add current model

.gitattributes

@@ -26,3 +26,13 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zstandard filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 ukiyoe-diffusion-256.pt filter=lfs diff=lfs merge=lfs -text
+models/ukiyoe-all/v1/ema_0.9999_056000.pt filter=lfs diff=lfs merge=lfs -text
+models/ukiyoe-all/v1/images/secondary_off_3.png filter=lfs diff=lfs merge=lfs -text
+models/ukiyoe-all/v1/images/secondary_on_0.png filter=lfs diff=lfs merge=lfs -text
+models/ukiyoe-all/v1/images/secondary_on_1.png filter=lfs diff=lfs merge=lfs -text
+models/ukiyoe-all/v1/images/secondary_on_2.png filter=lfs diff=lfs merge=lfs -text
+models/ukiyoe-all/v1/images/secondary_off_0.png filter=lfs diff=lfs merge=lfs -text
+models/ukiyoe-all/v1/images/secondary_off_1.png filter=lfs diff=lfs merge=lfs -text
+models/ukiyoe-all/v1/images/secondary_off_2.png filter=lfs diff=lfs merge=lfs -text
+models/ukiyoe-few/v1/ukiyoe_diffusion_256_010000.pt filter=lfs diff=lfs merge=lfs -text
+models/ukiyoe-few/v1/ukiyoe_diffusion_256_022000.pt filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -0,0 +1 @@
+**/.DS_Store

README.md

@@ -9,9 +9,78 @@ datasets:
 ---
 
 
-# Ukiyoe-256
+# Ukiyo-e Diffusion
 
-## ukiyoe\_diffusion\_256
+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
+
+### Ukiyoe-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
+
+![](models/ukiyoe-all/v1/images/secondary_off_3.png)
+![](models/ukiyoe-all/v1/images/secondary_off_0.png)
+![](models/ukiyoe-all/v1/images/secondary_off_1.png)
+![](models/ukiyoe-all/v1/images/secondary_off_2.png)
+
+###### Secondary On
+
+![](models/ukiyoe-all/v1/images/secondary_on_0.png)
+![](models/ukiyoe-all/v1/images/secondary_on_1.png)
+![](models/ukiyoe-all/v1/images/secondary_on_2.png)
+
+
+##### 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) Ukiyoe-few
 
 Finetuned on 5224 images from Wikiart (1168) and ? (). 
 
@@ -36,5 +105,5 @@ model_config = {
 }
 ```
 
-Trained using a fork of [guided-diffusion-sxela](https://github.com/thegenerativegeneration/guided-diffusion-sxela). (Added random crop).
+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.
 

models/ukiyoe-all/v1/ema_0.9999_056000.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f9af55461783619f25dcbf8953f028c0768108801860afe8c947428dee7a991
+size 553273895