Overview
Who is this API for?
Fashion & Apparel



Food Delivery





How do I call the Visual QA API?
Last updated
Was this helpful?
The Visual QA API lets you automatically compare an edited image with the original one, to ensure product fidelity.
More specifically, this API outputs a score that tells you how much the product in the edited image is true to the one in the original image.
This is particularly useful when using editing features powered by generative AI, because these features can create hallucinations on the product.
Here are some examples of how the Visual QA API can be used depending on the industry:
Garments contain a lot of fine details that the best AI editing models will sometimes get wrong.
The Visual QA API allows you to work around this problem:
instead of a generating a single edited image, generate three of them
use the Visual QA API to measure the amount of product fidelity in each
select the edited image with the highest fidelity score
Here are some examples of this approach:



Pictures of dishes taken by restaurant owners can be of varying quality and AI editing is a great way to improve their quality.
However, it's important to ensure that the content of the dish stays the same and that no ingredient has been added or removed.
The Visual QA API solves this problem.
It analyzes the edited image and validates it when the dish hasn't been altered:


And it flags the edited image when the dish has been altered in a way that would mislead buyers:


When an edited image is flagged, you can then retry the generation and re-evaluate the new output:

If after 2 retries the image still doesn't pass validation, it's then safe to assume that the input image is likely too low quality to be meaningfully improved.
The Visual QA API is only available for Enterprise plans.
If you're interested to use the Visual API, please contact our team to book a demo.
Last updated
Was this helpful?
Was this helpful?