From 4683dca307762c4b827a7dae691dbfc47ea4d054 Mon Sep 17 00:00:00 2001 From: Claire Vlases Date: Wed, 25 Feb 2026 13:06:25 -0500 Subject: [PATCH] fixing docs --- artwork_assets/{strreet1.png => street1.png} | Bin documentation/saliency_tool_documentation.md | 10 +++++----- 2 files changed, 5 insertions(+), 5 deletions(-) rename artwork_assets/{strreet1.png => street1.png} (100%) diff --git a/artwork_assets/strreet1.png b/artwork_assets/street1.png similarity index 100% rename from artwork_assets/strreet1.png rename to artwork_assets/street1.png diff --git a/documentation/saliency_tool_documentation.md b/documentation/saliency_tool_documentation.md index 7617561..761bf12 100644 --- a/documentation/saliency_tool_documentation.md +++ b/documentation/saliency_tool_documentation.md @@ -1,16 +1,16 @@ # Algorithmic Attention (XAI) Tool Documentation -![flower](model_demo/flower-three.png) +![flower](../artwork_assets/flower-three.png) My tool uses pretrained image classifiers using gradient-based saliency methods from Google's [PAIR saliency library](https://github.com/PAIR-code/saliency), exposing the hidden attentional logic of neural networks as visual artifacts. Built as a custom ComfyUI node set. The core question it answers: *when a model classifies an image, which pixels drove that decision?* (and, how can we make art with *algorithmic attention*. -![street1](model_demo/street1.png) -![street2](model_demo/street2.png) -![street3](model_demo/street3.png) +![street1](../artwork_assets/street1.png) +![street2](../artwork_assets/street2.png) +![street3](../artwork_assets/street3.png) --- @@ -275,7 +275,7 @@ Photoshop-style screen blend. Attention brightens salient regions. Outputs three panels side by side: original image | saliency map alone | composite. Shows the full chain of the visualization in one frame. -![triptych](composition_demo/triplych.png) +![triptych](composition_demo/triptych.png) ---