What image types are supported?
We aim to support all types of images. We currently support all the common image formats: JPEG, JPEG 2000, GIF, PNG, WEBP, BMP, TIFF.
Please note that animated GIF images will be treated as videos, meaning that each frame will be processed. For more details, see how we process animated GIF images.
If you are submitting PNG images with an alpha channel, please note that most of our models will drop the alpha channel so that any offending content is found, even if the transparency is high and makes it hard to "see".
As a rule of thumb, if you can choose between different image formats it is usually faster to submit natural images in WEBP, JPEG or JPEG 2000 format. Most of the time this will save you bandwidth and transfer time.
If you need to process some other format that is not yet supported, please send us a message.
Other frequent questions
- What is a model?
- What are the ways to send an image to the API?
- What are the acceptable / recommended image dimensions?
- How do you process GIF images with multiple frames (animated GIFs)?
- Do you use image metadata to moderate images?
- Is it possible to perform bulk image moderation / to submit images in batch? How many images can be submitted at once?
- Can you detect duplicate images, or image spam?
- Is it possible to customize the Image Moderation API to my needs?
- Can you improve the moderation results based on my reports of incorrectly classified or mislabeled images?