justinpinkney
commited on
Merge branch 'main' of https://huggingface.co/lambdalabs/sd-image-variations-diffusers into main
Browse files
README.md
CHANGED
@@ -2,7 +2,7 @@
|
|
2 |
thumbnail: "https://repository-images.githubusercontent.com/523487884/fdb03a69-8353-4387-b5fc-0d85f888a63f"
|
3 |
datasets:
|
4 |
- ChristophSchuhmann/improved_aesthetics_6plus
|
5 |
-
license:
|
6 |
tags:
|
7 |
- stable-diffusion
|
8 |
- stable-diffusion-diffusers
|
@@ -12,15 +12,19 @@ tags:
|
|
12 |
# Stable Diffusion Image Variations Model Card
|
13 |
|
14 |
π£ V2 model released, and blurriness issues fixed! π£
|
|
|
15 |
π§¨π Image Variations is now natively supported in π€ Diffusers! ππ§¨
|
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 |
-
|
|
|
24 |
|
25 |
## Example
|
26 |
|
|
|
2 |
thumbnail: "https://repository-images.githubusercontent.com/523487884/fdb03a69-8353-4387-b5fc-0d85f888a63f"
|
3 |
datasets:
|
4 |
- ChristophSchuhmann/improved_aesthetics_6plus
|
5 |
+
license: creativeml-openrail-m
|
6 |
tags:
|
7 |
- stable-diffusion
|
8 |
- stable-diffusion-diffusers
|
|
|
12 |
# Stable Diffusion Image Variations Model Card
|
13 |
|
14 |
π£ V2 model released, and blurriness issues fixed! π£
|
15 |
+
|
16 |
π§¨π Image Variations is now natively supported in π€ Diffusers! ππ§¨
|
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 |
|