Inside PhotoroomProduct updates

Explore new Gen AI features coming soon to the Photoroom API

With the launch of our brand new AI model, we have additional solutions for our API on the way that we're excited for you to try:

Higher quality AI Backgrounds: A more enhanced AI background generator that provides crisper, higher resolution, and more realistic backgrounds. Great for revitalizing your product catalog and for ad creative testing.

AI Expand: Our generative AI will realistically expand the scene around an existing image.

AI Fill: Customize an item or area of your image with AI for more creative control. Instantly modify your visuals without photo shoots.

AI Images: Create brand new images using text prompts.

AI Upscale: Get higher resolution images or restore the details of old photos. Automatically elevate your product imagery for your e-commerce and point of sale materials.

Register to get early access

We're eager for you to try these amazing features in our API. Contact us, if you’re interested in being an early tester.

Udo KajaCommercial leader passionate about businesses flourishing. I write about how the Photoroom API can significantly impact businesses.
Explore new Gen AI features coming soon to the Photoroom API
Design your next great image

Design your next great image

Whether you're selling, promoting, or posting, bring your idea to life with a design that stands out.

Keep reading

How we automated our changelog thanks to ChatGPT
Jeremy Benaim
Jeremy Benaim
How we divided our server latency by 3 by switching from T4 GPUs to A10g
Matthieu Toulemont
What's new in product: July 2024
Jeanette Sha
Photoroom foundation diffusion model: why, how, and where do we go from there?
Benjamin Lefaudeux
What's new in product: February 2024
Jeanette Sha
Businesses need more threesomes, reveals market report
Aisha Owolabi
Redesigning an Android UI used by millions
Aurelien Hubert
From the Alps to AI: How Photoroom can cut your carbon footprint
Lyline Lim
4 times faster image segmentation with TRTorch
Matthieu Toulemont
We’re training a text-to-image model from scratch and open-sourcing it
Jon Almazán