joachimsallstrom commited on
Commit
af38605
1 Parent(s): cf42e39

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +34 -1
README.md CHANGED
@@ -1,4 +1,37 @@
1
- This is the Double Exposure style trained on personally generated images from the MidJourney version 4 model.
2
  ---
3
  license: creativeml-openrail-m
 
 
 
4
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
  license: creativeml-openrail-m
3
+ tags:
4
+ - stable-diffusion
5
+ - text-to-image
6
  ---
7
+ **Double Exposure Diffusion**
8
+
9
+ This is the Double Exposure Diffusion model, trained on personally generated images off of MidJourney version 4.
10
+ You trigger double exposure style images using token: **_dbl_ex_**.
11
+
12
+ **Videogame Characters rendered with the model:**
13
+ ![Videogame Samples](https://huggingface.co/nitrosocke/mo-di-diffusion/resolve/main/modi-samples-01s.jpg)
14
+ **Animal Characters rendered with the model:**
15
+ ![Animal Samples](https://huggingface.co/nitrosocke/mo-di-diffusion/resolve/main/modi-samples-02s.jpg)
16
+ **Cars and Landscapes rendered with the model:**
17
+ ![Misc. Samples](https://huggingface.co/nitrosocke/mo-di-diffusion/resolve/main/modi-samples-03s.jpg)
18
+
19
+ #### Prompt and settings for Lara Croft:
20
+ **modern disney lara croft**
21
+ _Steps: 50, Sampler: Euler a, CFG scale: 7, Seed: 3940025417, Size: 512x768_
22
+
23
+ #### Prompt and settings for the Lion:
24
+ **modern disney (baby lion) Negative prompt: person human**
25
+ _Steps: 50, Sampler: Euler a, CFG scale: 7, Seed: 1355059992, Size: 512x512_
26
+
27
+ This model was trained using the diffusers based dreambooth training by ShivamShrirao using prior-preservation loss and the _train-text-encoder_ flag in 9.000 steps.
28
+
29
+ ## License
30
+
31
+ This model is open access and available to all, with a CreativeML OpenRAIL-M license further specifying rights and usage.
32
+ The CreativeML OpenRAIL License specifies:
33
+
34
+ 1. You can't use the model to deliberately produce nor share illegal or harmful outputs or content
35
+ 2. The authors claims no rights on the outputs you generate, you are free to use them and are accountable for their use which must not go against the provisions set in the license
36
+ 3. You may re-distribute the weights and use the model commercially and/or as a service. If you do, please be aware you have to include the same use restrictions as the ones in the license and share a copy of the CreativeML OpenRAIL-M to all your users (please read the license entirely and carefully)
37
+ [Please read the full license here](https://huggingface.co/spaces/CompVis/stable-diffusion-license)