Skip to main content

DALL-E 3 could take AI image generation to the next level

DALL-E 2DALL-E 2 Image on OpenAI.

OpenAI might be preparing the next version of its DALL-E AI text-to-image generator with a series of alpha tests that have now been leaked to the public, according to the Decoder.

An anonymous leaker on Discord shared details about his experience, having access to the upcoming OpenAI image model being referred to as DALL-E 3. He first appeared in May, telling the interest-based Discord channel that he was part of an alpha test for OpenAI, trying out a new AI image model. He shared the images he generated at the time.

We've NEVER seen Image Generation This Good! | SNEAK PEAK

The May alpha test version had the ability to generate images of multiple aspect ratios inside the image model. YouTuber, MattVidPro AI then showcased several of the images that were generated in a 16:9 aspect ratio. This version also showed the model’s prowess for high-quality text production, which continues to be a pain point for rival models, even for top generators such as Stable Diffusion and Midjourney.

Some examples showcased images, such as text melded into a brick wall, a neon sign of words, a billboard sign in a city, a cake decoration, and a name etched into a mountain. The model maintains that DALL-E is good at generating people. One such image displayed a woman eating spaghetti at a party from a fisheye point of view.

The leaker returned to the Discord channel in mid-July with more details and new images. He claimed to be a part of a “closed alpha” test version that included approximately 400 subjects. He added that he was invited to the trial via email and was also included in the testing of the original DALL-E and DALL-E 2. This is what led to the conclusion that the alpha test might be for DALL-E 3, though it has not been confirmed.

The model has been updated considerably between May and July. The leaker has showcased this by sharing images generated based on the same prompt, showing how powerful DALL-E 3 has gotten over time. The prompt reads a painting of a pink jester giving a high five to a panda while in a cycling competition. The bikes are made of cheese and the ground is very muddy. They are driving in a foggy forest. The panda is angry.

The May alpha produces the general scene that hits most of the points of the prompt. There’s a little distortion in the hands connecting, and the wheels of the bikes are yellow as opposed to being made of cheese. However, the July alpha is far more detailed, with the pink jester and the panda clearly high-fiving and the bicycle wheels made of cheese in several generations.

Meanwhile, in Midjourney, the jester is missing from the scene, the pandas are on motorcycles instead of bicycles. There are roads, instead of mud. The pandas are happy instead of angry.

There are a host of DALL-E 3 July alpha image examples that show the potential of the model. However, with the alpha test being uncensored, the leaker noted that also has the potential to generate scenes of “violence and nudity or copyrighted material such as company logos.”

Some examples include a gory anime girl, a Game of Thrones character, a Grand Theft Auto V cover, a zombie Jesus eating a Subway sandwich, also suggesting mild gore, and Shrek being dug up from an archeological dig, among others.

MattVidPro AI noted that the image model generates images as if they’re supposed to be in a specific style.

DALL-E 2 launched in April 2022 but was heavily regulated with a waitlist due to its popularity and concerns about ethics and safety. The AI image generator became accessible to the public in September 2022.

Editors' Recommendations

Fionna Agomuoh
Fionna Agomuoh is a technology journalist with over a decade of experience writing about various consumer electronics topics…
Google’s AI image-detection tool feels like it could work
An AI image of the Pope in a puffy coat.

Google announced during its I/O developers conference on Wednesday its plans to launch a tool that will distinguish whether images that show up in its search results are AI-generated images.

With the increasing popularity of AI-generated content, there is a need to confirm whether the content is authentic -- as in created by humans -- or if it has been developed by AI.

Read more
OpenAI’s new Shap-E tool is Dall-E for 3D objects
Purple and pink-diamond on blue background by Rostislav Uzunov.

OpenAI's latest endeavor, Shap-E, is a model that allows you to generate 3D objects from text, not unlike how Dall-E can create 2D images.

According to OpenAI, Shap-E is "a conditional generative model for 3D assets. Unlike recent work on 3D generative models which produce a single output representation, Shap-E directly generates the parameters of implicit functions that can be rendered as both textured meshes and neural radiance fields."

Read more
5 things AI image generators still struggle with
Dall-E was an early AI leader but hands are not its thing.

AI image generators like Dall-E, Stable Diffusion, Midjourney, and Bing Image Creator produce amazing results, but sometimes they can be incredibly frustrating. With simple prompts containing just a few words, an AI can output impressive images that appear to be professional photographs and convincing art in various styles. However, the same prompt will occasionally create some horrific creature or hilariously flawed rendering.

Negative prompts might help reduce the likelihood of these errors, but complexity can't always save you. Even AI experts struggle with misshapen creatures and unworldly scenes, requiring long hours of refining prompts or touching-up images with a traditional photo editor. For the time being, if you look carefully in the right areas of an image, there's a good chance you'll be able to identify if it was made by a machine.
Hand salad and balls of fingers
AI developers have made progress in the struggle to teach artificial intelligence tools how human hands should look, but there's plenty of room for improvement. If fingers aren't featured prominently, it's easy to miss errors, but it's an ongoing problem.

Read more