Hugging Face's logo

lambda
/
sd-image-variations-diffusers

Image-to-Image
Diffusers
StableDiffusionImageVariationPipeline
stable-diffusion
stable-diffusion-diffusers
Model card Files
xet
 Community
25
justinpinkney commited on
Commit
e5b0426
·
1 Parent(s): a2a1398

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +5 -1
README.md CHANGED
@@ -12,15 +12,19 @@ tags:
12
  # Stable Diffusion Image Variations Model Card
13
 
14
  📣 V2 model released, and blurriness issues fixed! 📣
 
15
  🧨🎉 Image Variations is now natively supported in 🤗 Diffusers! 🎉🧨
16
 
 
 
17
  ## Version 2
18
 
19
  This version of Stable Diffusion has been fine tuned from [CompVis/stable-diffusion-v1-4-original](https://huggingface.co/CompVis/stable-diffusion-v-1-4-original) to accept CLIP image embedding rather than text embeddings. This allows the creation of "image variations" similar to DALLE-2 using Stable Diffusion. This version of the weights has been ported to huggingface Diffusers, to use this with the Diffusers library requires the [Lambda Diffusers repo](https://github.com/LambdaLabsML/lambda-diffusers).
20
 
21
  This model was trained in two stages and longer than the original variations model and gives better image quality and better CLIP rated similarity compared to the original version
22
 
23
- ![](https://raw.githubusercontent.com/justinpinkney/stable-diffusion/main/assets/im-vars-thin.jpg)
 
24
 
25
  ## Example
26
 
 
12
  # Stable Diffusion Image Variations Model Card
13
 
14
  📣 V2 model released, and blurriness issues fixed! 📣
15
+
16
  🧨🎉 Image Variations is now natively supported in 🤗 Diffusers! 🎉🧨
17
 
18
+ ![](https://raw.githubusercontent.com/justinpinkney/stable-diffusion/main/assets/im-vars-thin.jpg)
19
+
20
  ## Version 2
21
 
22
  This version of Stable Diffusion has been fine tuned from [CompVis/stable-diffusion-v1-4-original](https://huggingface.co/CompVis/stable-diffusion-v-1-4-original) to accept CLIP image embedding rather than text embeddings. This allows the creation of "image variations" similar to DALLE-2 using Stable Diffusion. This version of the weights has been ported to huggingface Diffusers, to use this with the Diffusers library requires the [Lambda Diffusers repo](https://github.com/LambdaLabsML/lambda-diffusers).
23
 
24
  This model was trained in two stages and longer than the original variations model and gives better image quality and better CLIP rated similarity compared to the original version
25
 
26
+ See training details and v1 vs v2 comparison below.
27
+
28
 
29
  ## Example
30