DD-65 commited on
Commit
ecb3d9a
·
verified ·
1 Parent(s): 9bb275e

Update model card

Browse files
Files changed (1) hide show
  1. README.md +12 -6
README.md CHANGED
@@ -1,5 +1,5 @@
1
  ---
2
- license: mit
3
  library_name: diffusers
4
  pipeline_tag: unconditional-image-generation
5
  tags:
@@ -7,12 +7,12 @@ tags:
7
  - ddpm
8
  - unconditional-image-generation
9
  - art
 
10
  ---
11
 
12
  # RandomArt DDPM
13
 
14
- RandomArt is an unconditional diffusion model trained from scratch on a local
15
- collection of artwork images. It generates 128×128 painterly and abstract
16
  compositions without text prompts.
17
 
18
  ## Examples
@@ -36,7 +36,7 @@ elif torch.cuda.is_available():
36
  else:
37
  device = "cpu"
38
 
39
- pipe = DDPMPipeline.from_pretrained("DD_65/randomart").to(device)
40
  image = pipe(num_inference_steps=250).images[0]
41
  image.save("randomart.png")
42
  ```
@@ -63,5 +63,11 @@ their intended use.
63
 
64
  ## License
65
 
66
- No broad license grant is asserted for the training data. Review the model and
67
- training-data provenance before production or commercial use.
 
 
 
 
 
 
 
1
  ---
2
+ license: other
3
  library_name: diffusers
4
  pipeline_tag: unconditional-image-generation
5
  tags:
 
7
  - ddpm
8
  - unconditional-image-generation
9
  - art
10
+ - diffusion-models-class
11
  ---
12
 
13
  # RandomArt DDPM
14
 
15
+ RandomArt is an unconditional diffusion model trained from scratch on 7k Images of [huggan/wikiart](https://huggingface.co/datasets/huggan/wikiart) on Apple Silicon. It generates 128×128 painterly and abstract
 
16
  compositions without text prompts.
17
 
18
  ## Examples
 
36
  else:
37
  device = "cpu"
38
 
39
+ pipe = DDPMPipeline.from_pretrained("DD-65/randomart").to(device)
40
  image = pipe(num_inference_steps=250).images[0]
41
  image.save("randomart.png")
42
  ```
 
63
 
64
  ## License
65
 
66
+ This model was trained on [huggan/wikiart](https://huggingface.co/datasets/huggan/wikiart), whose license limits
67
+ use to non-commercial research and requires compliance with WikiArt's
68
+ terms and conditions.
69
+
70
+ The model weights are therefore provided for non-commercial research
71
+ and experimental use only. No rights are granted to the underlying
72
+ artworks, and users are responsible for ensuring their use complies
73
+ with applicable copyright law and WikiArt's terms.