ChatGPT Formula for Generating Prompts

 

I recently came across a YouTube video by a creator named Monice in which she gave a formula that would enable one to use ChatGPT as an image generator for Midjourney.  The given formula to be entered into ChatGPT reads as follows:

"Here’s a Midjourney formula for you to understand.

‘/imagine prompt: [Image we are prompting], [5 descriptive keywords], [Camera type], [Camera lens type], [time of the day], [focal distance], [style of photograph], [by photographer name] –ar x:y Reply ‘yes’ if you understood the formula."

I decided to give it a try and ChatGPT quickly furnished me with the following parameters:

"/imagine prompt: [Image we are prompting], [5 descriptive keywords], [Camera type], [Camera lens type], [time of the day], [focal distance], [style of photograph], [by photographer name] –ar x:y

[Image we are prompting]: This is the main subject or content of the photograph that will be used as a basis for the prompt.

[5 descriptive keywords]: Five words that describe the main elements or characteristics of the image.

[Camera type]: The type of camera used to capture the photograph.

[Camera lens type]: The specific lens used on the camera to capture the image.

[time of the day]: The specific time of day when the photograph was taken (e.g., morning, afternoon, evening).

[focal distance]: The distance at which the camera's lens is focused when capturing the image.

[style of photograph]: The artistic style or approach used in the photograph (e.g., abstract, portrait, landscape).

[by photographer name]: The name of the photographer who took the picture.

–ar x:y: The aspect ratio (ar) of the photograph, represented by 'x:y'"

I in turn provided the following information:

"Here are the specifics for each parameter as numbered above: 1. image we are prompting = A depressed young woman sits on wet floor in an unfurnished darkened basement and stares forlornly at a tiny skylight high above her head; 2. five descriptive keywords = depressed, melancholy, darkened, forlorn, muted; 3. camera type = nikon df dslr; 4. lens type = nikon 23mm wide angle lens; time of day = 4pm EST; focal distance = 5 feet; style of photograph - artistic vintage color; name of photographer = paola m franqui; aspect ratio = 1620 px wide by 1080 px high"

ChatGPT then issued the following prompt:

"A depressed young woman sits on the wet floor in an unfurnished darkened basement and stares forlornly at a tiny skylight high above her head. Keywords: depressed, melancholy, darkened, forlorn, muted. Camera type: Nikon DF DSLR. Lens type: Nikon 23mm wide-angle lens. Time of day: 4 PM EST. Focal distance: 5 feet. Style of photograph: Artistic vintage color. By photographer Paola M Franqui. –ar 1620:1080"

Since I do not currently have an account on Midjourney, I instead entered the prompt into Clipdrop Stable Diffusion XL which generated four images from it, two of which are shown here.

I thought the images were very much in line with what I had been looking for, though I don't know if it really had been necessary to go through ChatGPT to get them.