Hugging Face's logo

yurman
/
mri-sd-v21-oasis

Text-to-Image
Diffusers
Safetensors
StableDiffusionPipeline
stable-diffusion
stable-diffusion-diffusers
Inference Endpoints
Model card Files Community
mri-sd-v21-oasis / README.md
yurman's picture
yurman
End of training
70adb65 verified
preview code
|
raw
history blame contribute delete
1.41 kB
metadata
license: creativeml-openrail-m
base_model: stabilityai/stable-diffusion-2-1
datasets:
  - OASIS-3
tags:
  - stable-diffusion
  - stable-diffusion-diffusers
  - text-to-image
  - diffusers
inference: true

Text-to-image finetuning - yurman/mri-sd-v21-oasis

This pipeline was finetuned from stabilityai/stable-diffusion-2-1 on the OASIS-3 dataset for brain image generation. Below are some example images generated with the finetuned pipeline:

val_imgs_grid

Pipeline usage

You can use the pipeline like so:

from diffusers import DiffusionPipeline
import torch

pipeline = DiffusionPipeline.from_pretrained("yurman/mri-sd-v21-oasis", torch_dtype=torch.float16)
prompt = "An empty, flat black image with a MRI brain axial scan in the center"
image = pipeline(prompt).images[0]
image.save("my_image.png")

Training info

These are the key hyperparameters used during training:

  • Epochs: 25
  • Learning rate: 5e-05
  • embeds rate: 5e-05
  • Batch size: 4
  • Classifier free guidance: 1
  • VAE scaling: Same as in the original model
  • Input perturbation: 0.0
  • Noise offset: 0
  • Gradient accumulation steps: 4
  • Image resolution: 384
  • Mixed-precision: None
  • Max rotation degree: 0.0

More information on all the CLI arguments and the environment are available on your wandb run page.