Instructions to use Pixel-Dust/CC0_rebild_attempt with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Pixel-Dust/CC0_rebild_attempt with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("Pixel-Dust/CC0_rebild_attempt", 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
- Local Apps
- Draw Things
- DiffusionBee
Contributions
Good evening! I love the idea of your repository. I think having a model that can generate images that are safe to use in creative workflows without the risk of violation of IP law is crucial.
I have a computer with a GPU that I don't use very frequently, so I could use it to help train or source images. Is there any way I can help contribute to this project?
Thanks again for all your hard work on this!
I got a 3090 and two 3060, it's taking 400 hour to train, but this it not even close to the a100 used by other researchers, all the images I used where mostly manually chosen or captioned, by quality over quantity, I been need help in this field classification of the datatset, it will be released soon
Sup the microsmos dataset is gradually been uploaded if u wanna check