Instructions to use DD-65/randomart with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use DD-65/randomart with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("DD-65/randomart", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
Update model card
Browse files
README.md
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
---
|
| 2 |
-
license:
|
| 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
|
| 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("
|
| 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 |
-
|
| 67 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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.
|