Is this image AI-generated? Use these 10 checks
Ten checks for reviewing a suspicious photo, with a worksheet to record what you find. They help you investigate a claim; none is a shortcut to proving that an image is real or AI-generated.
Maintained by DetectFake · Updated
Quick answer
You usually cannot tell from one visual clue or detector score alone. Check who first published the image, search for earlier versions, inspect the highest-quality original, and compare text, hands, lighting, reflections and texture. Then use an automated scan as supporting evidence and leave the image unverified when the signals conflict.
Save your evidence, not just a score
Write down the claim, where the file came from, earlier appearances, and any conflicting evidence before deciding whether to share it. This makes the review useful even when a detector is uncertain.
Open the free media verification checklistThe 10 checks
- 1
Zoom to 100% before judging anything
Keep the original file and view it at native resolution. Inspect regions one at a time. Enlarging a small thumbnail cannot recover missing detail, and an unusual-looking detail is not proof of AI generation.
- 2
Read any text in the frame
Check signage, labels and book spines for inconsistent letters or impossible words. These can be clues, but blur and compression can also damage text, and generated images can contain correctly rendered writing.
- 3
Count and follow the hands
Check finger count, joint direction, and whether fingers actually wrap the object they hold. Also check where limbs disappear behind bodies and reappear on the wrong side.
- 4
Test the lighting story
Compare highlights and shadows across nearby objects. An unexplained mismatch deserves a closer look, but multiple light sources, reflections and ordinary editing can also explain it.
- 5
Check reflections and transparency
Compare mirrors, windows, sunglasses and water with the surrounding scene. Consider the viewing angle, crop and reflective surface before calling a mismatch suspicious. Reflections alone do not establish how an image was made.
- 6
Look at texture and skin
Inspect skin, hair, fabric and repeated patterns. Unusual smoothness or repetition may warrant review, but beauty filters, denoising, makeup and lighting can produce similar appearances in real photos.
- 7
Hunt for a local edit seam
Compare the sharpness, grain and lighting around a suspected added object with its surroundings. A mismatch may suggest editing, but convincing edits may leave no obvious seam, and a whole-image detector can miss a small altered region.
- 8
Judge the background separately
Cover the subject and study the background alone. Melted architecture, repeating crowd faces, doors to nowhere and warped straight lines show up clearly once the subject is not drawing your eye.
- 9
Chase the provenance
Search for earlier uses and a higher-resolution original. Check the source account and compare the caption with independent reporting. Inspect original-file metadata and verified Content Credentials separately; missing metadata proves nothing, and a genuine photo can still have a misleading caption.
- 10
Run an automated forensic check
Use DetectFake to obtain an image-classification verdict and supporting signals. Record the reported model and any fallback notice. Treat the score as one screening signal, not a measured probability or proof; disagreement with other evidence calls for more investigation.
Tells that are no longer reliable
“It looks too perfect,” missing metadata, strange hands and garbled text are not decisive tests. Generated images may avoid these artifacts, while real photos may look unusual because of perspective, blur or processing. Source verification matters even when every visible detail looks plausible.
Three situations where context changes the answer
These are illustrative review scenarios, not measured detector results.
- A forwarded screenshot: ask for the original and search for earlier appearances. Compression and missing metadata do not establish AI generation.
- A portrait with smooth skin: compare it with the source and ask about filters or retouching. Smoothness by itself cannot distinguish a real portrait from a generated one.
- A real photo with a new caption: look for the original date and place. A correct camera-origin verdict would still not verify the new story.
How to search for an image’s source
- Choose a safe file to share. An external image search sends the image or its URL to another provider. Do not upload private documents or sensitive photos without permission; use public source links or non-sensitive text clues instead.
- Search the image. On Google, select Search by image and upload the file or paste a public image URL. Results may include similar images and pages using them. See Google’s image-search instructions.
- Open and compare source pages. Look for the same scene, not just a similar subject. Record the page URL, caption, credited creator and publication date. Trace reused images back toward an attributable source.
- Keep the conclusion narrow. An earlier match can challenge a claim that the image is new, but does not by itself establish camera origin. No match means the search did not find one—not that the image is original or AI-generated.
Worked example: a forwarded photo labelled “today’s flood”
This fictional example demonstrates a review process, not a DetectFake test or a real news event. Suppose you receive a small image of a flooded street. One detector flags AI and another does not. Neither result resolves the claim about its date or location.
- Separate two questions. Record “Was this image generated?” separately from “Does it show today’s flood in the claimed town?” A genuine image can have a false caption.
- Search for earlier appearances. Search the full image and a distinctive crop, such as a shop sign. Open matching pages and record their URLs, captions and publication dates. A search-result date alone is not proof of when the photo was taken.
- Check a match. If an older article shows the same scene, compare stable details such as buildings and road markings. Look for independent corroboration; a copied caption on several sites is not several independent sources.
- Preserve the file history. Ask the sender for the original and how they obtained it. Keep the received copy unchanged. Note missing metadata without treating it as evidence of AI generation.
- Write a bounded conclusion. If a verified earlier publication contains the same image, the “taken today” claim is contradicted. Whether the file was originally AI-generated may still be unresolved. If no match is found, the date is still unverified.
Example review note: “The same scene appears in an independently checked earlier source. The current caption is not supported. Image-generation origin has not been established.” Save the source links and unresolved questions in the verification worksheet.
What to do when AI detectors disagree
Do not average scores from different tools or treat the highest number as the answer: their scores may describe different things. Record each tool, model version, file version and result. Compare the original with the received copy if both are available, and look for source evidence that does not depend on a detector. Several tools may share similar blind spots, so majority agreement is not independent proof.
Stop short of an accusation when provenance remains unresolved. Explain what you checked, what the evidence supports and what is still unknown. See how to interpret detector accuracy and confidence.
Tools and further reading
- Google’s guide to image search explains how to find matching or similar images and the sites using them.
- Content Credentials explains provenance records; use its verification tool with the original file when available.
- DetectFake’s methodology describes local inference, server fallback, and limits on metadata and video analysis.
- Detector accuracy and confidence explains false positives and how to evaluate results.
FAQs
How can I verify the authenticity of a photo?
Start with the source and claim, search for earlier versions, obtain the highest-quality original, inspect provenance or metadata when available, and compare visible details with the scene's context. Use an AI image detector as one additional screening signal, not as proof of authenticity.
Is there a reliable way to know for certain?
Pixels or a detector score alone do not establish certainty. Combine documented provenance, source verification, visual inspection and any automated signals. Agreement can add context but does not eliminate error; unresolved contradictions mean the claim should remain unverified.
Do AI images always have missing metadata?
No. Authentic photos can lose metadata through sharing or conversion, and generated images can contain metadata or Content Credentials. Check what a verified record actually says about creation and edits. Its presence alone does not establish camera origin or the truth of a caption.
What about AI-edited real photos rather than fully generated ones?
A local edit can be missed when most of the image remains unchanged. Compare the suspected region with an original version if available, check its boundaries and lighting, and do not treat a detector’s original verdict as proof that no editing occurred.
Can a detector prove an image is fake in court?
No. Automated detection is a probabilistic triage tool that documents its reasoning. A formal legal dispute needs a qualified forensic examiner working from the original file and its chain of custody.
Not sure after checking manually?
Run the image through DetectFake and compare its signal list against what you found.
Open DetectFake