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
Advice for fine-tuning this?
#5
by wktra - opened
Do you have any advice on how to fine tune this using something like Kohya or one-trainer?
I would also like to know how you could train loras and stuff with this model. I tried to follow this old stable diffusion 2.1 kohya training video but it didn't work for Mitsua Diffusion One-base model.
https://www.youtube.com/watch?v=TpuDOsuKIBo