Instructions to use Mitsua/mitsua-diffusion-one with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Mitsua/mitsua-diffusion-one with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("Mitsua/mitsua-diffusion-one", 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
Other free sources
Hi,
at first, thanks for your work. It is amzing to have a save legal, safe model to use. THANKS.
i'm from germany and i'd like do helb. With gpu power and content to imporve this model.
i found here other good cc0 sources:
1millionfreepictures.com
https://newoldstock.gumroad.com/
https://pickupimage.com/
https://gratisography.com/photo/happy-dog-portrait/
https://www.flickr.com/photos/britishlibrary/
https://www.splitshire.com/developer-79-free-stock-photos/
i will also provid my own content , put it don't like use twitter. Is it possible to send you a link to my nextcloud ?
How can i help you, to push this project internationerly. Currently it seems only a japenise local projekt.
And a other one 2.3 Million cc0 images ..
http://library.lowframerate.games/
Here is other page..
https://pxhere.com/de/license (cc0)
and here
https://www.pexels.com/de-de/@public-domain-pictures/
read also this ..
https://de.wikipedia.org/wiki/Wikipedia:Public-Domain-Bilderquellen
hobe dis will help you , to improve this model
Hello, I am one of the Mitsua contributors. There's a discord where you can upload files, images, links to a file uploader, so you can do it from there.
Fill in the discord username in the google form for Mitsua contributor and they will send you an invitation as long as you meet the criteria.