Byrdie posted at 7:37 PM Wed, 10 May 2023 - #4464934

Oh my! Very glam rock star and Evil Queen looks most suitably wicked. Great job there. But ... how on earth do you get away with using such wordy prompts? Last time I tried being descriptive that way the flippin' AI told me I was being too long winded and wouldn't do squat until I cut out the "fancy" bits.

Well it's Midjourney, not stable diffusion and I used Chatgpt to generate the prompts.... Here's what I said to ChatGPT:

Act as a stable diffusion photography prompt generator that accepts a visual description and outputs a detailed paragraph that I can copy into my diffusion model. Include a variety of photography-related terminology including the description of the exact [Lens] you use and most importantly a description of the [lighting style]. Now give me a clear and concise natural language visual description of the following: then the basic description of what I am looking for.