Skip to content

Each notebook contains an image editing method using diffusion models.

License

Notifications You must be signed in to change notification settings

tian-2024/Image-Edit-Diff

Repository files navigation

Image-Edit-Diff

Each notebook contains image editing methods using diffusion models.

notebook and method:

  • 00-img.ipynb: Preprocess images to get 512x512 images.
  • 01-ptp.ipynb: (2023 ICLR) Prompt-to-Prompt Image Editing with Cross-Attention Control
  • 02-nti.ipynb: (2023 CVPR) Null-text Inversion for Editing Real Images using Guided Diffusion Models
  • 03-dds.ipynb: (2023 ICCV) Delta Denoising Score
  • 04-fpe.ipynb: (2024 CVPR) Towards Understanding Cross and Self-Attention in Stable Diffusion for Text-Guided Image Editing

Reference Project

  1. Prompt-to-Prompt Image Editing with Cross-Attention Control
  2. Null-text Inversion for Editing Real Images using Guided Diffusion Models
  3. Delta Denoising Score
  4. Towards Understanding Cross and Self-Attention in Stable Diffusion for Text-Guided Image Editing

Plan to add more methods

  1. Paint by Example: Exemplar-based Image Editing with Diffusion Models
  2. Imagic: Text-Based Real Image Editing with Diffusion Models

About

Each notebook contains an image editing method using diffusion models.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published