Text-to-Image
Diffusers
Safetensors
StableDiffusionPipeline
stable-diffusion
stable-diffusion-diffusers
pip install -U diffusers transformers accelerate
import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("yurman/mri-sd-v21-oasis", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]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:
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.
- Downloads last month
- -
# Gated model: Login with a HF token with gated access permission hf auth login