Dimensions and bytes
Exact file properties. A short side below 256 pixels triggers review; the current per-image upload ceiling is 30 MB.
Free private input checker
Compare face swap source and target images before upload
Measure two images on this device, review narrow whole-image differences, and complete the face-specific checks the browser cannot automate. Neither selected file leaves this tab.
Source-target preflight
Compare two photos without uploading either one
Start with the source identity image. Add the target scene to expose broad technical differences that deserve visual review. Measurements describe complete images, not detected faces.
No upload: the analyzer contains no file-transfer request. Normal page telemetry does not receive file names, image bytes, pixels, measurements, checklist answers, or exported reports.
Step 1 · required
Source identity image
Choose the image that supplies the visible facial identity.
No source selected
JPEG, PNG, WebP, or AVIF when this browser can decode it.
Step 2 · recommended
Target scene image
Choose the scene, pose, expression, hair, clothing, and background reference.
No target selected
Add a target to compare whole-image measurements.
Technical measurements
Read each image before comparing the pair
Choose a source image to begin local measurement.
Source measurements
Target measurements
Whole-image comparison
Differences to inspect, not a compatibility score
These gaps cover complete decoded images. They cannot determine whether the two faces share a compatible pose, expression, light direction, or identity.
No quality score: flags are conservative review prompts, not a model score or output prediction. A clean report cannot establish identity similarity, consent, pose compatibility, or generated realism.
Measurement map
Five image signals plus a narrow pair comparison
Mean luminance
Average Rec. 709 luma. It can flag a globally dark or bright input but cannot tell whether a face is correctly exposed.
Contrast spread
Population standard deviation of luminance. A low value can indicate a flat input, but a high value is not proof of useful facial detail.
Clipping share
Percentage of sampled pixels near black or white. It identifies compressed tonal range without locating the affected facial features.
Adjacent-edge difference
Mean local luminance change. It responds to blur but also to texture, noise, resizing, and scene content.
Pair differences
Absolute gaps and an edge-detail ratio reveal broad mismatches worth inspecting. They are not face-level compatibility measurements.
Human inspection
Still required for the actual face, pose, expression, hair, hands, glasses, occlusion, permission, and intended audience.
Evidence and limits
See the controlled benchmark behind the analyzer
The published benchmark applies the same formulas to six controlled variants of one owned source. It includes the exact transformations, sample files, JSON, CSV, and SHA-256 hashes. The compressed sample also demonstrates why aggregate metrics must not be presented as a universal pass/fail score.
Checker questions
What the tool does and does not do
Does this upload either image?
No. Decoding, resizing, comparison, checklist state, and report creation happen inside this browser tab.
Does no warning guarantee a strong output?
No. The checker does not inspect the generation model or predict an output.
Does it detect a face?
No. It measures the complete decoded image and does not detect identity, landmarks, pose, expression, or consent.
What does the source-target comparison mean?
It shows differences between whole-image brightness, contrast, clipping, dimensions, and edge-detail measurements. It does not judge face compatibility.
Why should I still run a small test?
Only a representative generation can show how the selected inputs interact with the current workflow.
Use one representative image before scaling the task
After reviewing the input, open the photo workflow and test the smallest meaningful case first.