diff --git a/README.md b/README.md
index 398e5b7..47a15f3 100644
--- a/README.md
+++ b/README.md
@@ -10,6 +10,8 @@
 
 Visit us on [PitchHut](https://www.pitchhut.com/project/reverse-synthid-engineering)
 
+> This fork adds a drag and drop desktop app for the V3 bypass, no command line needed after setup. See [gui/README.md](gui/README.md) for setup and usage.
+
 <p align="center">
   <img src="https://img.shields.io/badge/Python-3.10+-blue?style=flat-square&logo=python" alt="Python">
   <img src="https://img.shields.io/badge/License-Research-green?style=flat-square" alt="License">
diff --git a/gui/README.md b/gui/README.md
index 998410c..e9022d3 100644
--- a/gui/README.md
+++ b/gui/README.md
@@ -1,23 +1,17 @@
 # SynthID Cleaner (GUI)
 
-A small drag-and-drop desktop app around this repo's V3 spectral bypass
-(`src/extraction/synthid_bypass.py`). Useful for e.g. removing the SynthID
-watermark left behind after using generative AI to restore old photographs.
+A drag and drop desktop app built on this repo's V3 spectral bypass
+(`src/extraction/synthid_bypass.py`). Made for removing the SynthID
+watermark left over after using generative AI to restore old photographs,
+though it works on any Gemini generated image.
 
-- Drop images in, get cleaned copies out — no command line needed after setup.
-- Runs `RobustSynthIDExtractor` on each image first. The spectral bypass only
-  runs if a watermark is actually detected; otherwise the image is passed
-  through untouched. (Blindly subtracting the codebook's carrier pattern from
-  an image that never had it would imprint a watermark-shaped artifact
-  instead of removing one — this is why detection gates the bypass.)
-- Optionally strips all EXIF/XMP/IPTC metadata from the output (including any
-  AI-generation provenance tags such as C2PA content credentials or IPTC
-  `DigitalSourceType`), by rebuilding the file from raw pixel data.
-- Runs fully offline. No network calls, no telemetry.
-- Uses V3 (pure signal processing — numpy/scipy/opencv/PyWavelets/
-  scikit-learn only, no PyTorch required, no GPU needed).
+## Setup (one time only)
 
-## Setup
+Double click `Launch SynthID Cleaner.command`. On first run it creates a
+virtual environment and installs everything it needs automatically. This
+takes a minute or two depending on your connection.
+
+If you would rather do it by hand from the terminal:
 
 ```bash
 cd gui
@@ -26,22 +20,41 @@ source venv/bin/activate
 pip install -r requirements-gui.txt
 ```
 
-## Run
+## Using it
 
-Double-click `Launch SynthID Cleaner.command`, or from the terminal:
+1. Double click `Launch SynthID Cleaner.command`. A small window opens.
+2. Drag your images into the box, or click the box to pick files from a
+   dialog instead.
+3. Pick a strength from the dropdown: gentle, moderate, aggressive, or
+   maximum. Aggressive is the default and works well for most photos.
+4. Leave "Strip EXIF/XMP/IPTC metadata" checked if you also want camera and
+   software tags, plus any AI provenance metadata, removed from the output
+   files.
+5. Set the output folder in the "Save to" field. It defaults to a
+   synthid-cleaned folder on your Desktop.
+6. Watch the status line at the bottom while it works. For each image it
+   reports whether a watermark was found and removed, or whether the image
+   was already clean and left untouched.
 
-```bash
-cd gui
-source venv/bin/activate
-python gui.py
-```
+Each output file keeps the original name with `_clean` added, so
+`photo.png` becomes `photo_clean.png` in the output folder.
 
-The first double-click sets up the venv automatically if it doesn't exist yet.
+## What it actually does
+
+Every image is checked first with this repo's `RobustSynthIDExtractor`.
+Only images where a watermark is actually detected go through the spectral
+bypass. Images with no detectable watermark are copied through unchanged
+instead, so the tool cannot accidentally stamp a watermark shaped pattern
+onto a photo that never had one.
+
+Everything runs locally: no network calls, no telemetry. It uses the V3
+pipeline only (numpy, scipy, opencv, PyWavelets, scikit-learn), so no
+PyTorch install or GPU is required.
 
 ## Notes
 
-- Reads the bypass codebook from `../artifacts/spectral_codebook_v3.npz` and
-  the detector codebook from `../artifacts/codebook/robust_codebook.pkl`
-  (both already in this repo) — no extra downloads.
-- Subject to this repo's [LICENSE](../LICENSE): non-commercial use, with
+- Codebooks are read straight from this repo: `../artifacts/spectral_codebook_v3.npz`
+  for the bypass, `../artifacts/codebook/robust_codebook.pkl` for detection.
+  Nothing extra to download.
+- Subject to this repo's [LICENSE](../LICENSE): non commercial use, with
   required attribution to the original author.