AI's Artistic Struggle: Capturing the 'Dramatic' Aesthetic with Dall-e-3
- 9 minutes read - 1809 wordsTable of Contents
The ‘dramatic’ aesthetic is a powerful tool in visual storytelling, evoking strong emotions and creating a sense of grandeur. It often involves striking contrasts, dramatic lighting, and a sense of heightened tension. This style is commonly used in film, photography, and even graphic design to create impactful visuals. However, replicating this aesthetic in AI-generated images presents unique challenges. This blog post explores the results of a generative AI model tasked with creating images based on the ‘dramatic’ aesthetic, highlighting its strengths and weaknesses.
Created with: dall-e-3
Silhouetted Against the Setting Sun: A Moment of Contemplation
A lone figure, silhouetted against a fiery sunset, holds a rifle. The dramatic lighting and vast landscape evoke a sense of melancholy and contemplation, leaving the viewer to ponder the figure’s story and the weight of their solitude.
Prompt
Avant-garde: Epic, melancholic ; A lone figure, silhouetted against a blazing sunset; long shot; Heroism; A vast, desolate landscape; cinematic
Characteristic
Shot : A lone figure stands silhouetted against a fiery sunset with a large sun in the background. The figure appears to be holding a weapon. The scene is set in a desolate, grassy landscape.
Aesthetic Score : 0.7
Mood : epic, dramatic, melancholic
Quality
Entropy : 6.25
Noise : 78
Prompt Clip Score : 0.28
AI Evaluation
Likelihood of AI : 0.90
Image errors : No major errors are evident in the image, though the rendering of the grass and the sky could be more detailed, especially considering the quality of the rest of the image.
Reaching for the Cosmic Unknown
A hand stretches towards a swirling vortex in a mesmerizing cosmic landscape. Geometric shapes and glowing lights dance amidst the stars, creating an ethereal and futuristic atmosphere. The scene evokes a sense of awe and wonder, hinting at the power and mystery of the unknown.
Prompt
Avant-garde: Surreal, mysterious ; A hand reaching out from a swirling vortex of light; close-up; Adventure; A kaleidoscope of colors and abstract shapes; cinematic
Characteristic
Shot : A hand reaching up towards a swirling vortex of light and energy in a space-like background
Aesthetic Score : 0.7
Mood : mysterious, cosmic, futuristic
Quality
Entropy : 6.92
Noise : 120
Prompt Clip Score : 0.29
AI Evaluation
Likelihood of AI : 0.90
Image errors : Some minor aliasing artifacts are visible in the background, but the image is generally well-rendered.
A Lone Figure in a Pixelated Metropolis
A solitary figure stands on a platform, silhouetted against a vibrant, neon-lit cityscape. The pixelated aesthetic and high vantage point create a futuristic, cyberpunk atmosphere, emphasizing the themes of isolation and grandeur.
Prompt
Avant-garde: Nostalgic, futuristic ; A pixelated character, rendered in a retro 8-bit style, standing on a precipice overlooking a digital cityscape; medium shot; Gaming; A neon-lit, futuristic cityscape; cinematic
Characteristic
Shot : A lone figure stands on a rooftop overlooking a sprawling futuristic city bathed in neon lights. The city is dominated by a central tower that shoots a beam of light into the sky, creating a dramatic and captivating scene.
Aesthetic Score : 0.7
Mood : futuristic, cyberpunk, awe
Quality
Entropy : 6.80
Noise : 115
Prompt Clip Score : 0.34
AI Evaluation
Likelihood of AI : 0.90
Image errors : The pixelated style can be a bit jarring and the lighting might be too uniform, lacking nuanced shadows.
A Suitcase Full of Memories on a Misty Platform
An old, worn leather suitcase sits alone on a deserted train platform, bathed in a soft, misty light. The train in the background adds a sense of journey and departure, while the empty platform evokes feelings of nostalgia and solitude. The contrasting light and dark elements create a dramatic atmosphere, highlighting the suitcase’s story waiting to be told.
Prompt
Avant-garde: Lonely, evocative ; A single, weathered suitcase, abandoned on a deserted train platform; close-up; Tourism; A misty, atmospheric train station; cinematic
Characteristic
Shot : A vintage suitcase sits on a train platform, with a train departing in the background.
Aesthetic Score : 0.8
Mood : nostalgic, somber, contemplative
Quality
Entropy : 6.32
Noise : 96
Prompt Clip Score : 0.33
AI Evaluation
Likelihood of AI : 0.30
Image errors : No noticeable artifacts or errors
Distorted Reality: A City on the Edge
A surreal cityscape unfolds, its perspective warped and fragmented. People march towards a radiant horizon, their path uncertain. The distorted reality evokes a sense of unease, leaving the viewer questioning their own perception and the path ahead.
Prompt
Avant-garde: Disorienting, dreamlike ; A pair of feet walking on a cracked, abstract pavement; low-angle shot; Travel; A distorted, surreal cityscape; cinematic
Characteristic
Shot : A city street with people walking, the perspective is from the ground looking up, and the image is heavily distorted with a fisheye lens effect
Aesthetic Score : 0.6
Mood : surreal, chaotic, dizzying
Quality
Entropy : 6.83
Noise : 115
Prompt Clip Score : 0.33
AI Evaluation
Likelihood of AI : 0.80
Image errors : The image has a lot of distortion, which makes it difficult to see the details clearly. There are also some artifacts around the edges of the image.
A Candle’s Glow: A Family’s Hope in the Darkness
A poignant image captures a family of five huddled together in a dimly lit room, illuminated by a single candle. Their simple clothing and the intimate setting suggest a shared moment of vulnerability and closeness, offering a glimpse into their resilience and hope amidst hardship.
Prompt
Avant-garde: Intimate, mysterious ; A family gathered around a flickering candle, their faces obscured by shadows; close-up; Family; A dimly lit, antique room; cinematic
Characteristic
Shot : A family of five is gathered around a table in a dimly lit room. A single candle illuminates their faces. The scene evokes a sense of intimacy and warmth.
Aesthetic Score : 0.8
Mood : intimate, warm, melancholic
Quality
Entropy : 6.30
Noise : 105
Prompt Clip Score : 0.28
AI Evaluation
Likelihood of AI : 0.20
Image errors : No visible errors
A Red Balloon of Hope in a White Wilderness
A lone astronaut, adrift in a stark, white landscape, finds a glimmer of hope in a vibrant red balloon. The balloon, tethered to the astronaut’s hand, floats towards an opening in a row of towering white structures, creating a striking contrast of color and a sense of optimism in this surreal and dreamy scene.
Prompt
Avant-garde: Hopeful, symbolic ; A single, red balloon floating against a stark, white background; close-up; Heroism; A minimalist, abstract setting; cinematic
Characteristic
Shot : A lone figure in a white, minimalist environment, holding a red balloon, walks towards an open doorway.
Aesthetic Score : 0.8
Mood : minimal, hopeful, whimsical
Quality
Entropy : 6.65
Noise : 75
Prompt Clip Score : 0.31
AI Evaluation
Likelihood of AI : 0.90
Image errors : No noticeable image errors.
Retro Gaming with a Shadowy Twist
A dimly lit room, a retro controller, and a shadowy figure lurking in the doorway. This scene evokes a sense of mystery and suspense, with the dramatic use of light and shadow adding to the retro aesthetic.
Prompt
Avant-garde: Nostalgic, introspective ; A hand holding a vintage game controller, the screen reflecting a distorted, pixelated world; close-up; Gaming; A dimly lit, retro-themed room; cinematic
Characteristic
Shot : A person is playing video games, their hands are holding a controller in the foreground. A shadowy figure is visible in the background, and a television set is in the center, showing what appears to be an 8-bit video game.
Aesthetic Score : 0.8
Mood : retro, eerie, suspenseful
Quality
Entropy : 6.67
Noise : 122
Prompt Clip Score : 0.29
AI Evaluation
Likelihood of AI : 0.80
Image errors : The image appears to be of high quality. However, some minor artifacts can be seen in the wood grain.
A Solitary Figure Gazes Upon a Mystical Vortex
A lone figure stands on a mountain peak, dwarfed by a swirling vortex of clouds above. The scene evokes a sense of mystery and awe, with the dramatic effect heightened by the figure’s small scale against the vastness of the sky.
Prompt
Avant-garde: Sublime, awe-inspiring ; A lone figure standing on a mountain peak, their silhouette framed by a swirling vortex of clouds; long shot; Adventure; A dramatic, mountainous landscape; cinematic
Characteristic
Shot : A lone figure stands on a mountain peak, looking up at a swirling cloud formation that fills the sky. The scene is framed by mountains and valleys in the foreground.
Aesthetic Score : 0.7
Mood : dramatic, awe-inspiring, mysterious
Quality
Entropy : 6.48
Noise : 113
Prompt Clip Score : 0.31
AI Evaluation
Likelihood of AI : 0.90
Image errors : The image has some minor artifacts, particularly in the clouds and mountains.
The World in Motion: A Collage of Travel and Urban Chaos
This dynamic and fast-paced collage captures the energy and movement of travel and urban life. With a multitude of small images depicting airplanes, cities, and other travel-related scenes, the image evokes a sense of overwhelming busyness and chaos.
Prompt
Avant-garde: Energetic, disorienting ; A series of fragmented, overlapping images, depicting different aspects of travel and tourism; montage; Tourism; A chaotic, abstract collage; cinematic
Characteristic
Shot : A collage of images featuring planes, airports, and other scenes of travel, all arranged in a grid pattern with an abstract, almost chaotic effect.
Aesthetic Score : 0.4
Mood : dynamic, fast-paced, exciting
Quality
Entropy : 6.91
Noise : 121
Prompt Clip Score : 0.26
AI Evaluation
Likelihood of AI : 0.80
Image errors : There are some visible artifacts and distortions in the image, particularly in the areas with high contrast and motion blur.
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 0.4, which is below the “good” range of 0.5 to 0.75. This suggests that the model didn’t perfectly capture the intended camera positions described in the prompt.
- Shot Analysis: The model scored 0.61, which falls within the “good” range. This indicates that the model was able to understand the scene described in the prompt and create a shot that was relatively close to the intended one.
- Aesthetic Analysis: The model scored 0.15, which is significantly higher than the “very good” range of -0.2 to 0.1. This suggests that the generated image’s aesthetic deviated significantly from the expected aesthetic described in the prompt.
Overall, the model shows promise in understanding scene composition and camera positioning, 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://openai.com/index/dall-e-3/