AI Captures the Essence of Dramatic Scenes, But Struggles with the 'Feel' with Scenario
- 10 minutes read - 2043 words
Table of Contents
The dramatic aesthetic is a powerful tool in storytelling, evoking strong emotions and immersing viewers in the narrative. It often involves stark contrasts, dramatic lighting, and a focus on the emotional impact of the scene. This style is commonly used in film, photography, and even video games to create a sense of grandeur, tension, or pathos. However, replicating this aesthetic in AI-generated images presents a unique challenge, as it requires the model to understand not just the visual elements of the scene, but also the underlying emotional intent.
Created with: scenario
A Soldier’s Silhouette Against the Setting Sun
A female soldier kneels in the desolate desert landscape, the setting sun casting a warm glow on her silhouette. A distant tank stands as a reminder of the battle that has passed, leaving a sense of melancholy and solitude in its wake.
Prompt
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 female soldier is kneeling in a war-torn landscape, looking towards a tank in the distance. The setting sun casts a warm glow on the scene, highlighting the soldier’s silhouette and the dust and debris surrounding them.
Aesthetic Score : 0.7
Mood : melancholy, pensive, dramatic
Quality
Entropy : 6.53
Noise : 95
Prompt Clip Score : 0.32
AI Evaluation
Likelihood of AI : 0.70
Image errors : No major errors, but the image appears to have been slightly oversharpened, which can make details appear harsh. The edges of the image also have a subtle halo effect.
Into the Unknown: A Woman’s Journey Begins
A determined woman, clad in gear for adventure, gazes into the dense jungle. The play of light and shadow adds a sense of mystery to her mission, hinting at the challenges and possibilities that lie ahead. Is she on a quest for discovery, or facing a perilous unknown? This image evokes a sense of hope and adventure, leaving the viewer eager to uncover the story behind her gaze.
Prompt
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 woman wearing a helmet and goggles looks off to the side, likely at a staircase into the forest. The lighting is dim and the image is in black and white.
Aesthetic Score : 0.7
Mood : mysterious, pensive, adventurous
Quality
Entropy : 6.75
Noise : 114
Prompt Clip Score : 0.30
AI Evaluation
Likelihood of AI : 0.60
Image errors : The image appears to be slightly blurry and the edges are not very sharp.
Late Night Gaming: A Cozy Escape
A young woman, lost in the world of a video game, sits surrounded by the remnants of a late-night gaming session. The warm lighting and cluttered background create a sense of intimacy and isolation, highlighting the comfort and focus of her gaming experience.
Prompt
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 young woman is sitting on the floor in front of a computer screen, playing a video game with a controller in her hand. She is surrounded by pizza boxes and other food items. The room is dimly lit and there is a warm glow coming from the computer screen.
Aesthetic Score : 0.7
Mood : cozy, relaxed, playful
Quality
Entropy : 6.79
Noise : 99
Prompt Clip Score : 0.35
AI Evaluation
Likelihood of AI : 0.90
Image errors : The image has some minor artifacts and errors, particularly in the areas of the pizza, the controller, and the woman’s hair. There are also some areas where the colors are not quite right.
Lost in the Desert’s Embrace: A Moment of Hope Amidst Loneliness
A young woman, her backpack a symbol of journey and uncertainty, stands before a neon-lit diner in the heart of a desolate desert. The fading light of dusk casts long shadows, creating an atmosphere of mystery and intrigue. Her solitary figure against the vast, empty landscape evokes a sense of isolation and longing, yet a flicker of hope shines through, hinting at a story waiting to unfold.
Prompt
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 woman stands in front of a diner with neon sign in the desert at dusk.
Aesthetic Score : 0.7
Mood : lonely, contemplative, nostalgic
Quality
Entropy : 6.70
Noise : 94
Prompt Clip Score : 0.35
AI Evaluation
Likelihood of AI : 0.20
Image errors : There are no visible artifacts or errors in the image.
Warmth and Intimacy on a Train Journey
A group of people, including children, share a moment of closeness on a train carriage bathed in warm light. The scene evokes a sense of nostalgia and intimacy, capturing the quiet beauty of shared travel.
Prompt
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 family sits on a train, likely a vintage one, with windows looking out to a countryside landscape
Aesthetic Score : 0.75
Mood : nostalgic, cozy, familial
Quality
Entropy : 6.51
Noise : 109
Prompt Clip Score : 0.34
AI Evaluation
Likelihood of AI : 0.10
Image errors : The painting has some obvious brushstrokes, especially in the woman’s hair and the background, but these are artistic choices and may not be considered errors. The shadows are well done. There is no technical error in the image, the style is consistent and well-executed
A Dreamy Glance Upward: A Young Girl Finds Wonder in the City
A young girl, her brown hair blending with the autumnal hues of her coat, stands on a bustling city street. Her gaze is fixed upwards, drawn to the towering buildings that pierce the bright blue sky. The scene evokes a sense of dreamy hope and nostalgia, capturing the awe and wonder that can be found in the everyday.
Prompt
Gritty realism: Awe, curiosity ; eyes wide with wonder, staring up at a towering skyscraper; low angle shot; Family; a bustling city street filled with people and traffic; cinematic
Characteristic
Shot : A young girl with long brown hair is looking up at a tall building in a busy city street. The city is full of people and shops. The girl is wearing a brown jacket and a white fur collar. The building is a mix of old and new architecture.
Aesthetic Score : 0.7
Mood : dreamy, nostalgic, hopeful
Quality
Entropy : 6.72
Noise : 110
Prompt Clip Score : 0.30
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image has some minor artifacts, particularly in the background, that detract slightly from the overall quality.
Eyes on the Fire: A Firefighter’s Unwavering Resolve
A close-up portrait captures the intensity of a female firefighter, her gaze fixed on the horizon amidst a backdrop of smoke. The image exudes a sense of urgency and professionalism, highlighting the unwavering determination of those who face danger head-on.
Prompt
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 portrait of a young woman wearing a firefighter helmet and jacket, with a blurred background of smoke and fire.
Aesthetic Score : 0.7
Mood : serious, intense, powerful
Quality
Entropy : 6.74
Noise : 96
Prompt Clip Score : 0.30
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image is slightly overexposed, with some areas of the background being blown out.
Epic Mountain Adventure: Hikers Conquer Snowy Peaks
Witness the breathtaking beauty of towering snow-capped mountains as a group of hikers navigate a winding path. The vastness of the landscape and the small scale of the hikers create a sense of awe and adventure. This serene scene captures the essence of exploration and the majesty of nature.
Prompt
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 group of hikers are trekking through a snowy mountain valley, surrounded by towering snow-capped peaks and a winding glacier. The sun is shining brightly, illuminating the snow and ice.
Aesthetic Score : 0.8
Mood : serene, adventurous, vast
Quality
Entropy : 6.38
Noise : 101
Prompt Clip Score : 0.32
AI Evaluation
Likelihood of AI : 0.80
Image errors : No obvious artifacts or errors detected. The image appears to be of high quality.
Lost in Thought, Fueled by Code
A young woman, headphones on, sits at her computer, her gaze fixed on something unseen. The soft glow of the monitor casts an air of mystery and anticipation, hinting at a moment of deep focus and creative exploration.
Prompt
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 woman wearing headphones is sitting in front of a computer, her gaze is directed away from the screen, perhaps to the side. There are two computer monitors behind her, with one displaying a dynamic, colorful background and the other being a blur.
Aesthetic Score : 0.7
Mood : focused, contemplative, introspective
Quality
Entropy : 6.62
Noise : 88
Prompt Clip Score : 0.30
AI Evaluation
Likelihood of AI : 0.70
Image errors : The image quality is good, but there is a slight blurriness around the edges of the subject. It’s not very noticeable, but it could be improved by sharpening the image slightly.
Lost in the Neon Rain
A solitary figure walks through a rain-soaked city, bathed in the glow of neon signs. The image evokes a sense of melancholy and mystery, capturing the loneliness of urban life.
Prompt
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 woman with a suitcase walks down a rainy street in a city. The buildings are tall and the street is wet and reflective. There are neon lights on the buildings and a sense of solitude to the woman walking
Aesthetic Score : 0.7
Mood : melancholy, lonely, city
Quality
Entropy : 6.74
Noise : 121
Prompt Clip Score : 0.35
AI Evaluation
Likelihood of AI : 0.80
Image errors : Slight banding in the sky and a blurry texture to the reflection on the wet road.
Conclusion
The results show that the generative AI model performed well in terms of understanding the scene and camera position, but struggled with the aesthetic. Here’s a breakdown:
- Camera Position: The model scored 0.45, which is considered okay. This means the generated image’s camera position was somewhat similar to what was requested in the prompt.
- Shot Analysis: The model scored 0.59, which is considered good. This indicates the model successfully captured the scene described in the prompt.
- Aesthetic Analysis: The model scored -0.03, which is considered very good. This means the generated image’s aesthetic closely matched the expected aesthetic.
Overall, the model demonstrates a good understanding of the scene and camera position, but could benefit from further training to improve its ability to generate images with 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://www.scenario.com