nodes/cvlases-creative-code-comfyui
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

fixing docs

Browse Source
This commit is contained in:
Claire Vlases
2026-02-25 13:06:25 -05:00
parent 01852afc77
commit 4683dca307
2 changed files with 5 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files
artwork_assets/strreet1.png → artwork_assets/street1.png
View File
Side by Side Swipe Overlay

Before

Width:  |  Height:  |  Size: 96 KiB

After

Width:  |  Height:  |  Size: 96 KiB

documentation/saliency_tool_documentation.md
+5 -5
View File
@@ -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)
---