AI's Artistic Journey: Capturing the Essence of Style with Leonardo-ai
- 9 minutes read - 1818 wordsTable of Contents
The world of AI is rapidly evolving, with advancements in image generation pushing the boundaries of creative expression. One intriguing area of exploration is the ability of AI to capture and recreate specific aesthetic styles. This blog post examines a case study where a generative AI model was tasked with generating images based on a set of prompts, each specifying a particular scene, camera position, and desired aesthetic. The results offer valuable insights into the current capabilities and limitations of AI in understanding and replicating artistic vision.
Created with: leonardo-ai
Silhouetted Solitude at Sunset
A lone figure, cloaked in mystery, stands on a rocky precipice, gazing out at a city bathed in the warm glow of a setting sun. The dramatic silhouette against the orange sky evokes a sense of melancholy and contemplation, leaving the viewer to ponder the figure’s thoughts and the story behind their solitary moment.
Prompt
Postmodern: Epic, melancholic ; A lone figure, silhouetted against a blazing sunset; wide shot; Heroism; A vast, desolate landscape with a crumbling cityscape in the distance; cinematic
Characteristic
Shot : A lone figure stands in the foreground, silhouetted against a fiery sunset over a cityscape.
Aesthetic Score : 0.7
Mood : melancholy, contemplative, hopeful
Quality
Entropy : 6.04
Noise : 74
Prompt Clip Score : 0.34
AI Evaluation
Likelihood of AI : 0.20
Image errors : No visible errors.
Nostalgia in Pixels: A Vintage Gaming Setup
Step back in time with this nostalgic scene featuring a vintage television playing an old video game. The hand on the control panel, the retro buttons, and the wooden table all contribute to a sense of bygone days. This image captures the essence of retro tech and the enduring appeal of classic gaming.
Prompt
Postmodern: Surreal, playful ; A hand reaching out from a pixelated, digital world, grasping at a real-world object; close-up; Gaming; A cluttered desk with a gaming console and controllers; cinematic
Characteristic
Shot : A close-up shot of a person’s hand interacting with a control panel, in front of an old-school CRT monitor displaying a video game, likely a retro arcade game.
Aesthetic Score : 0.7
Mood : retro, nostalgic, focused
Quality
Entropy : 6.55
Noise : 95
Prompt Clip Score : 0.28
AI Evaluation
Likelihood of AI : 0.10
Image errors : No notable errors.
Lost in the City: A Couple’s Mysterious Encounter
A couple stands amidst the bustling city streets, their serious expressions and blurred surroundings hinting at a hidden story. The contrasting colors of their clothing add to the intrigue, leaving you wondering what secrets they hold.
Prompt
Postmodern: Ironic, detached ; A family of four, their faces obscured by oversized sunglasses, standing in front of a famous landmark; medium shot; Tourism; A bustling tourist destination with crowds and souvenir shops; cinematic
Characteristic
Shot : A couple stands in a European city square, likely a tourist destination, with a blurry background of people and a bus. There is a tall building in the background, suggesting a busy, urban environment.
Aesthetic Score : 0.6
Mood : casual, summery, mysterious
Quality
Entropy : 6.82
Noise : 101
Prompt Clip Score : 0.30
AI Evaluation
Likelihood of AI : 0.30
Image errors : The image is slightly overexposed, causing some highlights to be blown out and the colors to be less saturated. The background appears somewhat blurry and lacking in detail. There are some slight artifacts present in the image, particularly around the edges of objects.
Timeworn Treasures: A Room Frozen in Time
Step into a room steeped in nostalgia, where peeling paint and weathered suitcases whisper tales of forgotten journeys. This abandoned space evokes a sense of travel and the passage of time, leaving you to ponder the stories hidden within its dusty corners.
Prompt
Postmodern: Nostalgic, melancholic ; A vintage travel poster, faded and torn, with a romanticized image of a foreign land; close-up; Travel; A dusty, cluttered attic filled with old suitcases and maps; cinematic
Characteristic
Shot : An abandoned room with peeling paint on the walls, cluttered with old suitcases and maps, creating a sense of nostalgia and decay.
Aesthetic Score : 0.7
Mood : nostalgic, melancholic, abandoned
Quality
Entropy : 6.91
Noise : 103
Prompt Clip Score : 0.28
AI Evaluation
Likelihood of AI : 0.20
Image errors : No noticeable artifacts or errors.
Friends Dive into a Neon-Lit VR Arcade
Four friends immerse themselves in a futuristic arcade experience, their VR headsets glowing under vibrant pink and blue neon lights. The scene captures the playful energy and engaging nature of their shared virtual adventure.
Prompt
Postmodern: Energetic, futuristic ; A group of friends, their faces obscured by digital avatars, playing a virtual reality game; medium shot; Gaming; A brightly lit, futuristic arcade with neon lights and holographic displays; cinematic
Characteristic
Shot : Four young adults wearing VR headsets are playing a video game at an arcade. The scene is illuminated by neon lights.
Aesthetic Score : 0.7
Mood : futuristic, playful, energetic
Quality
Entropy : 6.31
Noise : 91
Prompt Clip Score : 0.36
AI Evaluation
Likelihood of AI : 0.10
Image errors : No visible artifacts or errors
Lost in Transit: A Moment of Solitude in a Bustling Airport
A lone traveler navigates the vast, modern airport terminal, their luggage trailing behind. The high ceilings and large windows bathe the space in a play of light and shadow, creating an atmosphere of quiet contemplation amidst the bustling crowds. A sense of travel and anticipation hangs in the air, hinting at the journey ahead.
Prompt
Postmodern: Lonely, alienated ; A lone traveler, their back to the camera, walking through a crowded airport terminal; long shot; Travel; A chaotic airport terminal with people rushing and luggage carts; cinematic
Characteristic
Shot : A man with luggage walks through a large airport terminal with other passengers standing in line
Aesthetic Score : 0.6
Mood : quiet, lonely, anticipation
Quality
Entropy : 6.76
Noise : 111
Prompt Clip Score : 0.28
AI Evaluation
Likelihood of AI : 0.10
Image errors : The image has some slight graininess and the colors are a bit muted.
Family Moments Against a Cityscape
A father stands, gazing out a window at a sprawling city skyline, while his three children sit on the couch, engrossed in something in their hands. The scene evokes a sense of calm and familial connection, juxtaposed against the grandeur of the urban landscape.
Prompt
Postmodern: Reflective, nostalgic ; A family portrait, with each member holding a different, iconic object from their travels; medium shot; Family; A minimalist, modern living room with a large window overlooking a cityscape; cinematic
Characteristic
Shot : A family is sitting on a couch in a living room with a large window overlooking a cityscape. The father is standing and the children are seated.
Aesthetic Score : 0.7
Mood : relaxed, peaceful, cozy
Quality
Entropy : 6.85
Noise : 100
Prompt Clip Score : 0.34
AI Evaluation
Likelihood of AI : 0.20
Image errors : Slight blurriness in some areas, particularly in the foreground.
Lost in the Digital Woods: A Bland Smartphone Snapshot
A hand holds a smartphone displaying a map app, highlighting a location in a blurry, out-of-focus forest. The scene evokes a sense of boredom and blandness, lacking any dramatic effect or visual interest.
Prompt
Postmodern: Intriguing, suspenseful ; A hand holding a smartphone, displaying a map with a pin dropped on a remote, unknown location; close-up; Adventure; A dark, mysterious forest with dense foliage and shadows; cinematic
Characteristic
Shot : A hand holding a smartphone with Google Maps open in a forest. The phone’s screen shows a map with a red pin marking a location.
Aesthetic Score : 0.2
Mood : simple, practical, everyday
Quality
Entropy : 6.61
Noise : 82
Prompt Clip Score : 0.33
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image appears slightly blurry.
Hope Amidst the Ashes: Superhero Stands Tall Over Devastated City
A lone superhero, silhouetted against a backdrop of smoke and destruction, offers a glimmer of hope in a city ravaged by disaster. The dramatic scene evokes a sense of both despair and resilience, leaving viewers wondering what the future holds.
Prompt
Postmodern: Desolate, hopeful ; A superhero, their costume ripped and tattered, standing on a rooftop overlooking a city in chaos; wide shot; Heroism; A dystopian cityscape with crumbling buildings and smoke in the air; cinematic
Characteristic
Shot : A superhero stands on a rooftop overlooking a city in ruins, with smoke billowing in the distance.
Aesthetic Score : 0.7
Mood : dramatic, heroic, somber
Quality
Entropy : 6.87
Noise : 93
Prompt Clip Score : 0.31
AI Evaluation
Likelihood of AI : 0.30
Image errors : The image has some minor artifacts, particularly around the edges of the smoke and the hero’s cape.
Whimsical Robot Captures City’s Attention
A vibrant green, anthropomorphic robot stands out amidst the bustling cityscape, its presence creating a sense of wonder and intrigue. The robot is bathed in light, while the surrounding people are softly blurred, drawing the viewer’s eye to this futuristic marvel.
Prompt
Postmodern: Surreal, humorous ; A vintage video game character, rendered in a hyper-realistic style, standing in a real-world environment; medium shot; Gaming; A bustling city street with people and traffic; cinematic
Characteristic
Shot : A green robot standing in the middle of a busy street in New York City.
Aesthetic Score : 0.7
Mood : futuristic, urban, quirky
Quality
Entropy : 6.70
Noise : 107
Prompt Clip Score : 0.28
AI Evaluation
Likelihood of AI : 0.90
Image errors : The image has some minor artifacts, such as the blurry background and the grainy texture of the robot.
Conclusion
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 0.35, indicating a moderate ability to interpret and implement camera positions from the prompt. This falls short of the “good” range (0.5-0.75) but is not significantly bad.
- Shot Analysis: The model scored 0.57, which falls within the “good” range. This suggests the model was able to understand the scene described in the prompt and translate it into a visually coherent image.
- Aesthetic Analysis: The model scored 0.12, which is significantly lower than the “very good” range (-0.2 to 0.1). This indicates a noticeable difference between the intended aesthetic and the actual aesthetic of the generated image. The model may have struggled to capture the desired mood, style, or visual elements.
Overall, the model shows promise in understanding scene composition and camera positions, but needs improvement in achieving 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://leonardo.ai