Instructions to use 22h/vintedois-diffusion-v0-1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use 22h/vintedois-diffusion-v0-1 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("22h/vintedois-diffusion-v0-1", 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 Settings
- Draw Things
- DiffusionBee
Training details?
#4
by bryandlee - opened
Hi, thanks for the amazing model.
I was wondering if you can share the details of the training such as dataset or training source code?
Thanks!
We are working on this. I hope we have something in the next week!
@pedrogengo Any news here? I'm also very curious as not a lot of users share these details. The "open weights and configs" part really got me in the model card :)
To clarify, I'm curious about the hyperparameters chosen for training, the size of the data, what kind of class images used. Thank you!
Hi, I am also interested on how this was trained? Would you have time to help me setup a training setup?
bryandlee changed discussion status to closed