kayfahaarukku/UrangDiffusion-1.2

UrangDiffusion 1.2

UrangDiffusion 1.2 (oo-raw-ng Diffusion) is an updated version of UrangDiffusion 1.1. This version provides dataset refresh, improvements over the last iteration and training parameter correction.

Standard Prompting Guidelines

The model is finetuned from Animagine XL 3.1. However, there is a little bit changes on dataset captioning, therefore there is some different default prompt used:

Default prompt:

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

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, displeasing

Default configuration:

Euler a with around 25-30 steps, CFG 5-7, and ENSD set to 31337. Sweetspot is around 28 steps and CFG 7.

Training Configurations

• Finetuned from: Animagine XL 3.1

Pretraining:

• Dataset size: ~23,600 images

• GPU: 1xA100

• Optimizer: AdaFactor

• Unet Learning Rate: 3.75e-6

• Text Encoder Learning Rate: 1.875e-6

• Batch Size: 48

• Gradient Accumulation: 1

• Warmup steps: 100 steps

• Min SNR Gamma: 5

• Epoch: 10 (epoch 9 is used)

Finetuning:

• Dataset size: ~6,800 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

• Warmup steps: 5%

• Min SNR Gamma: 5

• Epoch: 10

• Noise Offset: 0.0357

Added Series

Wuthering Waves, Zenless Zone Zero, and hololiveEN -Justice- have been added to the model.

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