Hugging Face's logo

keras-dreambooth
/
dreambooth-piranesi

Text-to-Image
Keras
TF-Keras
stable-diffusion
keras-dreambooth
consentful
Model card Files Community
1
lposti commited on
Commit
9926dcd
·
1 Parent(s): 00a1984

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +15 -5
README.md CHANGED
@@ -1,21 +1,31 @@
1
  ---
2
  library_name: keras
 
 
 
 
 
 
 
3
  ---
4
 
5
  ## Model description
6
 
7
- More information needed
8
 
9
- ## Intended uses & limitations
10
 
11
- More information needed
 
12
 
13
- ## Training and evaluation data
14
 
15
- More information needed
 
16
 
17
  ## Training procedure
18
 
 
19
  ### Training hyperparameters
20
 
21
  The following hyperparameters were used during training:
 
1
  ---
2
  library_name: keras
3
+ license: apache-2.0
4
+ tags:
5
+ - keras
6
+ - stable-diffusion
7
+ - text-to-image
8
+ - keras-dreambooth
9
+ - consentful
10
  ---
11
 
12
  ## Model description
13
 
14
+ This is a Keras Dreambooth model fine-tuned to some 18th century etching artworks by italian artist [Giambattista Piranesi](https://en.wikipedia.org/wiki/Giovanni_Battista_Piranesi).
15
 
16
+ A few samples below
17
 
18
+ ![](output-samples/db-piranesi_0.jpg) ![](output-samples/db-piranesi_1.jpg) ![](output-samples/db-piranesi_2.jpg) ![](output-samples/db-piranesi_3.jpg)
19
+ ![](output-samples/db-piranesi_4.jpg)
20
 
21
+ ## Intended uses & limitations
22
 
23
+ The base prompt is "image of monuments in sks style".
24
+ A slightly better prompt would be "image of monuments in sks style, 8k, high quality, old paper" with negative prompt "distorted".
25
 
26
  ## Training procedure
27
 
28
+
29
  ### Training hyperparameters
30
 
31
  The following hyperparameters were used during training: