Files changed (1) hide show
  1. README.md +14 -4
README.md CHANGED
@@ -1,8 +1,13 @@
 
 
 
 
 
 
 
1
  ```python
2
  from diffusers import UnCLIPPipeline
3
  import torch
4
- import random
5
- import numpy as np
6
 
7
  pipe = UnCLIPPipeline.from_pretrained("fusing/karlo_unclip", torch_dtype=torch.float16)
8
  pipe = pipe.to('cuda')
@@ -11,7 +16,12 @@ prompt = "a high-resolution photograph of a big red frog on a green leaf."
11
 
12
  image = pipe([prompt]).images[0]
13
 
14
- image.save("/home/patrick_huggingface_co/images/frog.png")
15
  ```
16
 
17
- ![img](https://huggingface.co/datasets/patrickvonplaten/images/resolve/main/frog.png)
 
 
 
 
 
 
1
+ ## Karlo v1 alpha
2
+
3
+ Karlo is a text-conditional image generation model based on OpenAI's unCLIP architecture with the improvement over the standard super-resolution model from 64px to 256px, recovering high-frequency details only in the small number of denoising steps.
4
+
5
+
6
+ Karlo is available in diffusers!
7
+
8
  ```python
9
  from diffusers import UnCLIPPipeline
10
  import torch
 
 
11
 
12
  pipe = UnCLIPPipeline.from_pretrained("fusing/karlo_unclip", torch_dtype=torch.float16)
13
  pipe = pipe.to('cuda')
 
16
 
17
  image = pipe([prompt]).images[0]
18
 
19
+ image.save("./frog.png")
20
  ```
21
 
22
+ ![img](https://huggingface.co/datasets/patrickvonplaten/images/resolve/main/frog.png)
23
+
24
+ [Original codebase](https://github.com/kakaobrain/karlo)
25
+
26
+ This alpha version of Karlo is trained on 115M image-text pairs, including [COYO](https://github.com/kakaobrain/coyo-dataset)-100M high-quality subset, CC3M, and CC12M. For those who are interested in a better version of Karlo trained on more large-scale high-quality datasets, please visit the landing page of our application [B^DISCOVER](https://bdiscover.kakaobrain.com/).
27
+