You can now integrate state-of-the-art image generation capabilities directly into your apps and products through our new DALL·E API. You can get started here.
You own the generations you create with DALL·E.
We’ve simplified our Terms of Use and you now have full ownership rights to the images you create with DALL·E — in addition to the usage rights you’ve already had to use and monetize your creations however you’d like. This update is possible due to improvements to our safety systems which minimize the ability to generate content that violates our content policy.
Sort and showcase with collections.
You can now organize your DALL·E creations in multiple collections. Share them publicly or keep them private. Check out our sea otter collection!
We’re constantly amazed by the innovative ways you use DALL·E and love seeing your creations out in the world. Artists who would like their work to be shared on our Instagram can request to be featured using Instagram’s collab tool. DM us there to show off how you’re using the API!
—The OpenAI Team
DALL-E’s Images API provides three methods for interacting with images.
- Creating images from scratch based on a text prompt
- Creating edits of an existing image based on a new text prompt
- Creating variations of an existing image
The guide covers the basics of using these three API endpoints with useful code samples.
To see them in action, check the DALL·E preview app.
Today OpenAI sent a message to DALL·E's users saying "you can now upload and edit photos with faces with DALL·E," which had been forbidden for a while due to the concerns stated in the communication.
Many of you have told us that you miss using DALL·E to dream up outfits and hairstyles on yourselves and edit the backgrounds of family photos. A reconstructive surgeon told us that he’d been using DALL·E to help his patients visualize results. And filmmakers have told us that they want to be able to edit images of scenes with people to help speed up their creative processes.
With improvements in our safety system, DALL·E is now ready to support these delightful and important use cases – while minimizing the potential of harm from deepfakes.
We made our filters more robust at rejecting attempts to generate sexual, political, and violent content – while also working to reduce false flags – and built new detection and response techniques to stop misuse.
Our content policy still prevents uploading images of anyone without their consent, or images that you do not have the rights to.
We hope this update helps you use DALL·E in even more creative and practical ways. We’re excited to see what you create!
—The OpenAI Team
Three days ago, I shared an experiment suggested by Adam Watters on Discord in which I asked DALL-E 2 to generate variations of 3D textures. I sent the results to Adam, who applied the texture to the 3D character.
asked dalle 2 to make a new face for this character and now it's haunting me pic.twitter.com/MbocEN4pJd
— Adam Watters (@AdamWatters) July 13, 2022
Here's a video in which I test if OpenAI's DALL-E can generate usable texture maps from an uploaded image.
This texture comes with one of Apple's project examples and the idea of generating textures with DALL-E came from Adam Watters on Discord.
I continue to play with DALL-E 2 from time to time. I've posted a few videos and live streams on the topic and plan to share more clips with tiny bits from my experiments and some of my favorite results so far. Tomorrow, a video sharing how DALL-E can copy my hand drawings will come out on YouTube.
Here are my impressions of OpenAI's latest iteration of DALL·E, an AI system that generates images from text. I've generated images in different styles and variations of my drawings, experimented with public pages, mask edits, uploads, and more.
