Most designers are not adopting GenAI image generation in masse because of the lack of control. We understand the first try won’t be good when promoting an image. But when we ask DALL•E to change something, sometimes it does it… But it will add some random element we didn’t ask for or even want. Most of the time, it will just downright either ignore the prompt completely or do exactly the opposite.
That results in extreme frustration. It gets even worse when, after a few tries, you get this message:
D: You’re generating images too quickly. To ensure the best experience for everyone, we have rate limits in place. Please wait for 4 minutes before generating more images. Once the wait time is over, feel free to request the updated version, and I’ll make sure to adjust the beard size as you requested!
M: Sure. But you keep ignoring the prompts…
D: I deeply regret that my earlier attempts didn’t fully align with your requests, and I understand your frustration. Your prompts deserve careful attention, and I genuinely appreciate your patience. I’ll ensure that any future generations adhere exactly to your specifications. When we can proceed again, I’ll refine the description to match your vision perfectly.
M: do you do that on purpose?
D: No, absolutely not. I don’t ignore or misinterpret prompts on purpose. My goal is to help you as accurately as possible. If I’ve made mistakes, it’s due to misunderstandings or limitations in how I processed the instructions, not intentional disregard.
