This extension enables visualization of cross-attention heatmaps within Stable Diffusion models, showing exactly which parts of the image correspond to specific words in the prompt — good for analyzing and debugging model outputs and LoRA training.

👉 Example workflows are available in workflows.

This project was adapted from the SD Web UI implementation. Special thanks to @kousw for the original work!

✨ Features

✅ Positive / Negative prompt heatmap visualization
✅ SDXL, SD1.5, SD3 support
✅ Flux Dev support (Beta)

🚀 Installation

Now Available on Comfy Registry and Custom Node Manager!

Manual Install

Clone this repo into your ComfyUI custom_nodes directory:

git clone https://github.com/nisaruj/comfyui-daam.git

Then install the required packages

cd comfyui-daam
python3 -s -m pip install -r requirements.txt

Restart ComfyUI.

🧩 DAAM Nodes

`CLIPTextEncodeWithTokens`

Identical to CLIPTextEncode but also outputs the tokenized prompt required for the analysis.

`KSamplerDAAM`

A hooked version of KSampler. During sampling, it records attention maps for later analysis.

Outputs:

latent — standard latent output
pos_heatmaps — positive prompt's raw heatmaps for input into the analyzer
neg_heatmaps — negative prompt's raw heatmaps for input into the analyzer

`DAAMAnalyzer`

This node generates overlay heatmaps that show which parts of the image correspond to selected words in the prompt.

Inputs:

clip — CLIP model used to encode the attention text
tokens — from CLIPTextEncodeWithTokens
heatmaps — from KSamplerDAAM
images — the output images to overlay the heatmaps
A text box for comma-separated words to generate heatmaps

Output:

A batch of images with word-level heatmaps overlaid

📷 Example Output

Prompt: A photo of corgi with a cowboy hat riding a skateboard in the park

Attention words: corgi,skateboard,hat,park

📦 Changelog

0.4.0
- Flux and SD3 initial support
- Code Refactor and Minor bug fixes
0.3.0
- Negative prompt support
- Code Refactor and Minor bug fixes
0.2.0
- Added support for batched inputs
- SD 1.5 models compatibility
- Bug fixes and stability improvements
0.1.1
- Initial Version with SDXL support