AI Struggles to Capture the 'Dramatic' Aesthetic with Freepik
- 9 minutes read - 1846 wordsTable of Contents
The ‘dramatic’ aesthetic is a powerful tool in visual storytelling. It uses elements like strong lighting, dramatic composition, and evocative colors to create a sense of tension, excitement, or even fear. This style is often used in film, photography, and even video games to enhance the emotional impact of a scene. But can AI truly understand and replicate this style? In this blog post, we explore the results of a generative AI model tasked with creating images in a ‘dramatic’ style. We analyze the model’s performance and discuss the challenges of teaching AI to understand and replicate artistic styles.
Created with: freepik
Silhouetted Solitude: A Moment of Contemplation at Sunset
A lone figure stands on a mountain peak, silhouetted against a breathtaking sunset. The vastness of the valley and distant mountains create a sense of peace and contemplation, emphasizing the smallness of the human figure in the face of nature’s grandeur.
Prompt
Expressionist: Epic, determined ; A lone figure, silhouetted against a blazing sunset; wide shot; Heroism; A vast, desolate landscape with towering mountains in the distance; cinematic
Characteristic
Shot : A solitary figure stands on a mountaintop, looking out at a vast valley and mountain range at sunset. The sky is ablaze with warm hues of orange and red, casting long shadows across the landscape.
Aesthetic Score : 0.7
Mood : tranquil, serene, contemplative
Quality
Entropy : 6.56
Noise : 49
Prompt Clip Score : 0.33
AI Evaluation
Likelihood of AI : 0.80
Image errors : The image has a slightly artificial or overly-processed look, particularly in the sky and mountains. The texture of the clouds and the light sources appear unnatural.
Lost in the Mist: A Path Through a Haunting Forest
A winding stone path disappears into a thick, swirling fog, leading through a forest of bare trees and moss-covered ground. The scene evokes a sense of mystery and melancholy, inviting you to explore the unknown.
Prompt
Expressionist: Mysterious, suspenseful ; A winding, cobblestone path disappearing into a dense, swirling fog; low-angle shot; Adventure; A dark, foreboding forest with gnarled trees and flickering shadows; cinematic
Characteristic
Shot : A winding stone path leading through a misty forest. The path leads up a slight incline and disappears into the fog, creating a sense of mystery and intrigue.
Aesthetic Score : 0.8
Mood : mysterious, eerie, haunting
Quality
Entropy : 6.76
Noise : 96
Prompt Clip Score : 0.32
AI Evaluation
Likelihood of AI : 0.20
Image errors : No visible artifacts or errors.
Lost in the Neon Glow: A Cyberpunk Focus
A young woman, clad in a jacket with glowing lines, sits in a dimly lit cyberpunk space, her gaze fixed on a screen. The neon lights and futuristic decor create a captivating atmosphere, highlighting her intense concentration.
Prompt
Expressionist: Intense, futuristic ; A pixelated character, illuminated by the glow of a computer screen; close-up; Gaming; A chaotic, neon-lit cityscape with flashing lights and distorted reflections; cinematic
Characteristic
Shot : A young woman with short dark hair and a futuristic jacket is sitting in front of a computer. She is typing on the keyboard and looking intently at the screen. The background is a blurred cityscape with neon lights and a cyberpunk aesthetic.
Aesthetic Score : 0.7
Mood : cyberpunk, futuristic, focused
Quality
Entropy : 6.49
Noise : 72
Prompt Clip Score : 0.32
AI Evaluation
Likelihood of AI : 0.90
Image errors : The image has some minor artifacts around the edges of the subject’s hair and clothing. There are also some minor errors in the rendering of the light on the subject’s face and hair.
Golden Hour Majesty: A Cathedral Bathed in Sunset Glory
From above, a grand cathedral stands bathed in the warm glow of the setting sun. A sea of people gathers in the square below, creating a scene of serene beauty and majestic scale.
Prompt
Expressionist: Awe-inspiring, spiritual ; A towering, ancient cathedral bathed in the golden light of dawn; high-angle shot; Tourism; A bustling, crowded marketplace with vibrant colors and exotic goods; cinematic
Characteristic
Shot : An aerial view of a large cathedral with a crowd of people in the foreground. The sun is setting, casting a warm glow on the scene.
Aesthetic Score : 0.8
Mood : tranquil, majestic, awe-inspiring
Quality
Entropy : 6.71
Noise : 108
Prompt Clip Score : 0.32
AI Evaluation
Likelihood of AI : 0.20
Image errors : No noticeable errors
A Whirlwind Through Color: Canyon Train Ride
Experience the thrill of a speeding train journey through a vibrant canyon, captured in a dynamic shot that emphasizes the motion and excitement of the moment. The colorful rock formations and the perspective from above the train create a sense of adventure and wonder.
Prompt
Expressionist: Surreal, disorienting ; A train speeding through a surreal, dreamlike landscape; long shot; Travel; A distorted, abstract landscape with swirling colors and shifting shapes; cinematic
Characteristic
Shot : A train travelling through a canyon with colorful rock formations.
Aesthetic Score : 0.7
Mood : dramatic, adventurous, surreal
Quality
Entropy : 6.72
Noise : 101
Prompt Clip Score : 0.32
AI Evaluation
Likelihood of AI : 0.90
Image errors : The motion blur is slightly overdone, making the image look a bit artificial. The colors in the rock formations are unrealistic.
Secrets in the Shadows: A Family Dinner Filled with Tension
A dimly lit room, a floral wallpaper, and a family gathered around a candlelit table. The low lighting and their expressions create an atmosphere of suspense and unspoken secrets. What is happening in this intimate, yet tense moment?
Prompt
Expressionist: Intimate, melancholic ; A family huddled together in a dimly lit room, their faces illuminated by flickering candlelight; close-up; Family; A cramped, cluttered room with faded wallpaper and worn furniture; cinematic
Characteristic
Shot : A family of four sits at a table lit by candles in a dimly lit room. The room appears to be an old-fashioned dining room with wood paneling and wallpaper. The family members have a serious, somber expression.
Aesthetic Score : 0.7
Mood : serious, somber, mysterious
Quality
Entropy : 6.71
Noise : 72
Prompt Clip Score : 0.29
AI Evaluation
Likelihood of AI : 0.30
Image errors : No major errors, except for minor noise in the shadows, especially near the background.
Solitude Amidst the Storm
A solitary figure stands defiant against the raw power of nature, silhouetted against a tempestuous sky and crashing waves. The scene evokes a sense of dramatic tension and melancholic beauty, highlighting the fragility of life in the face of overwhelming forces.
Prompt
Expressionist: Dramatic, contemplative ; A lone figure standing on a precipice, gazing out at a stormy sea; medium shot; Heroism; A dramatic, stormy seascape with crashing waves and swirling clouds; cinematic
Characteristic
Shot : A lone figure stands on a cliff overlooking a stormy sea. Large waves crash against the rocks, while a dark, stormy sky looms overhead.
Aesthetic Score : 0.8
Mood : dramatic, intense, foreboding
Quality
Entropy : 6.59
Noise : 67
Prompt Clip Score : 0.33
AI Evaluation
Likelihood of AI : 0.30
Image errors : The image has slight artifacts in the clouds and water. The figure is slightly over-exposed.
Silhouettes in the Mist: A Mysterious Alleyway Unveiled
Two figures, shrouded in shadow, navigate a narrow cobblestone alley bathed in the flickering glow of gaslights. Intricate carvings adorn the walls, adding to the sense of mystery and intrigue. The scene evokes a mood of suspense and atmosphere, leaving the viewer captivated by the unknown.
Prompt
Expressionist: Confusing, suspenseful ; A labyrinthine maze of twisting corridors and flickering lights; low-angle shot; Adventure; A dark, claustrophobic dungeon with dripping water and eerie shadows; cinematic
Characteristic
Shot : Two figures walk towards the end of a narrow, dimly lit, cobblestone alleyway, the walls are textured and worn, with an ornate design, the alleyway is wet and foggy.
Aesthetic Score : 0.7
Mood : mysterious, eerie, atmospheric
Quality
Entropy : 6.40
Noise : 93
Prompt Clip Score : 0.28
AI Evaluation
Likelihood of AI : 0.80
Image errors : No visible artifacts or errors
Lost in the Digital Dawn: A Woman Embraces the Future
A woman, captivated by the vibrant, futuristic cityscape, stands before a dazzling display of light and color. The scene evokes a sense of wonder and exploration, hinting at the boundless possibilities of the digital realm.
Prompt
Expressionist: Immersive, futuristic ; A virtual reality headset, displaying a vibrant, pixelated world; close-up; Gaming; A distorted, abstract landscape with swirling colors and shifting shapes; cinematic
Characteristic
Shot : A young woman wearing a VR headset is standing in a futuristic cityscape. The scene is filled with vibrant colors and neon lights.
Aesthetic Score : 0.7
Mood : futuristic, dreamy, hopeful
Quality
Entropy : 6.88
Noise : 88
Prompt Clip Score : 0.32
AI Evaluation
Likelihood of AI : 0.90
Image errors : There are some artifacts in the background, and the colors are slightly oversaturated.
Lost in the City’s Pulse
A bustling city street, teeming with life, captures the anonymity of urban existence. The blurred figures of the crowd create a sense of motion and emphasize the vastness of the city, leaving the individual feeling small and insignificant.
Prompt
Expressionist: Chaotic, overwhelming ; A bustling, crowded street scene, with people rushing past in a blur; long shot; Tourism; A distorted, abstract cityscape with exaggerated buildings and swirling colors; cinematic
Characteristic
Shot : A crowded street in a city, with people walking in both directions. The buildings on either side of the street are tall and have many windows. The sky is cloudy, and there is a lot of light reflecting off the buildings.
Aesthetic Score : 0.4
Mood : busy, urban, crowded
Quality
Entropy : 6.76
Noise : 93
Prompt Clip Score : 0.28
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image has a lot of noise and grain, particularly in the shadows. The colors are also a bit washed out and the image is generally quite blurry, especially the people in the distance.
Conclusion
The results show that the generative AI model performed well in understanding the scene and camera position, but struggled with the aesthetic style. 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 different from what was requested in the prompt.
- Shot Analysis: The model scored 0.6, which is considered good. This indicates the generated image’s shot composition was fairly close to what was described in the prompt.
- Aesthetic Analysis: The model scored 0.04, which is considered pretty bad. This means the generated image’s aesthetic style deviated significantly from the desired style.
Overall, the model seems to be better at understanding the scene and camera position than it is at 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://www.freepik.com