Type | |
Stats | 271 2,498 |
Reviews | (41) |
Published | Sep 16, 2024 |
Base Model | |
Training | Steps: 7,160 Epochs: 10 |
Usage Tips | Clip Skip: 2 |
Hash | AutoV2 2CADDDCB0D |
[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.
===