Instructions to use Mitsua/mitsua-diffusion-cc0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Mitsua/mitsua-diffusion-cc0 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-cc0", 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
How to upscale.
#8
by ShamelesslyAI - opened
Hello. Is there any public domain model/tool/method for upscaling Mitsua images? don't want to use the SD Upscalers as it would defeat the purpose of mitsua (Assuming these would even be compatible, I have not setup an upscaler pipeline before so I have no idea).
Thanks!
Unfortunately, maybe there is no easy-to-use CC0 trained SD upscaler so far.
There is one CC0 trained upscaler here, but we've not tested yet.
https://github.com/alfredplpl/HAT-CC-0
Thank you very much! I'll give it a look