Hugging Face's logo

Stomper10
/
CXR_unet_profile2

Text-to-Image
Diffusers
Safetensors
StableDiffusionPipeline
stable-diffusion
stable-diffusion-diffusers
Inference Endpoints
Model card Files Community
CXR_unet_profile2 / README.md
Stomper10's picture
Stomper10
End of training
bc0f4f5
preview code
|
raw
history blame
No virus
1.25 kB
metadata
license: creativeml-openrail-m
base_model: /shared/s1/lab06/wonyoung/diffusers/CXR_ti_nf
datasets:
  - None
tags:
  - stable-diffusion
  - stable-diffusion-diffusers
  - text-to-image
  - diffusers
inference: true

Text-to-image finetuning - Stomper10/CXR_unet_profile2

This pipeline was finetuned from /shared/s1/lab06/wonyoung/diffusers/CXR_ti_nf on the None dataset. Below are some example images generated with the finetuned pipeline using the following prompts: ['A photo of a lung-xray.']:

val_imgs_grid

Pipeline usage

You can use the pipeline like so:

from diffusers import DiffusionPipeline
import torch

pipeline = DiffusionPipeline.from_pretrained("Stomper10/CXR_unet_profile2", torch_dtype=torch.float16)
prompt = "A photo of a lung-xray."
image = pipeline(prompt).images[0]
image.save("my_image.png")

Training info

These are the key hyperparameters used during training:

  • Epochs: 1
  • Learning rate: 0.00128
  • Batch size: 32
  • Gradient accumulation steps: 1
  • Image resolution: 512
  • Mixed-precision: fp16

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