multimodalart HF staff commited on
Commit
01d267f
1 Parent(s): eed3674

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +40 -1
README.md CHANGED
@@ -6,6 +6,45 @@ tags:
6
  - text-to-image
7
  license: bigscience-bloom-rail-1.0
8
  inference: true
 
9
  ---
10
 
11
- # stable-diffusion-wikiart v1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6
  - text-to-image
7
  license: bigscience-bloom-rail-1.0
8
  inference: true
9
+
10
  ---
11
 
12
+ # stable-diffusion-wikiart
13
+
14
+ sd-wikiart is a stable diffusion model that has been fine-tuned on the [wikiart dataset](https://huggingface.co/datasets/fusing/wikiart_captions) to generate artistic images in different style and genres.
15
+
16
+ ## License
17
+
18
+ This model is open access and available to all, with a CreativeML OpenRAIL-M license further specifying rights and usage.
19
+ The CreativeML OpenRAIL License specifies:
20
+
21
+ 1. You can't use the model to deliberately produce nor share illegal or harmful outputs or content
22
+ 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
23
+ 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)
24
+ [Please read the full license here](https://huggingface.co/spaces/CompVis/stable-diffusion-license)
25
+
26
+ ## Downstream Uses
27
+
28
+ This model can be used for entertainment purposes and as a generative art assistant.
29
+
30
+ ## Example Code
31
+
32
+ ```python
33
+ import torch
34
+ from diffusers import StableDiffusionPipeline
35
+
36
+ model_id = "valhalla/sd-wikiart"
37
+ device = "cuda"
38
+
39
+ pipe = StableDiffusionPipeline.from_pretrained(
40
+ model_id,
41
+ torch_dtype=torch.float16,
42
+ )
43
+ pipe = pipe.to(device)
44
+
45
+ prompt = "a painting of eiffel tower in the style of surrealism"
46
+ with torch.autocast("cuda"):
47
+ image = pipe(prompt, guidance_scale=7.5).images[0]
48
+
49
+ image.save("eiffel_impressionism.png")
50
+ ```