diffusers-interpret is a model explainability tool built on top of Diffusers. Model explainability for Diffusers. Get explanations for your generated images. Install directly from PyPI. It is possible to visualize pixel attributions of the input image as a saliency map. diffusers-interpret also computes these token/pixel attributions for generating a particular part of the image. To analyze how a token in the input prompt influenced the generation, you can study the token attribution scores. You can also check all the images that the diffusion process generated at the end of each step. Gradient checkpointing also reduces GPU usage, but makes computations a bit slower.

Features

  • Visualize pixel attributions of the input image as a saliency map
  • Gradient checkpointing reduces GPU usage
  • You can check all the images that the diffusion process generated at the end of each step
  • Analyze how a token in the input prompt influenced the generation
  • Computes token/pixel attributions for generating a particular part of the image
  • output will have all the properties that were presented for StableDiffusionPipeline

Project Samples

Diffusers-Interpret Screenshot 1

Project Activity

See All Activity >

Categories

AI Image Generators, Generative AI

License

MIT License

Follow Diffusers-Interpret

Diffusers-Interpret Web Site

Other Useful Business Software
$300 in Free Credit Towards Top Cloud Services Icon
$300 in Free Credit Towards Top Cloud Services

Build VMs, containers, AI, databases, storage—all in one place.

Start your project in minutes. After credits run out, 20+ products include free monthly usage. Only pay when you're ready to scale.
Get Started
Rate This Project
Login To Rate This Project

User Reviews

Be the first to post a review of Diffusers-Interpret!

Additional Project Details

Registered

2023-03-22
Report inappropriate content