UrangDiffusion v3.0 (oo-raw-ng Diffusion) is the first UrangDiffusion version that utilize Animagine XL 4.0 as the base.
The name “Urang” comes from Sundanese, meaning “We/Our/I.” The history behind the name is to make the model not only suitable for me but also for many people. Another reason is that I use many resources (training scripts, dataset collecting scripts, etc.) from other people. It’s unfair to claim this model as “my work.”
Standard Prompting Guidelines
Prompting guide:
https://cdn-uploads.huggingface.co/production/uploads/64c088660a4d02f37a965f6c/YPe3MCnQAHM7nCZ1vQ7vI.png [Animagine XL 4.0 prompting guide]
Default negative prompt: lowres, bad anatomy, bad hands, text, error, missing finger, extra digits, fewer digits, cropped, worst quality, low quality, low score, bad score, average score, signature, watermark, username, blurry
Default configuration: Euler a with around 25-30 steps, CFG 5-7, and ENSD set to 31337. Sweet spot is around 27 steps and CFG 6.
Training Configurations
Finetuned from: Animagine XL 4.0-Zero
Finetuning:
Dataset size: ~1,600 images
GPU: 1xA100 80GB
Optimizer: AdaFactor
Unet Learning Rate: 1.25e-6
Text Encoder Learning Rate: N/A (Turned off)
Batch Size: 48
Gradient Accumulation: 1
Warmup steps: 5%
Min SNR: 5
Epoch: 11
Special Thanks
My co-workers(?) at CagliostroLab for the insights and feedback.
Nur Hikari and Vanilla Latte for quality control.
Linaqruf, my tutor and role model in AI-generated images, and also the person behind tag ordering.
License
UrangDiffusion v3.0 falls under the CreativeML OpenRAIL++-M license.