AI's Artistic Struggle: Capturing the 'Dramatic' Aesthetic with Imagen-v3-fast
- 10 minutes read - 1982 words
Table of Contents
The ‘dramatic’ aesthetic is a powerful tool in visual storytelling, evoking strong emotions and immersing viewers in a world of heightened tension and intensity. It’s often characterized by stark contrasts, dramatic lighting, and a sense of grandeur. But can AI truly capture this complex aesthetic? In this experiment, we tasked a generative AI model with creating images that embody the ‘dramatic’ style. While the model demonstrated a good understanding of camera positions and shot types, it struggled to capture the desired mood and atmosphere. This highlights the ongoing challenge of teaching AI to understand and replicate artistic styles, particularly those that rely on subtle nuances and emotional impact.
Created with: imagen-v3-fast
A Soldier’s Silhouette Against the Setting Sun
A lone soldier walks away from a devastated battlefield, the setting sun casting a melancholic glow on the scene. The image evokes a sense of isolation and contemplation, highlighting the somber aftermath of war.
Prompt
style-aesthetic Gritty realism: Melancholy, determined ; A lone soldier, silhouetted against the setting sun; wide shot; Heroism; a war-torn battlefield littered with debris and the wreckage of tanks; cinematic
Characteristic
Shot : A lone soldier walks away from a destroyed battlefield, the sun setting behind him. There are scattered ruins of buildings and a tank in the background.
Aesthetic Score : 0.7
Mood : melancholy, somber, reflective
Quality
Entropy : 6.91
Noise : 69
Prompt Clip Score : 0.34
AI Evaluation
Likelihood of AI : 0.70
Image errors : There are no noticeable errors in the image.
Lost in the Jungle: A Man’s Desperate Search
A lone figure, weathered and scarred, stands amidst the ruins of an ancient temple, his gaze fixed on the horizon. The setting sun paints the lush jungle in warm hues, casting long shadows that amplify the sense of mystery and danger. What secrets lie hidden within the overgrown walls? What fate awaits this man in the heart of the jungle?
Prompt
style-aesthetic Gritty realism: Intrigued, apprehensive ; A weathered explorer, their face etched with lines of hardship, peering through a dense jungle canopy; close-up; Adventure; overgrown ruins of an ancient temple; cinematic
Characteristic
Shot : A man with a worried expression, covered in dirt and scratches, stares into the distance. He’s standing in front of a temple ruin in a lush jungle. The setting sun casts a warm glow on the scene.
Aesthetic Score : 0.8
Mood : dramatic, suspenseful, mysterious
Quality
Entropy : 6.62
Noise : 81
Prompt Clip Score : 0.33
AI Evaluation
Likelihood of AI : 0.80
Image errors : The image appears to be slightly blurry around the edges. The lighting is also slightly uneven.
The Focus is on the Game, Not the Pizza
A casual gaming session captured in a moment of intense focus. The blurry background of pizza and drinks hints at the relaxed atmosphere, while the player’s grip on the controller reveals their dedication to the game.
Prompt
style-aesthetic Gritty realism: Focused, intense ; A gamer’s hands, gripping a worn controller, illuminated by the flickering glow of a monitor; close-up; Gaming; a dimly lit room filled with empty pizza boxes and energy drink cans; cinematic
Characteristic
Shot : A person is holding a gaming controller in their hands. There is a blurry background with pizza and drinks
Aesthetic Score : 0.5
Mood : intense, focused, casual
Quality
Entropy : 6.57
Noise : 29
Prompt Clip Score : 0.36
AI Evaluation
Likelihood of AI : 0.30
Image errors : The image has some slight blurriness and the lighting is uneven.
Lost in Time: A Solitary Figure Haunts a Deserted Diner
A lone man, burdened by a backpack, stands before a forgotten diner, its Coca-Cola sign a faded echo of a bygone era. The desolate setting whispers of solitude and melancholy, leaving a lingering sense of mystery in the air. The stark contrast between the man’s presence and the empty diner amplifies the feeling of isolation, inviting contemplation on the weight of loneliness and the passage of time.
Prompt
style-aesthetic Gritty realism: Lonely, contemplative ; A weary traveler, their backpack slung over their shoulder, gazing out at a desolate, dusty landscape; medium shot; Tourism; a crumbling roadside diner with faded neon signs; cinematic
Characteristic
Shot : A lone man with a backpack stands in front of a deserted diner with a ‘Coca Cola’ sign in the background. The setting is likely a rural or desert area.
Aesthetic Score : 0.7
Mood : melancholy, nostalgic, solitude
Quality
Entropy : 6.68
Noise : 58
Prompt Clip Score : 0.37
AI Evaluation
Likelihood of AI : 0.20
Image errors : No significant errors detected. The image has a slightly grainy texture but it contributes to the overall mood.
Where Are They Going? The Mystery Unfolds on This Train
A group of passengers, shrouded in shadow, gaze out the window of a moving train. The dim lighting and tense atmosphere create a palpable sense of suspense, leaving viewers to wonder what awaits them at their unknown destination.
Prompt
style-aesthetic Gritty realism: Intimate, hopeful ; A family huddled together in a cramped train compartment, their faces illuminated by the flickering light of a single overhead bulb; medium shot; Travel; a train rattling through a dark, rain-soaked countryside; cinematic
Characteristic
Shot : A group of people are sitting on a train, looking out the window. The lighting is dim and the atmosphere is tense.
Aesthetic Score : 0.6
Mood : suspenseful, moody, mysterious
Quality
Entropy : 6.39
Noise : 87
Prompt Clip Score : 0.32
AI Evaluation
Likelihood of AI : 0.10
Image errors : There are no noticeable image errors.
Lost in the City’s Shadow
A solitary figure stands dwarfed by a towering skyscraper, shrouded in the moody light of an overcast city. The low camera angle emphasizes their isolation and the imposing grandeur of the urban landscape.
Prompt
style-aesthetic Gritty realism: Awe, trepidation, isolation ; A lone figure, dwarfed by the towering skyscraper, gazes upwards with a mixture of awe and trepidation. The camera slowly pans up, revealing the building’s imposing facade against the backdrop of a bustling cityscape.; cinematic
Characteristic
Shot : A lone figure in a hooded jacket stands in the shadow of a towering skyscraper in a city setting. The camera is positioned low, looking upwards towards the building. The city is bathed in a moody, overcast light.
Aesthetic Score : 0.7
Mood : dark, ominous, lonely
Quality
Entropy : 6.22
Noise : 70
Prompt Clip Score : 0.32
AI Evaluation
Likelihood of AI : 0.70
Image errors : The image is slightly overexposed, resulting in a loss of detail in the shadows. There are also some minor artifacts in the background, likely due to noise reduction.
Facing the Flames: A Firefighter’s Courage in the Face of Danger
A powerful image captures the intensity of a firefighter’s duty. Standing before a burning building, the flames blurred in the background, the firefighter’s calm gaze speaks volumes about their bravery and dedication. The contrast between the controlled presence and the raging fire creates a dramatic and impactful scene.
Prompt
style-aesthetic Gritty realism: Brave, determined ; A firefighter, their face obscured by smoke, battling a raging inferno; close-up; Heroism; a burning building with flames licking at the sky; cinematic
Characteristic
Shot : A firefighter in full gear, standing in front of a burning building. The flames are out of focus in the background, and the firefighter is looking directly at the camera.
Aesthetic Score : 0.7
Mood : intense, dramatic, serious
Quality
Entropy : 6.54
Noise : 51
Prompt Clip Score : 0.32
AI Evaluation
Likelihood of AI : 0.30
Image errors : There are no visible image errors, however, the image is slightly blurry which can be a result of the camera settings. The exposure of the image could also be improved.
One Man, One Mountain: A Hiker’s Solitary Journey
A lone hiker braves the snowy mountain pass, his determined gaze reflecting the challenge ahead. The vast, white landscape evokes a sense of isolation and adventure, hinting at a difficult but rewarding journey. Two other hikers in the distance offer a glimpse of companionship, but for now, he walks alone, facing the mountain’s majesty.
Prompt
style-aesthetic Gritty realism: Exhausted, determined ; A group of adventurers, their faces grimy and exhausted, navigating a treacherous mountain pass; wide shot; Adventure; a snow-covered mountain range with jagged peaks; cinematic
Characteristic
Shot : A lone hiker, facing the camera, walks through a snowy mountain pass. Two other hikers are visible in the distance, walking towards the peak.
Aesthetic Score : 0.7
Mood : dramatic, adventurous, lonely
Quality
Entropy : 6.58
Noise : 89
Prompt Clip Score : 0.32
AI Evaluation
Likelihood of AI : 0.80
Image errors : The image has some minor pixelation and blurring, especially in the distant mountains.
Neon Focus: A Gamer’s Intensity
A young man, bathed in the glow of neon lights, sits at his computer desk, his headphones on, fingers flying across the keyboard. The image captures the focused intensity of a gamer fully immersed in their digital world.
Prompt
style-aesthetic Gritty realism: Focused, competitive ; A gamer, their eyes glued to the screen, their fingers flying across the keyboard; close-up; Gaming; a dimly lit room filled with computer monitors and gaming peripherals; cinematic
Characteristic
Shot : A young man wearing headphones is sitting at a computer desk, typing on a keyboard, in a dark room lit by neon lights.
Aesthetic Score : 0.6
Mood : focused, intense, determined
Quality
Entropy : 6.60
Noise : 51
Prompt Clip Score : 0.30
AI Evaluation
Likelihood of AI : 0.10
Image errors : The image appears to be slightly over-saturated, and the colors are slightly too intense. There is some noise in the image, particularly in the shadows.
Lost in the City’s Shadow
A solitary figure walks through the deserted streets, his suitcase a silent companion. The towering buildings loom above, casting long shadows that amplify the sense of loneliness and introspection. The man’s retreating back leaves a trail of mystery, inviting the viewer to ponder his story.
Prompt
style-aesthetic Gritty realism: Lonely, introspective ; A lone traveler, their suitcase in hand, walking down a deserted street; medium shot; Tourism; a city skyline at night, with neon lights reflecting off the wet pavement; cinematic
Characteristic
Shot : A lone man walks down a city street at night with a suitcase, with tall buildings in the background
Aesthetic Score : 0.7
Mood : melancholy, lonely, contemplative
Quality
Entropy : 6.34
Noise : 90
Prompt Clip Score : 0.37
AI Evaluation
Likelihood of AI : 0.70
Image errors : The street reflections are slightly blurry and the man’s right foot is slightly deformed, possibly AI generated.
Conclusion
The results show 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 0.48, which is slightly below the “good” range of 0.5 to 0.75. This suggests that the model’s ability to accurately interpret and reproduce camera positions in the generated images is decent, but could be improved.
- Shot Analysis: The model scored 0.545, which falls within the “good” range. This indicates that the model is generally able to understand the scene described in the prompt and create images that reflect the intended shot type.
- Aesthetic Analysis: The model scored 0.06, which is significantly lower than the “very good” range of -0.2 to 0.1. This suggests that the generated images did not closely match the expected aesthetic style.
Overall, the model demonstrates a good understanding of camera positions and shot types, 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://deepmind.google/technologies/imagen-3/