ghost
Sign In

UrangDiffusion | an AingDiffusion XL sequel

186
1.6k
11.0k
33
Updated: Sep 26, 2024
base modelanimewomangame charactergirlsman
image (9).png
image.png
image (10).png
image (3).png
image (5).png
image (6).png
image (7).png
image (13).png
image (15).png
image (17).png
image (2).png
image (12).png
Images hidden due to mature content settings
Verified:
SafeTensor
Type
Checkpoint Trained
Stats
271
2,498
Reviews
(41)
Published
Sep 16, 2024
Base Model
SDXL 1.0
Training
Steps: 7,160
Epochs: 10
Usage Tips
Clip Skip: 2
Hash
AutoV2
2CADDDCB0D
default creator card background decoration
Sleepless Nights
kayfahaarukku's Avatar
kayfahaarukku
License:
CreativeML Open RAIL++-MAddendum
image (9).png
image.png
image (10).png
image (3).png
image (5).png
image (6).png
image (7).png
image (13).png
image (15).png
image (17).png
image (2).png
image (12).png
Images hidden due to mature content settings

[UrangDiffusion v1.4 is sponsored by CagliostroLab, the makers of Animagine XL]

UrangDiffusion v1.4 (oo-raw-ng Diffusion) is an updated version of UrangDiffusion v1.3. This version provides refreshed dataset, better image tagging, improvements over the last iteration, training parameter correction, and better overall generation results.

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.”

Standard Prompting Guidelines

The model is finetuned from Animagine XL 3.1, which is trained with danbooru tags. 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: nsfw, lowres, (bad), text, error, fewer, extra, missing, worst quality, jpeg artifacts, low quality, watermark, unfinished, displeasing, oldest, early, chromatic aberration, signature, extra digits, artistic error, username, scan, [abstract],

  • Default configuration: Euler a with around 25-30 steps, CFG 5-7, and ENSD set to 31337. Sweet spot is around 26 steps and CFG 5.

Training Configurations

Finetuned from: Animagine XL 3.1

Pretraining:

  • Dataset size: 34,368 images

  • GPU: 1xA100 80GB

  • 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: 5

  • Epoch: 10 (epoch 9 is used)

Finetuning:

  • Dataset size: 7,104 images

  • GPU: 1xA100 80GB

  • Optimizer: AdaFactor

  • Unet Learning Rate: 3e-6

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

  • Batch Size: 48

  • Gradient Accumulation: 1

  • Warmup steps: 5%

  • Min SNR: 5

  • Epoch: 10 (epoch 8 is used)

  • Noise Offset: 0.0357

Added Series

Wuthering Waves, Zenless Zone Zero, Sewayaki Kitsune no Senko-san and hololiveEN -Justice- have been added to the model.

Special Thanks

  • CagliostroLab for sponsoring the model pretraining by letting me borrowed the organization’s RunPod account.

  • 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.

===

https://tensor.art/u/699664973248342228