v0.5.0

• Add token attributions visualization; kudos to @TomPham97 👏

output.token_attributions.plot(normalize=True)

• output.token_attributions is now a list TokenAttributions object and output.pixel_attributions is now a np.ndarray PixelAttributions object (both compatible with previous version)
• output.normalized_token_attributions and output.normalized_pixel_attributions now raise a DeprecationWarning (but both still work). Use output.token_attributions.normalized and output.pixel_attributions.normalized instead.

v0.4.0

• Full compatibility with StableDiffusionImg2ImgPipeline and StableDiffusionInpaintPipeline 🚀
• New GIF visualization for all the generated images during the diffusion process (kudos to @TomPham97 )
• Cleaner API, docstrings and usage documentation

v0.3.1

fix n_last_diffusion_steps_to_consider_for_attributions=0

v0.3.0

Full compatibility with diffusers v0.3.0

v0.2.4

• Fixes previous bugs from versions 0.2.2 and 0.2.3
• Add support for gradient checkpointing
• Add Google Colab notebook

v0.2.2

fix v0.2.0 missing html files and other minor changes (#3)

v0.2.1

Fix image slider not rendering correctly on v0.2.0

v0.2.0

This minor version update adds a new image slider visualization for the images generated during the diffusion process.

Kudos to @andrewizbatista ! 👏🎉🚀

v0.1.0

Added requirement.txt in MANIFEST.in

v0.0.1

First version