SEO-optimized README, add sample images from multiple AI models

- Rewrite README for SEO: Nano Banana, SynthID, Made with AI, C2PA keywords
- Add Supported Models table with 7 AI services
- Add 'Made with AI' label removal to features
- Rename sections for search discoverability
- Add samples: ChatGPT/DALL-E, Midjourney, Adobe Firefly
- Reorganize data/samples with flat structure and clear naming

README.md

@@ -1,29 +1,45 @@
 # Remove-AI-Watermarks
 
-Unified tool for removing **visible** and **invisible** AI watermarks from images.
+Remove **visible** and **invisible** AI watermarks from images generated by Google Gemini (Nano Banana), ChatGPT / DALL-E, Stable Diffusion, Adobe Firefly, Midjourney, and other AI models.
+
+Strips SynthID, C2PA Content Credentials, EXIF/XMP "Made with AI" labels, and visible sparkle overlays — all in one command.
 
 ## Features
 
-- **Visible watermark removal** — Gemini sparkle logo via reverse alpha blending (fast, offline, deterministic)
+- **Visible watermark removal** — Gemini / Nano Banana sparkle logo via reverse alpha blending (fast, offline, deterministic)
 - **Invisible watermark removal** — SynthID, StableSignature, TreeRing via diffusion-based regeneration
-- **AI metadata stripping** — EXIF, PNG text chunks, C2PA provenance manifests
-- **Analog Humanizer** — film grain and chromatic aberration injection to bypass AI image classifiers
+- **AI metadata stripping** — EXIF, PNG text chunks, C2PA provenance manifests, XMP DigitalSourceType
+- **"Made with AI" label removal** — removes the metadata that triggers AI labels on Instagram, Facebook, X (Twitter)
+- **Analog Humanizer** — film grain and chromatic aberration to bypass AI image classifiers
 - **Smart Face Protection** — automatic extraction and blending of human faces to prevent AI distortion
-- **High-Res Upscaler** — prevents resolution degradation during invisible watermark removal
 - **Batch processing** — process entire directories
 - **Detection** — three-stage NCC watermark detection with confidence scoring
 
+## Supported models
+
+| AI model | Visible watermark | Invisible watermark | Metadata | Our approach |
+| --- | --- | --- | --- | --- |
+| **Google Gemini / Nano Banana** | ✅ Sparkle logo | ✅ SynthID | ✅ C2PA + EXIF | Alpha reversal + diffusion + metadata strip |
+| **OpenAI DALL-E 3 / ChatGPT** | — | — | ✅ C2PA manifest | Metadata strip |
+| **Stable Diffusion (AUTOMATIC1111, ComfyUI)** | — | ✅ DWT / steganographic | ✅ PNG text chunks | Diffusion regeneration + metadata strip |
+| **Adobe Firefly** | — | — | ✅ Content Credentials (C2PA) | Metadata strip |
+| **Midjourney** | — | — | ✅ EXIF + XMP (prompt, model, seed) | Metadata strip |
+| **StableSignature** (Meta) | — | ✅ In-model watermark | — | Diffusion regeneration |
+| **TreeRing** | — | ✅ Latent space watermark | — | Diffusion regeneration |
+
+> Visible watermarks (logo overlays) are currently used only by Google Gemini / Nano Banana. Other services rely on invisible watermarks and/or metadata. Our diffusion-based regeneration works against any invisible watermark in pixel or frequency domain.
+
 ## How it works
 
-### 1. Visible watermark removal
+### Removing the Gemini / Nano Banana sparkle watermark
 
-Gemini embeds a sparkle logo using alpha blending:
+Google Gemini (internally codenamed **Nano Banana**) adds a visible sparkle logo to generated images using alpha blending:
 
 ```text
 watermarked = α × logo + (1 − α) × original
 ```
 
-We reverse this with a known alpha map (extracted from Gemini on a pure-black background):
+We reverse this with a known alpha map (extracted from Gemini / Nano Banana output on a pure-black background):
 
 ```text
 original = (watermarked − α × logo) / (1 − α)
@@ -33,9 +49,9 @@ A three-stage NCC (Normalized Cross-Correlation) detector finds the watermark po
 
 **Speed**: ~0.05s per image. No GPU needed.
 
-### 2. Invisible watermark removal
+### Removing SynthID and other invisible watermarks
 
-AI services (Google SynthID, StableSignature, TreeRing) embed imperceptible patterns in the frequency domain. These survive cropping, resizing, and JPEG compression.
+Google embeds **SynthID** into every image generated by Gemini / Nano Banana. Other AI services use StableSignature, TreeRing, and similar schemes. These imperceptible frequency-domain patterns survive cropping, resizing, and JPEG compression.
 
 The removal pipeline:
 
@@ -52,13 +68,14 @@ The key insight: even minimal noise injection (strength 0.02 = 2% perturbation)
 
 **Analog Humanizer**: optional film grain and chromatic aberration injection that makes the output indistinguishable from a photo of a screen, defeating AI-generated image classifiers.
 
-### 3. AI metadata stripping
+### Stripping C2PA, EXIF, and "Made with AI" metadata
 
-AI tools embed generation metadata in multiple layers:
+AI tools embed generation metadata that social platforms use to show "Made with AI" labels:
 
-- **EXIF tags** — prompt, seed, model hash, sampler settings
-- **PNG text chunks** — ComfyUI workflows, Stable Diffusion parameters
-- **C2PA manifests** — Google Imagen, OpenAI DALL-E, Adobe Firefly provenance
+- **EXIF tags** — prompt, seed, model hash, sampler settings (Stable Diffusion, Midjourney)
+- **XMP DigitalSourceType** — `trainedAlgorithmicMedia` tag used by Instagram, Facebook, and X (Twitter) to show "Made with AI"
+- **PNG text chunks** — ComfyUI workflows, AUTOMATIC1111 parameters
+- **C2PA Content Credentials** — cryptographic provenance manifests from Google Imagen, OpenAI DALL-E, Adobe Firefly
 
 The cleaner parses each layer, removes AI-related fields, and preserves standard metadata (Author, Copyright, Title).
 
@@ -153,13 +170,13 @@ remove-ai-watermarks batch ./images/ --mode all
 #### Individual commands
 
 ```bash
-# Visible watermark only (Gemini sparkle) — fast, offline
+# Visible watermark only (Gemini / Nano Banana sparkle) — fast, offline
 remove-ai-watermarks visible image.png -o clean.png
 
 # Invisible watermark only (SynthID etc.) — requires GPU
 remove-ai-watermarks invisible image.png -o clean.png --humanize 4.0
 
-# Check / strip AI metadata only
+# Check / strip AI metadata (C2PA, EXIF, "Made with AI" labels)
 remove-ai-watermarks metadata image.png --check
 remove-ai-watermarks metadata image.png --remove
 

pyproject.toml

@@ -1,7 +1,7 @@
 [project]
 name = "remove-ai-watermarks"
 version = "0.2.2"
-description = "Unified tool for removing visible and invisible AI watermarks from images"
+description = "Remove visible and invisible AI watermarks from images (Gemini / Nano Banana, ChatGPT, Stable Diffusion)"
 readme = "README.md"
 requires-python = ">=3.10"
 license = {text = "MIT"}