Modified PonyDiffusionV6XL for LoRA trainingThis model may improve the quality of LoRA.not suitable for artstyle LoRAs and photorealistic styleこのモデルはLoRAの品質を改善するかもしれません。画風LoRAと実写風には向いていません。<h2 id="heading-187">Training information:</h2>Finetuned PonyDiffusionV6XL by repeating the training and merging a LoRA two times with sd-scripts.sd-scriptsで二回lora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。<h3 id="heading-204">DO NOT USE THESE PARAMETERS FOR LORA!</h3>Training parameters(This is not a recommended setting):Resolution:1024x1024Bucketing: enabled,min512,max2048LR scheduler: cosine_with_restartsOptimizer: LionKeep tokens:0Network dim/alpha: 8/4Conv dim/alpha:1/0.25Gradient checkpointing:trueGrad acc steps:1Batch size: 2Epochs:1Unet learning rate:0.00015Shuffle caption:trueSeed:42LR warmup steps:100<h2 id="heading-188">Dataset information:</h2>Dataset size: 4157<h2 id="heading-189">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="heading-190">Notice/おしらせ:</h2>This model is licensed under the <a target="_blank" rel="ugc" href="https://freedevproject.org/faipl-1.0-sd/">Fair AI Public License 1.0-SD</a>.If you make modify this model, you must share both your changes and the original license.You are not permitted to run inference of this model on websites or applications allowing any form of monetization (paid inference, faster tiers, etc.). This applies to any derivative models or model merges.このモデルは<a target="_blank" rel="ugc" href="https://freedevproject.org/faipl-1.0-sd/">Fair AI Public License 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。このモデルの生成サービスでの商用利用を禁止します。これは継承先にも適用されます。

GenePony(for LoRA training)

Baked VAE(works without no-half-vae)

Files with SHA256: 5a746fc7a2e9b149f3a5b9a0d14f590ddd099b633995237f78669a1a2912456f