C2PA Content Credentials
Reads embedded content credentials and manifest data.
- Upload an image to start automatic analysis.
Meaning for the AI verdict
Waiting for analysis SynthID checker
SynthID Checker
Review C2PA and pixel-based AI signals here, then use Gemini’s official verification flow for Google SynthID.
SynthID
Verify officially in Gemini
C2PA
Signed provenance
Pixel model
AI probability is not a watermark
Drop an image here
JPG, PNG, WebP, or AVIF up to 10 MB
Image preview appears after upload
No file selected
JPG, PNG, WebP, or AVIF up to 10 MB
This page does not claim to verify SynthID automatically. Analysis starts after upload and sends a privacy-reduced copy to Hive only when trusted AI provenance is not already confirmed.
Analyzing image
Preparing a privacy-reduced analysis copy…
0% Automatic analysis
AI likelihood and all signal details appear when analysis is complete.
AI likelihood report
Waiting for image upload
Upload an image to start automatic analysis.
Waiting Probability this image is AI-generated
—
Waiting for analysis
Upload an image to calculate a probability
Deepfake probability
—
Deepfake is a separate face-manipulation signal; it does not by itself mean the whole image is AI-generated.
Google SynthID verification is available through Gemini’s official signed-in verification flow. A general AI probability is not a SynthID result.
How to read the result
0%–30% No strong AI signal; real photos and ordinary screenshots often fall here.
31%–89% Inconclusive; compression, redraws, AI edits, reposted screenshots, and mixed editing appear here more often.
90%–100% The pixel model found a strong AI signal.
100% Verified AI Not a Hive model probability; trusted signed provenance directly confirms the AI origin.
Signal breakdown
Trusted AI provenance
Confirms AI provenance only when a valid credential explicitly declares generative AI use.
- Automatic server analysis pending
Meaning for the AI verdict
Waiting for analysis Pixel-based AI classifier
Uses Hive pixel analysis to estimate the probability that the image is AI-generated.
- Automatic server analysis pending
Meaning for the AI verdict
Waiting for analysis Deepfake signal
Separately checks for face-swap or deepfake signals.
- Automatic server analysis pending
Meaning for the AI verdict
Waiting for analysis Basic metadata signals
Records format, size, dimensions, and cache hash evidence.
- Automatic server analysis pending
Meaning for the AI verdict
Informational only; not an AI classifier Verify SynthID in Google Gemini
EasyGlobe does not claim to detect Google’s private watermark through a general vision API. Upload the original file to Gemini and ask whether it was created or edited by Google AI.
What this SynthID review page checks
SynthID is a watermarking system for AI-generated media. This page is built around the specific search intent behind SynthID checker, SynthID detector, and Google AI watermark queries.
Last updated: July 10, 2026
SynthID signal
Links to Gemini, the official signed-in workflow that can verify supported Google AI invisible watermarks.
C2PA fallback
Reads Content Credentials locally first, because signed provenance can provide strong origin evidence.
No-signal context
Separates no SynthID found from not AI-generated, which is the most important interpretation gap.
What SynthID can and cannot detect
Google’s official SynthID verification is most useful when it finds a supported Google AI watermark. EasyGlobe’s pixel probability remains a separate general model result, not a SynthID result.
Can help identify
- Images or videos with supported SynthID watermark evidence.
- Files with C2PA Content Credentials that name Google, Gemini, Imagen, or another trusted AI source.
- Cases where a positive signal should be escalated for provenance review.
Cannot prove
- That an image is human-made when no SynthID signal is found.
- That unsupported AI generators, screenshots, or heavily recompressed files are clean.
- Whether the visual claim in an image is true, misleading, or edited after generation.
How to interpret SynthID results
Treat SynthID as a high-value provenance signal, not a universal AI detector. The result is strongest when the watermark or signed provenance is found, and limited when no supported signal is available.
Detected
A SynthID result detected by Google’s official verifier is strong evidence that supported Google AI provenance exists. It does not explain whether the image is accurate, misleading, or edited after generation.
Not found
No SynthID signal in Google’s official verifier means no supported Google AI watermark was found. The image may still be generated by another AI system or may have lost signals during editing or reposting.
Inconclusive
Simple images, tiny edits, screenshots, compression, or damaged files can make provenance review less clear. Keep these cases in a manual review workflow.
SynthID vs C2PA vs metadata
AI provenance is easier to understand when invisible watermarks, signed credentials, and ordinary file metadata are reported separately.
Signal
What it can show
Main limitation
SynthID
Whether supported AI watermark evidence is present.
Verification is performed by Google and currently focuses on supported Google AI content.
C2PA
Signed provenance, tool names, edit history, and AI-use declarations.
Metadata can be stripped, invalidated, or stored remotely by some tools.
Metadata
File type, dimensions, size, and sometimes camera or editor details.
Easy to remove or rewrite, so it is context rather than proof.
Related AI watermark tools
Use the broader EasyGlobe tools for C2PA, metadata, and pixel-model context. Use Gemini for the actual SynthID verification result.
Reference sources
These official references explain how SynthID, signed provenance, and provider verification tools should be interpreted.
Google DeepMind SynthID
Official overview of Google's invisible watermarking system for generated media.
Gemini SynthID Verification
Google help documentation for checking supported AI-generated images and videos with SynthID.
C2PA open standard
The provenance standard behind Content Credentials and signed media records.
OpenAI Verify
Example of a provider verification workflow for supported provenance signals.
SynthID checker FAQ
Practical interpretation details for Google AI watermark checks.
Google verifies SynthID inside the signed-in Gemini app. This page checks C2PA and a separate pixel-based AI probability, then links to Google’s official verification flow.
No. A negative result in Google’s official SynthID verification only rules out a supported Google AI watermark; the image could still come from another AI system.
Watermarks are designed to survive common edits, but screenshots, heavy recompression, cropping, format conversion, or repeated edits can still reduce detection confidence.
SynthID is an invisible watermark embedded into generated media. C2PA Content Credentials are signed provenance records that can describe origin, editing history, and whether AI tools were used.