April 2, 2023
Dr. Dmitriy Starson, CEO of Passio Inc.
MidJourney and other diffusion models have transformed the world of art, content creation and design. As so many of us in the AI community, our team at Passio has been actively experimenting with generative art and especially MidJourney. As the creators of Nutrition-AI we are especially excited about about the role generative models can play in food image and food art creation. In our recent post, Text-to-image Generation in Computer Vision, explored how generative models like Dall-E and Stable Diffusion can impact creation of AI datasets for computer vision and now we want to dive more into the creative side of things and explore how Midjourney can be used to create stunning food art.
MidJourney is a great tool for creating realistic food images for advertising, packaging, and menu design. With its advanced features and user-friendly interface, it allows for quick creation of beautiful food images. This post provides an in-depth look at using MidJourney for high-quality food images to achieve business goals.
Script for Chat GPT:
Write without word wraps, headlines, connection words. Write back to back separated with commas and spaces:
[1], [2], [3], [4], [5]
replace [1] with a [USE YOUR PROMPT for example "a bottle of wine" or "chocolate cake"]
replace [2] with a list of detailed descriptions about [1]
replace [3] with a list of detailed descriptions about the environment of the scene
replace [4] with a list of detailed descriptions about the mood/feelings and atmosphere of the scene
replace [5] with a list of detailed descriptions about the way the prompt should be realized (eg. Photography with camera model and according settings, Painting with detailed descriptions about the materials and working material used, rendering with engine settings, and everything else that could be called output type)
complex prompt for an AI-based text to image program that converts a prompt about a topic into an image. The outcome depends on the prompts coherency. The topic of the whole scene is always depends on the subject that is replaced with [1]. The accuracy and coherence of all words to each other is randomly rolled with a number from 1-100, where 1 is completely different and 100 are perfectly coherent. The number is never written but is only used for calculation
always start the prompt with "/imagine prompt: "
always end the prompt with " --v 4"
never write anything that is in [] brackets
don't use any line breaks
when the subject looks better vertically, add "--ar 2:3" before "--v 4".
When the subject looks better horizontally, use "--ar 3:2" instead
Top Videos & Influencers We Learned From:
Grow your business with ready-to-use AI modules and AI/AR-driven experiences.
