Exploring AI Art Generation with Midjourney (October 8th, 2023)

 



October 8th, 2023

Exploring AI Art Generation through Image Variations and Stylistic Experiments

I focused on exploring the creative possibilities of Midjourney, an AI image generation tool, by experimenting with different prompts and settings to produce variations of an image depicting "Ronald McDonald." My objective was to create a series of images portraying Ronald McDonald's family, including his wife and daughter. Through trial and error, I adjusted the parameters, particularly the prompt strength, to achieve a realistic photograph-like appearance. Despite requiring multiple attempts, this experimentation resulted in high-quality, realistic images that aligned well with my vision.


Experiment 1: Ronald McDonald’s Family


The initial focus was to develop realistic photographic depictions of Ronald McDonald’s wife and daughter. The challenge was balancing prompt strength, number of inference steps, and guidance scale to yield a photograph-like aesthetic. The following are key prompt configurations that helped achieve desirable results:


Original photograph: 


Ronald McDonald's Wife:

Prompt: "Ronald McDonald's wife, photograph, 8k"

Prompt Strength: 0.7




Ronald McDonald's Daughter:

Prompt: "Ronald McDonald's daughter, young girl, photograph, 8k"

















Prompt:  A fantasy landscape of mcdonald's, hyper-realistic, photograph, 8k

Negative prompt: digital art, unrealistic

Prompt strength: 0.8

Num_inference_step: 158

Guidance_scale: 7.5



Prompt strength: 1

Scheduler: DPM solver multi step



Experiment 2: Claymation Image Transformation


For my next experiment, I wanted to transform a 3D image into one resembling claymation, drawing inspiration from Ralph Bakshi's art style. I used prompts that focused on achieving a distinct aesthetic:


Prompt: "A fantasy landscape, claymation"

Negative Prompt: "Ugly, deformed"

Prompt Strength: 0.8

Num Inference Steps: 25

Guidance Scale: 7.4





Original image:



Despite adjusting the prompt strength and inference steps, achieving the desired claymation style proved challenging. However, I ultimately identified an effective prompt combination to create a unique artistic image. I found that maintaining the guidance scale within a mid-range was crucial to retaining the desired level of detail.



Conclusions


These experiments provided valuable insights into the nuanced use of Midjourney's prompt configurations. Adjusting prompt strength, inference steps, and guidance scale allowed for creative flexibility while generating images. Definitely takes A LOT of trial and error with prompting to get what you have in mind…

Comments

Post a Comment

Popular posts from this blog

(October 29th, 2023)Development of a Customized Lora: A Deep Dive into Personalized AI-Generated Imagery

Image
  Development of a Customized Lora: A Deep Dive into Personalized AI-Generated Imagery October 29th, 2023 Objective: The primary objective of this project was to create a professional-grade photograph using a custom AI model, termed "Lora." This initiative was inspired by Aragon (https://www.aragon.ai/), a commercial AI tool available at Aragon AI, which offers similar capabilities but at a cost. Methodology: The project began with the compilation of two image datasets. The initial dataset lacked diversity, consisting of overly similar images, which necessitated the creation of a second, more varied dataset. Both the standard definition (SD) and extra-large (XL) versions of Lora were trained using Kohya's framework, renowned for its robustness and versatility in managing advanced AI models. Challenges and Results: The anticipated high-quality output from the XL Lora did not meet expectations initially, as the images suffered from pixelation and blurriness. Adjusting the s
Read more

Digital Marketing with AI - 30 Page Marketing Plan

Image
I created a marketing 30 page marketing document utilizing AI. Check it out below. It's quite long!!! I also can't figure out why the formatting is messed up here.... G.M.O.: AI Content Generation Services   Project Description Summary: G.M.O. (Graphically Modified Organisms) harnesses innovative AI tools to produce unique and cost-effective music videos and digital content tailored for artists and musicians. By leveraging advanced AI technologies, G.M.O. enhances online engagement through creative visuals and animations, offering an economical alternative to traditional content production methods. This approach not only amplifies the digital presence of artists but also delivers distinctive content that resonates with their audiences. 1. Persona The goal of G.M.O. is dedicated to bridging the gap between artists and musicians and our innovative AI video solutions, ensuring their digital presence is not just seen, but felt 2. Organization G.M.O. is at the forefront of AI-driven
Read more