Cross-check an image with multiple AI models, then ask real people on Mingyanshe.
Users
12
+1 in 30 days
Rating
5.0 / 5
unchanged in 30 days
Ratings
1
0 in 30 days
Store rank
#186K
#156K among extensions
Version
0.1.7
updated 25 Aug 2026
Users
monthly, 3 months
Latest, 21 Oct 2026:12 usersMove the mouse over the chart for any month
Ratings count
monthly, 3 months
Latest, 21 Oct 2026:1 ratingsMove the mouse over the chart for any month
The Chrome Web Store rounds user counts down to the leading digit, so the user line moves in steps. The ratings count is exact and is the better signal of real adoption.
About MingLens — AI Image Checker
Not sure about an image on the web? Right-click it and choose “Check this image with MingLens.” The side panel opens with the target image ready. You can also choose, paste, drop, or capture an image.
- Every stable installation receives the free allowance configured for that day, with the exact current quota shown in the panel. Connecting an account neither resets usage nor clears the remaining free checks; free quota is still used first. Network, account and service-wide abuse controls do not consume free checks.
- After the free quota, every check costs exactly 5 Light Points and requires its own explicit confirmation. The exact before-and-after balance is shown; there is no automatic charging.
- If MingLens cannot locate a right-clicked image, it falls back to a preview of the whole visible page with a clear warning. You must crop, confirm, and actively submit it.
- Local crop and compression, real upload progress, background polling, and badge completion status. A small local thumbnail of the exact submitted crop remains in recent history for recognition, while the complete image is still deleted after successful submission.
- The result view shows only the overall machine opinion, AI/compositing index, and aggregate explanation. The index is a weighted direction, not accuracy or authenticity probability. It does not expose model names, internal sensitivity policy, prompt versions, or forensic debug fields.
- Optional per-check complete-file forensics and Google reverse image search. MingLens does not collect or send the current page title, image alt text, nearby text, or page URL as model context.
- Extension checks remain private and are never published automatically. Community handoff starts only when you choose it and requires a new public-rights confirmation on the website.
Multiple models provide cross-checking signals, but machine analysis is only decision support. It is not proof and cannot guarantee a correct answer.