I tested Dall.e 2, an AI that creates images from text

In summary, the conversation discusses the use of Dalle.e 2, a software that claims to create images from text descriptions. However, the participants of the conversation were disappointed with the results, as the images produced were not as expected and the software was not user-friendly. They also mention other AI tools used for creating art and express that humans are the true creators of art. Despite spending hours trying to configure and generate images, the consensus is that the software is currently not worth using.
  • #1

fluidistic

Gold Member
3,923
260
So I tested ChatGPT's cousin, Dalle.e 2. It is said to create images from text, and the website suggest to be very explicit in the description of the image, add many details, to get a good picture.
My mind started to wander... Would I finally get a pic of Einstein battling dinosaurs, or having a dinner with Newton while Trump and Putin are playing chess under the table? Boy did I was disappointed. Terribly disappointed.

Don't waste your time... this software is absolute garbage (for now at least), it's light years behind chatGPT.

Albert Einstein having a dinner with Isaac Newton while dinosaurs are playing chess under the table.
DALL·E 2023-02-13 22.15.38 - Albert Einstein having a dinner with Isaac Newton while dinosaurs...png
Music flowing in a river with pink reflections with physics equations on the water
DALL·E 2023-02-13 22.18.12 - Music flowing in a river with pink reflections with physics equat...png
Humanized apes having dinner on a table with Einstein while playing Bitcoin
DALL·E 2023-02-13 22.19.22 - Humanized apes having dinner on a table with Einstein while playi...png
A neandertal fighting an angry tyranosaurus rex with a screwdriver on a busy road
DALL·E 2023-02-13 22.20.40 - A neandertal fighting an angry tyranosaurus rex with a screwdrive...png
 
  • Haha
Likes mcastillo356
Physics news on Phys.org
  • #2
I had the same experience with Defusion Bee. It was about the same as what you are showing. People on DeviantArt are producing wildly better things with Ai, including complex stories with consistent appearances of the characters. I don't know what tools they are using, but it isn't DeviantArt's own Ai. The thing threatened to ban me for my first request, and didn't even say why.
 
  • Like
Likes Office_Shredder
  • #3
The person who won that art competition said they spent 200 hours trying prompts before getting what they wanted. This isn't a fire and forget tool.
 
  • Like
Likes Algr
  • #4
Yes. Ai can't create art. But then neither can pencils, cameras, or photoshop. Humans create art.

cosmic_dreamer__a_girl_s_journey_through_the_stars_by_oanarinaldi_dfoh951-pre.jpg

p2u_city_background_56_by_luffassets_dfnpb5y-pre.jpg
pretty_library__made_with_ai__by_kroniksan_df9fsg9-fullview.jpg
 
  • #5
I have spent several evenings trying to configure stable diffusion to run on my computer using CUDA. I have spent even more hours generating over 24k images from different prompts (OK, my computer did, choosing and entering a prompt is like half a minute). I have but a few images that are reasonably close to being worth of showing.

Yes, at this stage it is mostly useless garbage.

1676362501600.png


1676362513156.png
 
  • Like
Likes BillTre, Algr and DennisN

1. What is Dall.e 2 and how does it work?

Dall.e 2 is an AI developed by OpenAI that uses natural language processing and generative adversarial networks to create images based on text input. It works by analyzing the text and generating a corresponding image using its vast database of visual elements and patterns.

2. How accurate are the images generated by Dall.e 2?

The accuracy of Dall.e 2's images depends on the complexity and specificity of the text input. In general, it has shown impressive accuracy in creating images that closely match the given text. However, it is still a work in progress and may not always produce perfect results.

3. Can Dall.e 2 be used for commercial purposes?

As of now, Dall.e 2 is not available for commercial use. It is still in its developmental stage and is only accessible to researchers and developers. However, OpenAI has plans to make it available for commercial use in the future.

4. Is Dall.e 2 capable of creating any type of image?

Dall.e 2 is trained on a wide range of visual elements and patterns, but it may not be able to create every type of image. Its capabilities are limited to the data it has been trained on, and it may struggle with more abstract or complex concepts.

5. How does Dall.e 2 differ from other AI image generation models?

Dall.e 2 is unique in its ability to create images from text input, rather than just modifying existing images. It also has a larger database of visual elements and patterns, which allows it to generate more diverse and accurate images. Additionally, Dall.e 2 is trained on a broader range of visual concepts, making it more versatile compared to other AI image generation models.

Similar threads

Replies
10
Views
2K
Back
Top