<img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/aa63cd08-7cd6-44db-adb6-c4814fadb8d0/width=525/aa63cd08-7cd6-44db-adb6-c4814fadb8d0.jpeg" /><h2 id="heading-816">A NEW SERIES OF MODELS TO COME!</h2>This is the first SDXL model I've successfully trained and even at that it isn't perfect. Works Best at a weighting of 0.9 - 1.0.Generation parameters: suzu, fox ears, fox tail, brown eyes, orange-brown hair, yellow miko kimono, medium hair, ahoge, hair between eyesUses the same dataset from <a rel="ugc" href="https://civarchive.com/models/91673/suzu-sewayaki-kitsune-no-senko-san">Suzu 1.5 v4</a><hr />Additional Details / Training Info (For anyone wanting to train SDXL for themselves)Trained using OneTrainer (<a rel="ugc" href="https://github.com/Nerogar/OneTrainer">Link</a>) (<a rel="ugc" href="https://huggingface.co/JVGA/OneTrainerSDXL12GBPreset/tree/main">Preset File</a>)20 Epochs (Final model uses the full 20)10 Dataset Repeats0.0003 Learning rate896x896 Train Resolution (Could go higher)(NOTE: FOR ANYONE LOOKING TO TRAIN ON THE KOHYA SDXL COLAB, DO NOT. IT IS BEYOND BROKEN AND ANY MODEL IT "TRAINS" DOESN'T WORK)

Files with SHA256: c44810a8771a685efbfd2cd6ed163642e65728d74399fd0109e6a4c374f6ee6d