kayfahaarukku / UrangDiffusion-1.0

UrangDiffusion 1.0

UrangDiffusion (oo-raw-ng Diffusion) is a sequel to AingDiffusion. This checkpoint is fully trained, unlike its predecessor.

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 sole work".

The model went through two steps of training: pretraining and finetuning. Pretraining is to make the model learn new things, while finetuning ensures the images produced by the model are decent (A.K.A. having a standard style) without mentioning style in the prompt.

Standard Prompting Guidelines

The model is finetuned from Animagine XL 3.1. However, I didn’t finetune the aesthetic tags trained with 3.1 due to some considerations. Therefore, the default prompt uses 3.0’s default prompting format:

Default prompt :

1girl/1boy, character name, from what series, everything else in any order, masterpiece, best quality

Default negative prompt :

lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, artist name

Default configuration:

Euler a with around 25-30 steps, CFG 5-7, and ENSD set to 31337.

Training Configurations

• Finetuned from: Animagine XL 3.1

Pretraining:

• Dataset size: ~17,200 images

• GPU: 1xA100

• Optimizer: AdaFactor

• Unet Learning Rate: 2.5e-6

• Text Encoder Learning Rate: 1.25e-6

• Batch Size: 48

• Gradient Accumulation: 1

• Epoch: 10 (epoch 8 is used)

Finetuning:

• Dataset size: ~1,300 images

• GPU: 1xA100

• Optimizer: AdaFactor

• Unet Learning Rate: 2e-6

• Text Encoder Learning Rate: - (Train TE set to False)

• Batch Size: 48

• Gradient Accumulation: 1

• Epoch: 10 (epoch 8 is used)

Added Series

Wuthering Waves and hololiveEN -Justice- have been added to the model.

Warning , the dataset is very small, and it still struggles to generate the characters added accurately. You can generate them with alternate costumes, but if you’re trying to generate them following the official art, you will struggle a lot.

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.

License

UrangDiffusion falls under the Fair AI Public License 1.0-SD license.