Momo XL is an anime-style SDXL base model, finetuned specifically for Danbooru tags.Key Features:<ul><li>Danbooru Target SDXL: Finetuned with a focus on Danbooru's content.</li><li>Best with Danbooru Tags: Works optimally when prompted with Danbooru-style tags.</li><li>Lora Compatibility: Compatible with most Loras available on the hub.</li></ul>Usage Instructions:<ul><li>It is recommended to separate tags with commas; tags can be used in any order.</li><li>Use <code>"year 20XX"</code> to generate art in the style of that specific year (e.g., year 2023).</li><li>High step size could be beneficial.</li></ul>Disclaimer: This model may produce unexpected results. Use at your own risk. Community: Join our <a target="_new" rel="ugc" href="https://discord.gg/Ph5w63p3Wx">Discord community</a> and share your creations!If you enjoy using Momo XL, feel free to drop by and say hi.Check out the official release page on Hugging Face: <a target="_new" rel="ugc" href="https://huggingface.co/PotatoBox/Momo-XL">Momo XL</a>Detailed information about the training will be released later on the repository. Thank you! 😊<hr />Momo XL - Training Details (Oct 15, 2024)Dataset: Momo XL was trained on a dataset of 400,000+ images sourced from Danbooru.Base Model: Momo XL is built on top of SDXL and includes elements from two additional finetuned models:<ul><li>Formula: SDXL_base + (Animagine 3.0 base - SDXL_base) * 1.0 + (Pony V6 - SDXL_base) * 0.5</li></ul>For more information about the source models:<ul><li>Animagine 3.0 base</li><li>Pony V6</li></ul>For more detailed information about the training process, visit the official Hugging Face repository <a target="_new" rel="ugc" href="https://huggingface.co/PotatoBox/Momo-XL">here</a>.

Momo XL

momoXL_momoXL.safetensors

<a target="_blank" rel="noopener noreferrer nofollow" href="https://civitai.com/models/826721">https://civitai.com/models/826721</a>

Files with SHA256: a0c9040f599727d51163fbaf2e0386fc4afd6789bfff9853a1d8a3e8ce3545ee