Download
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
License
MIT LicenseFollow Diffusers-Interpret
Other Useful Business Software
Build Securely on AWS with Proven Frameworks
Moving to the cloud brings new challenges. How can you manage a larger attack surface while ensuring great network performance? Turn to Fortinet’s Tested Reference Architectures, blueprints for designing and securing cloud environments built by cybersecurity experts. Learn more and explore use cases in this white paper.
Rate This Project
Login To Rate This Project
User Reviews
Be the first to post a review of Diffusers-Interpret!
