Edit model card

Text-To-Sinogram

is an app for generation of sinogram with stable diffusion.

This repository contains the model files, including:

  • a diffusers formated library
  • a compiled checkpoint file
  • a traced unet for improved inference speed

Model V1

It is a latent text-to-image diffusion model capable of generating sinogram images given any text input. These sinograms can be reconstructed back to the original image.

The model was created by Ashraf Al-Aodat as a proof of concept.

You can use the model directly.

The model was created by fine-tuning the Stable-Diffusion-v1-5 checkpoint. Read about Stable Diffusion here 🤗's Stable Diffusion blog.

Model Output

Examples of some generated sinograms using the prompt bat..

sinograms

After image reconstruction..

reconstructions

Model Details

Direct Use

The model is intended for research purposes only. Possible research areas and tasks include

  • Generation of artworks, and use in creative processes.
  • Applications in educational or creative tools.
  • Research on generative models.

Datasets

The modeal was trained on the sinograms dataset.

Fine Tuning

Check out the diffusers training examples from Hugging Face. Fine tuning requires a dataset of sinogram images of objects, with associated text describing them. Note that the CLIP encoder is able to understand and connect many words even if they never appear in the dataset. It is also possible to use a dreambooth method to get custom styles.

Citation

If you build on this work, please cite it as follows:

@article{TODO,
  author = {Al-Aodat, Ashraf*},
  title = {{Text-To-Sinogram - Stable diffusion for sinogram generation a proof of concept}},
  year = {2022}
}
Downloads last month
12