|
|
--- |
|
|
tags: |
|
|
- discodiffusion |
|
|
- guideddiffusion |
|
|
thumbnail: https://de.gravatar.com/userimage/52045156/8ab369c1d246e65bda88813ce7c4cb81.jpeg |
|
|
datasets: |
|
|
- wikiart |
|
|
|
|
|
--- |
|
|
|
|
|
|
|
|
# Ukiyo-e Diffusion |
|
|
|
|
|
If you make something using these models, you're welcome to mention me [@thegenerativegeneration](https://www.instagram.com/thegenerativegeneration/) |
|
|
|
|
|
|
|
|
Named by dataset used. Current and best version is [models/ukiyoe-all/v1/ema_0.9999_056000.pt](models/ukiyoe-all/v1/ema_0.9999_056000.pt) |
|
|
|
|
|
# Current Plans |
|
|
|
|
|
* clean dataset |
|
|
* remove borders |
|
|
* remove some of the samples with text in them |
|
|
|
|
|
# Models |
|
|
|
|
|
## Ukiyo-e-all |
|
|
|
|
|
### v1 |
|
|
|
|
|
[models/ukiyoe-all/v1/ema_0.9999_056000.pt](models/ukiyoe-all/v1/ema_0.9999_056000.pt) |
|
|
|
|
|
Model configuration is: |
|
|
|
|
|
```python |
|
|
model_config = { |
|
|
'attention_resolutions': '32, 16, 8', |
|
|
'class_cond': False, |
|
|
'image_size': 256, |
|
|
'learn_sigma': True, |
|
|
'rescale_timesteps': True, |
|
|
'noise_schedule': 'linear', |
|
|
'num_channels': 128, |
|
|
'num_heads': 4, |
|
|
'num_res_blocks': 2, |
|
|
'resblock_updown': True, |
|
|
'use_checkpoint': True, |
|
|
'use_fp16': True, |
|
|
'use_scale_shift_norm': True, |
|
|
} |
|
|
``` |
|
|
#### Tips |
|
|
|
|
|
- Results closest to original training data are achieved by turning off the secondary model in Disco Diffusion. |
|
|
- Turning secondary model on can lead to very creative results |
|
|
- It is not necessary to specify Ukiyo-e as artstyle to get ukiyo-e-like images. |
|
|
|
|
|
#### Examples |
|
|
|
|
|
If you make something nice using these models, I would like to link your image. |
|
|
|
|
|
##### Secondary Off |
|
|
|
|
|
 |
|
|
 |
|
|
 |
|
|
 |
|
|
|
|
|
##### Secondary On |
|
|
|
|
|
 |
|
|
 |
|
|
 |
|
|
|
|
|
|
|
|
#### About |
|
|
Trained from scratch on a ~170000 images corpus of [ukiyo-e.org](https://ukiyo-e.org) filtered by [colorfulness](https://pyimagesearch.com/2017/06/05/computing-image-colorfulness-with-opencv-and-python/ |
|
|
) >= 5. |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
## (Deprecated) Ukiyo-e-few |
|
|
|
|
|
[models/ukiyoe-few/v1/ukiyoe_diffusion_256_022000.pt](models/ukiyoe-few/v1/ukiyoe_diffusion_256_022000.pt) |
|
|
|
|
|
Finetuned on 5224 images from Wikiart (1168) and ? (). |
|
|
|
|
|
|
|
|
Model configuration is |
|
|
|
|
|
```python |
|
|
model_config = { |
|
|
'attention_resolutions': '16', |
|
|
'class_cond': False, |
|
|
'diffusion_steps': 1000, |
|
|
'rescale_timesteps': True, |
|
|
'timestep_respacing': 'ddim100', |
|
|
'image_size': 256, |
|
|
'learn_sigma': True, |
|
|
'noise_schedule': 'linear', |
|
|
'num_channels': 128, |
|
|
'num_heads': 1, |
|
|
'num_res_blocks': 2, |
|
|
'use_checkpoint': True, |
|
|
'use_scale_shift_norm': False |
|
|
} |
|
|
``` |
|
|
|
|
|
Trained using a fork of [guided-diffusion-sxela](https://github.com/thegenerativegeneration/guided-diffusion-sxela). Added random crop which did not lead to good results. |
|
|
|
|
|
|
