Instructions to use microsoft/mri-autoencoder-v0.1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use microsoft/mri-autoencoder-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("microsoft/mri-autoencoder-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
Finetuning
#2
by SuWenxin - opened
Hi, thanks for your great work.
How to finetuning this autoencoder model?
Thanks in advance.
Thanks! I think the easiest way to finetune would be to use the diffusers library. The notebook gives an example of how to load the weights for inference. For finetuning you will have to write your own training module. Depending on interest, we will look into open sourcing the training code at some point.
i'm pretty interested in the training code-base.
Hey, i would also be interested in the training process. Could you please share the code-basis to me?
I‘m currently doing my research in MRI-Reconstruction and therefore your work is very interesting for me:)