![](data:image/svg+xml,<svg xmlns="http://www.w3.org/2000/svg" width="73" height="73"><rect fill-opacity="0"/></svg>)
ok, I got ChatGPT working with Additive Prompting
Here's a 1 paragraph ChatGPT prompt you can use to generate infinite interior design/architecture photographs w/ 90%+ coherence to the prompt in Midjourney
Full prompt w/ examples in thread. Try reading the prompts as you go
🧵
Mar 13, 2023 · 3:12 AM UTC
The ChatGPT prompt is broken down in the next 2 tweets w/ videos, but here are some example outputs you can expect (Prompts in ALT tags)
My first video on Additive Prompting is coming this week on YouTube (link in bio)
ChatGPT prompt next tweet 👇
In a new chat, ask the following: (1/2)
"Please create a table that breaks down an interior architecture photograph composition into the following key elements, where each of these key elements is a column: ...[continued next tweet]
Key Elements: (2/2)
Composition, Camera Angle, Style, Room Type, Focal Point, Textures, Detail, Color Palette, Brand, Lighting, Location, Time of Day, Mood, Architecture
Fill the table with 10 rows of data, where:
Composition = "Editorial Style photo"
Additive Prompting is dynamic & modular by design, so it works well in the table format.
If you're after something specific, let ChatGPT know at the end of your prompt. For example...
...10 rows of data where:
Composition = "Editorial Style Photo"
Room Type = "Living Room"
You can copy & paste any row into Midjourney and it'll work great. Or, you can send a follow-up request and ask:
"Please write each row as a comma-separated sentence. Append each sentence with —ar 16:9"
There you go, infinite images with a good Additive Prompt structure and ChatGPT hack.
If you want new data, just ask for "10 more rows of data"
Now that you have a strong foundation to build off, you can tweak and edit the outputs to whatever you'd like.
Follow me @nickfloats
YouTube vid coming this week (link in bio)
My original interior thread 👇
