AI's Artistic Struggle: Capturing the Dramatic Aesthetic with Titan-g1
- 9 minutes read - 1893 wordsTable of Contents
The dramatic aesthetic, characterized by its use of strong contrasts, dramatic lighting, and evocative compositions, is a powerful tool in visual storytelling. It’s often used to create a sense of tension, mystery, or grandeur. But can AI truly capture this complex aesthetic? In this blog post, we explore the challenges and successes of using AI to generate images with a dramatic feel. We’ll analyze the results of a generative AI model, examining its ability to understand camera positions, scene composition, and overall style. Through this analysis, we’ll gain insights into the potential and limitations of AI in creating visually compelling and emotionally resonant images.
Created with: titan-g1
Silhouettes of Wonder: Two Figures Gaze Upon a Starry Cityscape
A tranquil scene unfolds as two figures stand silhouetted against a breathtaking starry night. Their presence on a rocky outcrop overlooking distant city lights evokes a sense of awe and contemplation, capturing the serenity of the moment.
Prompt
Gritty realism: Melancholy, determined ; A lone figure, silhouetted against the rising moon, stands atop a towering mountain peak; wide shot; a vast, star-strewn sky stretches out before them, dotted with the twinkling lights of distant cities.; cinematic
Characteristic
Shot : A night scene with a starry sky, a distant city illuminated with lights, and two silhouetted figures standing on a rock outcrop.
Aesthetic Score : 0.8
Mood : serene, contemplative, vast
Quality
Entropy : 6.34
Noise : 117
Prompt Clip Score : 0.25
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image is slightly blurry, possibly due to camera shake.
Lost in Time: Exploring the Ancient Ruins
A lone adventurer stands before a majestic, overgrown temple, its ancient stones whispering tales of forgotten civilizations. The low angle shot emphasizes the temple’s imposing scale, inviting viewers to imagine the mysteries hidden within its crumbling walls.
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 man with a backpack stands in front of an ancient stone temple overgrown with vegetation
Aesthetic Score : 0.7
Mood : mysterious, adventurous, historical
Quality
Entropy : 6.93
Noise : 105
Prompt Clip Score : 0.24
AI Evaluation
Likelihood of AI : 0.20
Image errors : No noticeable image errors.
Ready to Level Up: Pizza, Soda, and Game On!
A casual gaming setup with a pizza box, soda, and a controller in hand. The anticipation is palpable as the player prepares to dive into the game.
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 person is holding a gaming controller, with a box of pizza and a can of drink in the background. The lighting is dark and moody.
Aesthetic Score : 0.6
Mood : dark, moody, intense
Quality
Entropy : 6.66
Noise : 101
Prompt Clip Score : 0.31
AI Evaluation
Likelihood of AI : 0.20
Image errors : Some slight blurriness around the edges of the image.
Lost in the Desert Glow
A solitary figure stands beneath a desert canopy, bathed in the warm hues of sunset. The neon glow of a distant restaurant sign casts a melancholic spell, hinting at a story of longing and isolation.
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 figure stands in front of a building with a neon sign, looking away from the camera. The scene is set in a deserted landscape with a vast, open sky.
Aesthetic Score : 0.6
Mood : melancholy, lonely, nostalgic
Quality
Entropy : 6.53
Noise : 96
Prompt Clip Score : 0.29
AI Evaluation
Likelihood of AI : 0.10
Image errors : The image has a slight grainy texture, which could be due to the film used or the way it was processed. There are also some minor artifacts, particularly in the sky.
In the Shadow of the Train: A Family’s Silent Journey
A single lightbulb casts an ethereal glow on a family huddled together in a train car. The darkness outside the window and the textured metal frame create a sense of isolation and mystery, hinting at a story waiting to unfold.
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 is looking out of a train window with a dim light bulb in the foreground.
Aesthetic Score : 0.7
Mood : intimate, nostalgic, hopeful
Quality
Entropy : 6.58
Noise : 109
Prompt Clip Score : 0.31
AI Evaluation
Likelihood of AI : 0.10
Image errors : Slight noise and grain are visible in the image, especially in the darker areas. This could be a result of low light conditions or post-processing.
A City of Dreams: A Boy’s Curious Gaze
A young boy, his eyes filled with wonder, looks up at a towering city building. The image captures the innocence and hope of youth, as he explores the possibilities that lie ahead.
Prompt
Gritty realism: Awe, curiosity ; A young boy, his 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 boy, looking up in awe, stands on a city street, his gaze directed towards tall buildings, creating a sense of wonder and exploration.
Aesthetic Score : 0.6
Mood : curious, hopeful, urban
Quality
Entropy : 6.91
Noise : 99
Prompt Clip Score : 0.31
AI Evaluation
Likelihood of AI : 0.30
Image errors : No visible artifacts or errors in the image.
A Lone Climber Conquers the Sunset Peak
Witness the breathtaking beauty of a lone climber ascending a snow-capped mountain peak as the sun sets, casting a warm glow on the scene. The climber’s small figure against the massive mountain creates a sense of awe and adventure, while the soft blue sky and wispy clouds tinged with pink and orange evoke a feeling of serenity and inspiration.
Prompt
Gritty realism: Focused, determined ; silhouetted against the setting sun, clinging precariously to a rock face; close-up; Determination; a towering, snow-capped peak with clouds swirling around it.; cinematic
Characteristic
Shot : A lone climber ascends a sheer rock face, dwarfed by a towering mountain peak with a snow-capped summit. The sun casts a warm glow on the rock, creating a dramatic contrast with the dark silhouette of the climber.
Aesthetic Score : 0.7
Mood : dramatic, adventurous, awe-inspiring
Quality
Entropy : 6.52
Noise : 105
Prompt Clip Score : 0.25
AI Evaluation
Likelihood of AI : 0.10
Image errors : None
Conquering the Peaks: Hikers Embrace the Majestic Snowy Landscape
A breathtaking scene unfolds as four hikers navigate a snowy mountain range, with a towering peak dominating the background. The contrasting colors of the snow and mountains create a sense of depth and scale, while the hikers add a touch of human presence and adventure. This inspiring image captures the essence of exploration and the beauty of nature’s grandeur.
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 : Four hikers are climbing a snowy mountain. The hikers are wearing winter gear and carrying backpacks. The mountain is in the background, and the snow is in the foreground.
Aesthetic Score : 0.7
Mood : adventurous, determined, hopeful
Quality
Entropy : 6.77
Noise : 105
Prompt Clip Score : 0.26
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image appears to be somewhat overexposed, and there is a slight amount of noise present in the snow.
Immersed in the Game: A Gamer’s World Lit by Neon
A captivating scene of a gamer engrossed in their game, bathed in vibrant blue and purple lighting. The intense focus and futuristic aesthetic create a sense of drama and immersion, highlighting the player’s skillful movements on the keyboard.
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 person is gaming at their computer, their hands are on the keyboard.
Aesthetic Score : 0.6
Mood : focused, intense, techy
Quality
Entropy : 6.77
Noise : 106
Prompt Clip Score : 0.25
AI Evaluation
Likelihood of AI : 0.10
Image errors : There are no visible errors in the image.
Lost in the City Rain
A solitary figure, suitcase in hand, navigates a rain-slicked city street at night. The melancholic atmosphere and reflective surfaces evoke a sense of loneliness and introspection.
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 lone man walks down a rainy city street at night, pulling a suitcase behind him. The street is illuminated by streetlights and neon signs, creating a sense of urban loneliness and melancholy.
Aesthetic Score : 0.6
Mood : melancholy, lonely, urban
Quality
Entropy : 6.65
Noise : 109
Prompt Clip Score : 0.30
AI Evaluation
Likelihood of AI : 0.30
Image errors : There are some minor artifacts visible in the image, particularly in the background, due to over-sharpening. The colors are a bit too saturated.
Conclusion
The results indicate that the generative AI model performed well in terms of understanding camera positions and scene composition, but struggled with achieving the desired aesthetic. Here’s a breakdown:
- Camera Position: The model scored a 0.45, which falls 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 a 0.54, also falling below the “good” range. This indicates that the model had some difficulty understanding and translating the scene description from the prompt into the generated image.
- Aesthetic Analysis: The model scored a 0.08, which is significantly higher than the “very good” range of -0.2 to 0.1. This suggests a significant difference between the expected aesthetic and the actual aesthetic of the generated image. The model likely produced an image that didn’t match the desired style or visual feel.
Overall, the model shows promise in understanding camera positions and scene composition, but needs improvement in capturing the intended 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://docs.aws.amazon.com/bedrock/latest/userguide/titan-image-models.html