Issue with Image Quality – DALL·E 3 Not Working in My Piko?

Hi! I’m building a Piko that acts as a branding assistant for psychologists. It uses gpt-4o with a detailed prompt and is supposed to generate three images during the conversation (a conceptual illustration, a logo, and a Canva-style template).

:small_blue_diamond: The problem is that the images generated are low quality and look like they’re from DALL·E 2, not DALL·E 3.

I have already disabled the “Use default image generation (Flux)” option as recommended, and confirmed that the image is being generated inside the Piko’s flow — but the results don’t resemble the clean, sharp DALL·E 3 images I get using ChatGPT.


:test_tube: Additional details:

  • I’m using the gpt-4o model.
  • The prompt is identical to what I use in my working GPT on chat.openai.com.
  • When I use the same image prompts directly on ChatGPT (e.g., the surreal Magritte-style illustration), it generates stunning results with clear detail and text handling — but not inside Pickaxe.
  • I’ve tried switching models, toggling Flux, etc., with no improvement.
  • I need these images to be downloadable and good enough to be embedded into a final PDF branding document.

:red_question_mark:Questions:

  • How can I make sure my Piko is using real DALL·E 3 (like in ChatGPT)?
  • Is there a way to force it to use the actual v1/images/generations DALL·E 3 API instead of the internal Flux renderer?

Thanks in advance — any guidance would be really appreciated!

Hi @moira777,

Welcome to the Pickaxe community!

You can use DALL·E 3 directly in Pickaxe by adding your own OpenAI API key via the Community Actions section. This is done by editing your Pickaxe, going to the Actions tab, scrolling down to Community Actions, and adding your API key.


You might be interested in checking this thread as well: GPT Image-1 Action | How to add custom image parameters by @ab2308

I hope this helps.

That’s already been done, and it doesn’t work. I’ve attached images of my entire setup. The problem seems to be that pickaxe isn’t properly executing the API call.

Hmm, seems to work fine on my end. We are using dall-e-3 but OpenAI can lower down the quality anytime they want.

I’ve retested it and it still doesn’t work. It ALWAYS creates the images with DALL-2. The assistant I created is a chatbot that asks questions and creates the images based on them. The pickaxe function call to the DALL-3 API doesn’t work.