Umamusume All in One LoRA
This is an All-in-One LoRA designed to generate a wide variety of characters from the popular game Umamusume: Pretty Derby with a single model. Without the hassle of managing individual character LoRAs, you can easily bring numerous Umamusume to life, including Stay Gold, Almond Eye, Loves Only You, and many more, with just this one file.
Notice
This model is a re-upload. The previous model page was accidentally deleted during a version update process. My apologies for the inconvenience!
✨ Features
Extensive Character Library: Capable of generating most of the main characters from the game with high fidelity.
Versatile Costume Support: Faithfully reproduces each character's unique racing outfits, as well as school uniforms, casual wear, and other styles.
Easy to Use: Achieve your desired images simply by inputting character names or feature tags, without the need for complex prompts.
🌟 Character & Prompt Information
For detailed prompt information regarding the characters, costumes, and features included in this LoRA, please refer to the Hugging Face link. Find the precise tags for the character you wish to create and utilize them in your prompts.
License
This model is released under "Derivative work guidelines for umamusume".
And "Fair-AI public license 1.0-SD" License
Description
This is pony-uaf version of SDXL AIO LoRA of Uma Musume
Recommended options
LoRA weight 1.0
Trigger words
[character name] \(umamusume\) or [character name]
For example,
manhattan cafe \(umamusume\)
hayakawa tazuna
Settings
For Stable Diffusion XL Pony V6
Please follow pony's generation guide.
SDXL-Pony version
trained on sd-scripts by kohya_ss and LyCORIS by KohakuBlueleaf
Thank you all a lot!
Base model : Pony Diffusion V6 XL
Hardware : 4x A6000 48GB
Training time : 39 hours
Dataset : ULTIMA Dataset + knowledge cutoff: 2024-04 (uploading is soon)
With synthetic natural language caption. half-half ratio
Max Token Length : 225
Resolution : 1024x1024
Dim, Alpha : 32
Algorithm : LoCon
Network dropout = 0.1
Optimizer : Lion8bit
weight decay=0.1, betas=(0.9, 0.95)
Steps : 10,777 (13 epochs)
Total Batch size : 64
4 GPU x 8 batch size x 2 Gradient Accumulation steps
Learning rate :
U-Net : 8e-5
Text Encoder 1 : 4e-5
Text Encoder 2 : 4e-5
warmup to 1e-4 for 100 steps and then kept constantLR scheduler
LR scheduler : constant with warmup.
Min SNR gamma : 5
Noise Offset : 0.0357