<ul><li>Conducted highly complex model merging and additional training.</li><li>Adjusted to recent artistic styles.</li><li>Reduced anatomical inconsistencies.</li><li>Enhanced resilience to additional training and LoRA.</li></ul><h1 id="heading-3"> &lt;lyco:Important Notice:1.37&gt;</h1>default CFG Scale : 7default Sampler : DPM++ 2M Karrasdefault Steps : 20Negative prompt : (worst quality:1.6),(low quality:1.4),(normal quality:1.2),lowres,jpeg artifacts,long neck,long body,bad anatomy,bad hands,text,error,missing fingers,extra digit,fewer digits,cropped,signature,watermark,username,artist name,<h1 id="heading-3">&lt;Marge: The Recipe :0.7&gt;</h1><ol><li>Merge Animagine 3.0 and 3.1 using a base alpha of 0.49, and merge layers from IN00 to OUT11 at 0.82.</li><li>Train a model on sd_xl_base_1.0_0.9vae.safetensors with ~4.6 million images on A100x4, at a learning rate of 1e-5, for ~2 epochs, and then, for compatibility with Animagine models' CLIP modules, further train it with a dataset of 164 AI-generated images to refine CLIP and Unet, using PRODIGY, Initial D at 1e-06, D Coefficient at 0.9, and a batch size of 4 for 1500 steps.</li><li>Merge 1. and 2. using two sets of coefficients:<ul><li>Set 1: 0.2, 0.6, 0.8, 0.9, 0.0, 0.8, 0.4, 1.0, 0.7, 0.9, 0.3, 0.1, 0.1, 0.5, 0.6, 0.0, 1.0, 0.6, 0.5, 0.5</li><li>Set 2: 0.9, 0.8, 0.6, 0.3, 0.9, 0.1, 0.4, 0.7, 0.4, 0.6, 0.2, 0.3, 0.0, 0.8, 0.3, 0.7, 0.7, 0.8, 0.2, 0.3.</li></ul></li><li>Merge Set 1 and Set 2 using a base alpha of 0.79 and merge layers from IN00 to OUT11 at 0.73 to create Set 3.</li><li>Train a LoRA based on Set 3 with a curated dataset of 12,018 AI-generated images, Lion optimizer, batch size of 4, gradient accumulation steps of 16, and learning rate 3e-5 for 4 epochs. This model is then blended into Set 3 itself at a strength of 0.2, resulting in the creation of 7th anime B.</li><li>Train another LoRA based on 7th anime B with the same dataset as described in step 2. but with Lion optimizer, batch size of 4, lr_scheduler_num_cycles at 5, and learning rate 1e-5 for 80 epochs. This model is then blended into 7th anime B itself at a strength of 0.366, finally resulting in the creation of 7th anime A.</li></ol>

Files with SHA256: d49e3d8d13b062b6149671ca675fcbf5daf9c55b13905ffe9f971a9437dcda9f