justinpinkney commited on
Commit
73eca23
1 Parent(s): 0250758

Update app.py

Browse files
Files changed (1) hide show
  1. app.py +5 -3
app.py CHANGED
@@ -46,11 +46,13 @@ def main(
46
 
47
  description = \
48
  """
 
 
49
  Generate variations on an input image using a fine-tuned version of Stable Diffision.
50
  Trained by [Justin Pinkney](https://www.justinpinkney.com) ([@Buntworthy](https://twitter.com/Buntworthy)) at [Lambda](https://lambdalabs.com/)
51
 
52
  This version has been ported to 🤗 Diffusers library, see more details on how to use this version in the [Lambda Diffusers repo](https://github.com/LambdaLabsML/lambda-diffusers).
53
- __For the original training code see [this repo](https://github.com/justinpinkney/stable-diffusion).
54
 
55
  ![](https://raw.githubusercontent.com/justinpinkney/stable-diffusion/main/assets/im-vars-thin.jpg)
56
 
@@ -66,8 +68,8 @@ This creates images which have the same rough style and content, but different d
66
  This is a totally different approach to the img2img script of the original Stable Diffusion and gives very different results.
67
 
68
  The model was fine tuned on the [LAION aethetics v2 6+ dataset](https://laion.ai/blog/laion-aesthetics/) to accept the new conditioning.
69
- Training was done on 4xA6000 GPUs on [Lambda GPU Cloud](https://lambdalabs.com/service/gpu-cloud).
70
- More details on the method and training will come in a future blog post.
71
  """
72
 
73
  device = "cuda" if torch.cuda.is_available() else "cpu"
 
46
 
47
  description = \
48
  """
49
+ __Now using Image Variations v2!__
50
+
51
  Generate variations on an input image using a fine-tuned version of Stable Diffision.
52
  Trained by [Justin Pinkney](https://www.justinpinkney.com) ([@Buntworthy](https://twitter.com/Buntworthy)) at [Lambda](https://lambdalabs.com/)
53
 
54
  This version has been ported to 🤗 Diffusers library, see more details on how to use this version in the [Lambda Diffusers repo](https://github.com/LambdaLabsML/lambda-diffusers).
55
+ For the original training code see [this repo](https://github.com/justinpinkney/stable-diffusion).
56
 
57
  ![](https://raw.githubusercontent.com/justinpinkney/stable-diffusion/main/assets/im-vars-thin.jpg)
58
 
 
68
  This is a totally different approach to the img2img script of the original Stable Diffusion and gives very different results.
69
 
70
  The model was fine tuned on the [LAION aethetics v2 6+ dataset](https://laion.ai/blog/laion-aesthetics/) to accept the new conditioning.
71
+ Training was done on 8xA100 GPUs on [Lambda GPU Cloud](https://lambdalabs.com/service/gpu-cloud).
72
+ More details are on the [model card](https://huggingface.co/lambdalabs/sd-image-variations-diffusers).
73
  """
74
 
75
  device = "cuda" if torch.cuda.is_available() else "cpu"