AI's Artistic Journey: Capturing the Essence of 'Style-Aesthetic' with Midjourney
- 9 minutes read - 1857 wordsTable of Contents
The ‘style-aesthetic’ is a powerful tool in visual storytelling, allowing artists to evoke specific emotions and atmospheres through their work. It encompasses elements like color palettes, lighting, composition, and even the choice of camera lens. In the realm of AI image generation, capturing this ‘style-aesthetic’ is a crucial step towards creating truly compelling and evocative visuals. This blog post explores the results of an experiment that tested an AI model’s ability to understand and recreate the ‘style-aesthetic’ of various scenes. While the model demonstrated promising results in areas like camera positioning and shot analysis, it struggled to accurately capture the desired aesthetic, highlighting the ongoing challenges in this field. We’ll delve into the specifics of the experiment, analyzing the model’s performance and discussing the implications for the future of AI-generated imagery.
Created with: midjourney
Lost in the Sands: A Lone Wanderer Explores Ancient Ruins
A solitary figure traverses a desolate desert landscape, drawn towards the enigmatic remnants of a once-great city. The vastness of the surroundings and the towering ruins evoke a sense of awe and mystery, promising an adventure filled with wonder and intrigue.
Prompt
Vintage: Epic, adventurous, hopeful ; A lone, weathered explorer; medium shot; Adventure; a vast, sun-drenched desert landscape with ancient ruins in the distance; cinematic
Characteristic
Shot : A lone figure walks through a desolate desert landscape. The remains of a crumbling city rise in the distance, hinting at a lost civilization.
Aesthetic Score : 0.7
Mood : melancholy, solitary, mysterious
Quality
Entropy : 6.32
Noise : 97
Prompt Clip Score : 0.32
AI Evaluation
Likelihood of AI : 0.90
Image errors : Some blurring and artifacting present, particularly around edges of foreground figure
Candlelight Games: A Cozy Evening of Nostalgia
Three children huddle around a board game, illuminated by the warm glow of candlelight. The intimate setting evokes a sense of cozy nostalgia, while the surrounding darkness adds a touch of mystery. This image captures the simple joys of childhood and the magic of shared moments.
Prompt
Vintage: Nostalgic, intimate, playful ; A group of children playing a board game; close-up; Gaming; a dimly lit room with a worn wooden table and flickering candlelight; cinematic
Characteristic
Shot : Three children are playing a board game by candlelight in a dimly lit room. The scene is intimate and cozy, with a focus on the children’s playful interaction.
Aesthetic Score : 0.7
Mood : cozy, playful, intimate
Quality
Entropy : 6.22
Noise : 86
Prompt Clip Score : 0.33
AI Evaluation
Likelihood of AI : 0.10
Image errors : There are no noticeable artifacts or errors in the image.
A Moment of Departure: Nostalgia and Mystery on the Platform
A woman in a floral dress stands on a train platform, her back to the camera, gazing at a departing train. The steam billows around her, creating a sense of wistful nostalgia and dramatic movement. Her suitcase suggests a journey, leaving the viewer to wonder about her destination and the emotions behind her departure.
Prompt
Vintage: Romantic, adventurous, hopeful ; A young woman in a vintage dress standing on a train platform; long shot; Travel; a bustling train station with steam locomotives and vintage luggage; cinematic
Characteristic
Shot : A woman in a floral dress is standing on a train platform, with a vintage steam train behind her. The train is about to depart, and she is looking at it with a thoughtful expression.
Aesthetic Score : 0.7
Mood : nostalgic, romantic, pensive
Quality
Entropy : 6.80
Noise : 103
Prompt Clip Score : 0.38
AI Evaluation
Likelihood of AI : 0.10
Image errors : The image is slightly blurry, and there are some artifacts in the background.
Firefighter Bravely Rescues Child from Burning Building
A dramatic scene unfolds as a firefighter, clad in protective gear, stands with a small child in front of a blazing inferno. The contrast between the flames and the firefighter’s heroism creates a powerful image of courage and sacrifice.
Prompt
Vintage: Dramatic, heroic, suspenseful ; A firefighter carrying a child through a burning building; close-up; Heroism; a smoky, chaotic scene with flames and debris; cinematic
Characteristic
Shot : A firefighter carrying a child through a burning building or fire scene. The background is blurry and mostly filled with smoke and flames.
Aesthetic Score : 0.8
Mood : dramatic, heroic, somber
Quality
Entropy : 6.64
Noise : 100
Prompt Clip Score : 0.32
AI Evaluation
Likelihood of AI : 0.00
Image errors : No noticeable artifacts or errors
Campfire Night: A Family’s Cozy Escape Under the Stars
A heartwarming scene of a family gathered around a crackling campfire, bathed in its warm glow against the backdrop of a star-filled night. The image evokes feelings of peace, nostalgia, and the comforting embrace of loved ones.
Prompt
Vintage: Warm, nostalgic, peaceful ; A family gathered around a campfire; wide shot; Family; a serene forest setting with stars twinkling in the night sky; cinematic
Characteristic
Shot : A family of four is gathered around a campfire in a forest at night. The scene is set under a canopy of trees and a starry sky.
Aesthetic Score : 0.7
Mood : cozy, nostalgic, peaceful
Quality
Entropy : 6.75
Noise : 123
Prompt Clip Score : 0.34
AI Evaluation
Likelihood of AI : 0.80
Image errors : The image has some minor artifacts, such as the slight blurriness of the figures and the lack of detail in the background.
Nostalgia on the Open Road: A Vintage Car Through Majestic Mountains
A serene and nostalgic journey unfolds as a vintage car navigates a winding forest road, with a breathtaking mountain range serving as a backdrop. The scene evokes a sense of adventure and grandeur, capturing the timeless beauty of nature and the allure of classic automobiles.
Prompt
Vintage: Romantic, adventurous, nostalgic ; A vintage car driving down a winding mountain road; long shot; Tourism; a scenic mountain landscape with lush forests and snow-capped peaks; cinematic
Characteristic
Shot : A winding road through a mountain pass with a car driving towards the viewer.
Aesthetic Score : 0.7
Mood : tranquil, scenic, nostalgic
Quality
Entropy : 6.79
Noise : 122
Prompt Clip Score : 0.34
AI Evaluation
Likelihood of AI : 0.30
Image errors : Some minor noise, the car is a little blurry.
Soaring Through Nostalgia: A Vintage Biplane’s Journey
Experience the thrill of flight from the cockpit of a vintage biplane as it cuts through the clouds. This nostalgic scene evokes a sense of adventure and hope, transporting you to a bygone era of open skies and boundless possibilities.
Prompt
Vintage: Exhilarating, adventurous, free ; A pilot in a vintage biplane soaring through the clouds; close-up; Adventure; a breathtaking view of a vast, blue sky with fluffy white clouds; cinematic
Characteristic
Shot : A yellow biplane flying above the clouds, with a pilot in the cockpit wearing a leather helmet and goggles.
Aesthetic Score : 0.7
Mood : adventurous, nostalgic, daring
Quality
Entropy : 6.67
Noise : 100
Prompt Clip Score : 0.34
AI Evaluation
Likelihood of AI : 0.30
Image errors : Some slight blurriness and compression artifacts
Soldiers March Through a City Reduced to Rubble
A haunting image captures the grim reality of war, with soldiers silhouetted against a smoke-filled sky as they navigate a city ravaged by conflict. The scene evokes a sense of desolation and foreboding, highlighting the devastating impact of war on both the landscape and the human spirit.
Prompt
Vintage: Grim, heroic, determined ; A group of soldiers marching through a war-torn city; medium shot; Heroism; a desolate cityscape with rubble and smoke; cinematic
Characteristic
Shot : A group of soldiers walk through a war-torn city. The buildings are destroyed and there is smoke and debris everywhere.
Aesthetic Score : 0.7
Mood : grim, desolate, somber
Quality
Entropy : 6.54
Noise : 103
Prompt Clip Score : 0.33
AI Evaluation
Likelihood of AI : 0.50
Image errors : No visible artifacts, a little bit of noise in the background.
A Dance Amidst the Golden Glow: A Romantic Ballroom Scene
In a grand ballroom filled with elegantly dressed guests, a couple shares a dance, their connection highlighted by the warm, golden light from the massive chandelier above. The scene, with an aesthetic score of 0.7, exudes romance and nostalgia, creating a dramatic effect that emphasizes their intimacy and isolation amidst the crowd.
Prompt
Vintage: Romantic, elegant, nostalgic ; A couple dancing in a vintage ballroom; close-up; Tourism; a grand ballroom with chandeliers and elegant guests; cinematic
Characteristic
Shot : A ballroom dance scene with a couple in the foreground, other dancers in the background, and a beautiful chandelier in the top center of the frame.
Aesthetic Score : 0.75
Mood : romantic, elegant, nostalgic
Quality
Entropy : 6.81
Noise : 94
Prompt Clip Score : 0.37
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image has a slight color cast, and the overall lighting is a bit flat.
A Boy’s Journey Begins in the Shadows
A young boy, bathed in the warm glow of a single candle, studies a map spread across a wooden table. The dim light casts long shadows, adding to the air of mystery and intrigue. His focused expression suggests a sense of adventure about to unfold.
Prompt
Vintage: Curious, adventurous, hopeful ; A young boy gazing at a vintage map; close-up; Adventure; a dimly lit room with a worn wooden table and a flickering candlelight; cinematic
Characteristic
Shot : A young boy sits at a wooden table, lit by a single candle. He’s looking down at a large map spread out in front of him, possibly lost in thought about adventure.
Aesthetic Score : 0.7
Mood : mystical, contemplative, nostalgic
Quality
Entropy : 6.73
Noise : 76
Prompt Clip Score : 0.33
AI Evaluation
Likelihood of AI : 0.20
Image errors : No visible errors.
Conclusion
The results indicate that the generative AI model performed well in terms of camera position and shot analysis, but struggled with aesthetic analysis.
Here’s a breakdown:
- Camera Position: The model scored 0.45, which falls slightly below the “good” range of 0.5 to 0.75. This suggests that the model’s ability to interpret and recreate camera positions from the prompt is decent, but could be improved.
- Shot Analysis: The model scored 0.395, also slightly below the “good” range. This indicates that the model’s understanding of the scene and its ability to translate it into a shot is decent, but could be more accurate.
- Aesthetic Analysis: The model scored 0.07, which is significantly below the “very good” range of -0.2 to 0.1. This suggests that the model struggled to match the expected aesthetic of the image, indicating a potential mismatch between the prompt’s aesthetic description and the generated image’s visual style.
Overall, the model shows promise in understanding camera positions and scene composition, but needs improvement in capturing the desired aesthetic.
Sources:
- https://heartofnoir.com/knowing-noir/aesthetic-of-noir/
- https://www.yellowbrick.co/blog/film/maximizing-the-visual-impact-unveiling-the-art-of-film-aesthetics
- https://www.questjournals.org/jrhss/papers/vol10-issue8/1008255260.pdf
- https://www.jstor.org/stable/3331672
- https://www.cinepoetics.fu-berlin.de/activities/workshops/2020-12-ws/index.html
- https://resource.download.wjec.co.uk/vtc/2016-17/16-17_1-22/eng/Part%201%20What%20is%20Aesthetics.pdf
- https://midjourney.com