Great quality at a fraction of the price
And free while in Beta
Pick an image that you want to remove the background from and drag and drop it onto the page.
Our servers use powerful GPUs and multi-core CPUs to analyze your image and remove the background from it.
Inspect a preview of the result and download it if you like.
Downloads are free while in Beta.
We took a large sample of user-provided images and compared our output to the best known competing service's. Here are the results, and be sure to click on each title for an in-depth report:
Pixian.AI |
|
Competitor |
|
Pixian.AI |
|
Competitor |
|
Pixian.AI |
|
Competitor |
|
Pixian.AI |
|
Competitor |
|
Pixian.AI |
|
Competitor |
|
Based on reviewing outputs separately and assigning a binary good-or-bad score to each. While we have striven for fairness, results are subjective and in our opinion.
What matters more than the quality of our results in general, is the quality of our results on your images in particular. We therefore make the comparison tool available to you for free:
Ready to make the switch? Check out the API docs and the migration guide.
The service is free while in beta.
When we come out of beta we will offer long lasting Pay-As-You-Go-style credit packs, with no monthly fees or minimums, and no subscriptions. We intend to offer a free tier for low-volume users.
Cost-plus per-image pricing expected to be roughly:
0.25 MPx | ~ | $0.0010 |
1.00 MPx | ~ | $0.0016 |
4.00 MPx | ~ | $0.0039 |
12.00 MPx | ~ | $0.0100 |
25.00 MPx | ~ | $0.0200 |
Their margin is our opportunity.
We see AI commoditizing rapidly, and rather than fighting that tide we've decided to embrace it.
This thinking has impacted every aspect of our business. The size of our team, the choice of AI model, the architecture of our IT operations. We've optimized them all towards maximizing quality and minimizing price.
Our intention with this pricing model is to enable two broad use-cases. First, to bring background removal to graphics professionals and hobbyists at a 'makes sense' price. Second, to enable using background removal in ad-funded apps and websites.
Percentage of images processed within a given time.
While AI is rapidly transforming the way we as a society do business, AI itself is changing even faster. What was cutting edge only a few years ago is now rapidly becoming commoditized.
We choose to accept and accelerate this reality.
We therefore see ourselves less as a tech startup, and more as an outsourced MLOps extension to your engineering team. Our goal is to be more 'S3' and less 'Adobe' for state-of-the-art AI image processing.
Ready to make the switch? Check out the API docs and the migration guide.
Both James's and Jacob's respective childhood sports teams had the colors white and purple.
We currently support JPEG, PNG, BMP, GIF and WebP as input, and produce PNG as output. More output formats and options coming soon!
The max website image pixel size is 8 megapixels. The max API image pixel size is 25 megapixels. The max image file size is 30 megabytes.
The service is free while in beta.
We expect to come out of beta in Q2 or Q3 of 2023.
Their margin is our opportunity.
We see AI commoditizing rapidly, and rather than fighting that tide we've decided to embrace it.
This thinking has impacted every aspect of our business. The size of our team, the choice of AI model, the architecture of our IT operations. We've optimized them all towards maximizing quality and minimizing price.
So we don't have a 50 person sales team to wine and dine you (and at those margins they really should be!) All we're offering is a great service and outstanding value.
We see the API offering as the primary revenue driver for our and any background removal service going forward.
We will email the address you used to sign up for the API well in advance of starting to charge.
We work well on a broad range of image types, including photos of people. We distinguish ourselves on objects, artworks, logos and scans. See the Quality section for more details
Yes! Our AI model has been trained on a wide range of images with both hair and fur, so it does a nice job of preserving them.
Absolutely! Generative AI generally produces clean, slightly cartoonish images, and those usually work really well.
We have developed a custom AI model that we've trained on a large, proprietary dataset. The model has been specifically tuned for quality and efficiency.
Our terms of service just grant us the rights we need to deliver the service to you, and to improve our products. We don't claim any rights to the results, and we won't share your images with third parties unless you explicitly authorize us to do so.
Please see our Terms of Service for more details.
Right now, we retain images and results for five days after they are uploaded, after which they are permanently deleted. Please note that our data retention policies may change over time, and this current policy does not bind us in the future, or require your affirmative consent to change.