheduleFree



Resolución: 1024 (con bucketing)



Tasa de aprendizaje (LR): 0.0005



Planificador de tasa de aprendizaje (LR Scheduler): Constante con warmup (warmup=100)



Tamaño del lote (Batch size): 2



Época (Epoch): 1



Rank/Alpha: 16/8



Conv Rank/Alpha: 2/0.5



Debiased Estimation: True



Información del conjunto de datos



El modelo se entrenó con 5120 imágenes del conjunto de datos.

Se entrenó con 5120 imágenes recopiladas de Gelbooru. Se excluyeron las imágenes que cumplían las siguientes condiciones o que tenían las siguientes etiquetas:

filetype:gif, score:<0, mpixels:<1048576, tagcount:<16, artifacts, adversarialnoise, 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_(medium), mikumikudance, twitter_username



Script de entrenamiento (código fuente)



sd-scripts (https://github.com/kohya-ss/sd-scripts)



Aviso



Este modelo está licenciado bajo la Fair AI Public License 1.0-SD (https://freedevproject.org/faipl-1.0-sd/).

Si modificas este modelo, debes compartir tanto los cambios que realices como la licencia original.

Modified Illustrious-XL for LoRA training.It reduces unintended style changes.If you make a LoRA with this checkpoint, do not use "--noise_offset"!LoRA学習用のIllustrious-XLです。意図しない画風の変化を軽減します。これでLoRAを作る場合、「--noise_offset」は使用しないように！また、noise offsetの効果を打ち消したため、マージ用途の使用は推奨しません。Training information:Finetuned Illustrious-XL by repeating the training and merging a DoRA 3 times with sd-scripts.sd-scriptsで三回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。Dataset information: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_usernameTraining script(source code)sd-scripts( <a target="_blank" rel="noopener noreferrer nofollow" href="https://github.com/kohya-ss/sd-scripts">https://github.com/kohya-ss/sd-scripts</a> )Notice/おしらせ:This model is licensed under Fair AI Public License 1.0-SD( <a target="_blank" rel="noopener noreferrer nofollow" href="https://freedevproject.org/faipl-1.0-sd/">https://freedevproject.org/faipl-1.0-sd/</a> ).If you make modify this model, you must share both your changes and the original license.このモデルはFair AI Public License 1.0-SD( <a target="_blank" rel="noopener noreferrer nofollow" href="https://freedevproject.org/faipl-1.0-sd/">https://freedevproject.org/faipl-1.0-sd/</a> )でライセンスされています。このモデルを改変する場合、変更点および元のライセンスを明記する必要があります。

Files with SHA256: 89de75561c139161a1d10bd3a53992284ebb1ab717db259bbfdcde01a49cc985