Looking for DALL-E 3 Help

dall-e 3 header
I just returned to DALL-E 3 after using its Microsoft version (currently called Copilot | Designer) for a while. But I can’t get in.

See how it says “Try in ChatGPT↗︎?” When I do that, it goes to https://chat.openai.com/. After I log in there, it offers no clue about where DALL-E 3 is. So I asked, “How do I get to the DALL-E 3 page after I’m logged in here?”

ChatGPT answered, “As of my last update in January 2022, DALL-E 3 is a hypothetical iteration of the DALL-E model, and there’s no information about its existence or how to access it. If it were to be released, you might typically find access through OpenAI’s website or platform if they make it available to the public. However, without further updates or announcements, it’s challenging to provide specific instructions. If OpenAI releases DALL-E 3 or any similar model in the future, you can check their official website or announcements for information on how to access it.”

Additional useless dialog followed. So now I’ll ask the Lazyweb. Does anyone know how to get into DALL-E 3?



4 responses to “Looking for DALL-E 3 Help”

  1. It’s integrated into ChatGPT (you may need the pro account?)

    So you just type “Make me an image of xyz” into CHatGPT and Dall-E does its thing right there.

  2. I don’t have a pro account. Too expensive.

    But I just asked something. The result:

    Me:
    “Make me an image of an AM broadcast tower in an empty field.”

    ChatGPT:
    “As a text-based AI model, I’m unable to directly create images. However, I can guide you on how to describe the image to an artist or use image generation tools.

    “Here’s a detailed description you could provide:

    “The scene depicts a solitary AM broadcast tower rising from the ground in the center of an expansive empty field. The tower stands tall and imposing, constructed of steel lattice or solid metal beams. Its structure is symmetrical and segmented, tapering towards the top. Wires and cables extend from the tower, connecting it to various equipment and antennas.

    “The field surrounding the tower is vast and devoid of any significant vegetation or structures. The ground is flat and barren, covered in sparse grass or dry earth. In the distance, the horizon stretches out endlessly, meeting a clear sky above.

    “The lighting in the scene is soft and diffused, indicating either early morning or late afternoon. The sun casts long shadows across the field, adding depth to the landscape. There are no visible signs of human presence or activity, emphasizing the isolated and remote nature of the location.

    “You can use this description to commission an artist to create the image for you, or you can try using image generation tools that allow you to input text descriptions to generate corresponding images.”

    That’s a very special form of useless, no? It also doesn’t incentivize me to get a pro account.

  3. Well, I just broke down and started paying $20/month to ChatGPT for access to DALL-E, and all its answers to my prompt, “Make me an image of an AM broadcast tower in an empty field,” even after I gave it very clear instructions, have been completely wrong. Our dialog ended with this from ChatGPT:

    “Thank you for your patience and for providing specific feedback. Without the capability to directly view or access external images for direct comparison and with the constraints in accurately interpreting and translating very specific technical requirements into visual prompts for DALL-E, it seems we’ve encountered challenges in precisely meeting your request.

    “The details you’ve provided—such as the need for non-tapering towers except at the base, the absence of any additional structures on the towers, and having exactly two towers in the scene—are clear, yet it appears the generated images haven’t aligned perfectly with these specifications.

    “Given these limitations, if there’s another way I can assist you, or if you have different questions or requests, please let me know. Your understanding and flexibility are greatly appreciated.
    Thank you for your patience and for providing specific feedback. Without the capability to directly view or access external images for direct comparison and with the constraints in accurately interpreting and translating very specific technical requirements into visual prompts for DALL-E, it seems we’ve encountered challenges in precisely meeting your request.

    “The details you’ve provided—such as the need for non-tapering towers except at the base, the absence of any additional structures on the towers, and having exactly two towers in the scene—are clear, yet it appears the generated images haven’t aligned perfectly with these specifications.

    “Given these limitations, if there’s another way I can assist you, or if you have different questions or requests, please let me know. Your understanding and flexibility are greatly appreciated.”

    As we say in New Jersey, that’s fucked.

    Anyway, I just posted something about it, here.

  4. According to Microsoft, DALL-E 3.0 is available via Bing Chat https://blogs.bing.com/search/october-2023/DALL-E-3-now-available-in-Bing-Chat-and-Bing-com-create-for-free

    I just tested it against my ChatGPT Pro account and they seem dang close.

Leave a Reply

Your email address will not be published. Required fields are marked *