Futuristic Visions: Exploring the 'style-aesthetic' in AI-Generated Art with Imagen-v3-fast
- 10 minutes read - 1927 words
Table of Contents
The ‘style-aesthetic’ is a crucial aspect of visual storytelling, defining the overall mood, tone, and visual language of a scene. It’s a challenge for generative AI models, especially when it comes to capturing the essence of futuristic settings. This article explores the ‘style-aesthetic’ challenge, using examples of AI-generated images of futuristic scenes to illustrate the gap between desired and actual aesthetics. We’ll delve into the reasons behind this discrepancy and discuss potential solutions for improving AI’s ability to generate images that accurately reflect the intended aesthetic.
Created with: imagen-v3-fast
A Solitary Journey into the Neon Future
A lone figure walks through a futuristic cityscape, bathed in the glow of neon signs and a hazy blue sky. The image evokes a sense of mystery, isolation, and hopeful anticipation for what lies ahead.
Prompt
style-aesthetic Futuristic: determined, hopeful ; A lone, futuristic hero; wide shot; heroism; a sprawling cityscape with towering skyscrapers and holographic advertisements; cinematic
Characteristic
Shot : A lone figure walks down a futuristic city street. Tall, imposing buildings line the street, with glowing neon signs and advertisements. The sky is hazy and filled with a soft, blue light.
Aesthetic Score : 0.75
Mood : futuristic, solitary, hopeful
Quality
Entropy : 6.41
Noise : 82
Prompt Clip Score : 0.37
AI Evaluation
Likelihood of AI : 0.90
Image errors : Minor inconsistencies in building textures and repeating patterns of neon signs.
Lost in the Cosmic Expanse: A Starship’s Journey
A lone spaceship navigates the vast expanse of a distant galaxy, a brilliant star illuminating its path. The image evokes a sense of mystery, adventure, and the awe-inspiring scale of the universe.
Prompt
style-aesthetic Futuristic: awe-inspiring, adventurous ; A spaceship soaring through a nebula; close-up; adventure; a vast, star-filled space with swirling nebulas and distant galaxies; cinematic
Characteristic
Shot : A spaceship flying through a galaxy, with a bright star in the background. The ship appears to be in the foreground, with the galaxy in the background.
Aesthetic Score : 0.6
Mood : mysterious, futuristic, adventurous
Quality
Entropy : 6.36
Noise : 70
Prompt Clip Score : 0.28
AI Evaluation
Likelihood of AI : 0.90
Image errors : No apparent errors, though some details appear slightly blurry, which is likely due to the 3D rendering.
Unveiling the Future: A Glimpse into a Technological Wonderland
A mysterious figure interacts with a futuristic user interface, hinting at a world of advanced technology and hidden possibilities. The image evokes a sense of wonder and intrigue, leaving viewers eager to explore the secrets it holds.
Prompt
style-aesthetic Futuristic: intense, focused ; A gamer’s hands manipulating a holographic interface; close-up; gaming; a futuristic gaming room with glowing screens and advanced peripherals; cinematic
Characteristic
Shot : A person interacting with a futuristic user interface, possibly a video game or a software program. The interface is displayed on a screen with a futuristic design and the person is interacting with it by pressing keys on the keyboard and pointing their finger at the screen.
Aesthetic Score : 0.6
Mood : futuristic, technological, mysterious
Quality
Entropy : 6.56
Noise : 58
Prompt Clip Score : 0.31
AI Evaluation
Likelihood of AI : 0.70
Image errors : The image has some minor technical errors in the way the light interacts with the person’s hand, making it look slightly unnatural.
A Glimpse into the Future: A City of Wonder and Mystery
This futuristic cityscape, bathed in a warm glow, features sleek, towering buildings and flying vehicles. The perspective creates a sense of awe and scale, hinting at a world of endless possibilities.
Prompt
style-aesthetic Futuristic: exciting, vibrant ; A futuristic city skyline with flying cars and holographic billboards; long shot; tourism; a bustling, vibrant city with futuristic architecture and technology; cinematic
Characteristic
Shot : A futuristic cityscape with tall, sleek buildings, a wide street, and flying vehicles. The scene is lit by a soft, warm glow, creating a sense of mystery and wonder.
Aesthetic Score : 0.7
Mood : futuristic, sleek, mysterious
Quality
Entropy : 6.52
Noise : 79
Prompt Clip Score : 0.32
AI Evaluation
Likelihood of AI : 0.90
Image errors : The image is somewhat blurry and has some artifacts, especially in the buildings and the flying vehicles.
A Glimpse of Tomorrow: Family Embraces the Future on a Futuristic Train
A family of four, radiating joy and anticipation, rides a sleek, brightly lit train, gazing out at a sprawling cityscape. The large windows offer a breathtaking view of the modern metropolis, symbolizing hope and progress. This image captures the essence of a calm, hopeful future, where families embrace new possibilities.
Prompt
style-aesthetic Futuristic: optimistic, hopeful ; A family traveling through a futuristic subway system; medium shot; travel; a sleek, high-speed train with transparent windows showcasing a futuristic cityscape; cinematic
Characteristic
Shot : A family of four is riding a futuristic train, looking out the windows at a cityscape. The train is brightly lit and the windows are large, allowing for a good view of the city. The family is dressed in casual clothing and appears to be enjoying their ride.
Aesthetic Score : 0.6
Mood : calm, hopeful, modern
Quality
Entropy : 6.76
Noise : 71
Prompt Clip Score : 0.36
AI Evaluation
Likelihood of AI : 0.80
Image errors : The image has some minor artifacts, such as the slight blurriness of the windows. However, these are not major issues and do not detract significantly from the overall image quality.
A Family Dinner in a Bioluminescent Wonderland
A family of four enjoys a meal in a futuristic restaurant bathed in the ethereal glow of bioluminescent plants. The scene evokes a sense of wonder and mystery, hinting at a journey to a distant, alien world.
Prompt
style-aesthetic Futuristic: peaceful, serene ; A futuristic family enjoying a meal in a bioluminescent garden; medium shot; family; a lush, bioluminescent garden with glowing plants and futuristic furniture; cinematic
Characteristic
Shot : A family of four is having dinner in a futuristic restaurant surrounded by bioluminescent plants
Aesthetic Score : 0.7
Mood : mysterious, cozy, futuristic
Quality
Entropy : 6.34
Noise : 80
Prompt Clip Score : 0.42
AI Evaluation
Likelihood of AI : 0.90
Image errors : The image has some slight blurring and pixelation, and the lighting is a bit uneven. The plants in the background are not very realistic.
Neon Dreams: A Robotic Dog Runs Through a Foggy Alley
A futuristic scene unfolds in a neon-lit alley, where a robotic dog bounds across cobblestones. The fog adds an eerie touch, and a shadowy figure lurks in the background, hinting at a mysterious story waiting to be told.
Prompt
style-aesthetic Futuristic: Eerie, contemplative ; A sleek, metallic dog bounds across a neon-lit park, its glowing eyes fixated on a holographic ball, a lone figure watching from the shadows.; cinematic
Characteristic
Shot : A robotic dog running on a cobblestone path in a foggy, neon-lit alley. A shadowy figure is in the background.
Aesthetic Score : 0.7
Mood : futuristic, mysterious, eerie
Quality
Entropy : 6.59
Noise : 59
Prompt Clip Score : 0.35
AI Evaluation
Likelihood of AI : 0.95
Image errors : The image has a few minor artifacts, particularly in the fog and the cobblestone path, that could be smoothed out. There is some slight pixelation in the shadow of the figure.
Lost in the Digital Labyrinth
A solitary figure stands dwarfed by towering, luminous screens, their abstract patterns casting a surreal glow on the cityscape. The image evokes a sense of isolation and wonder, prompting contemplation on the vastness and potential impact of the digital world.
Prompt
style-aesthetic Futuristic: educational, nostalgic ; A futuristic cityscape with holographic projections of historical events; long shot; tourism; a bustling city with holographic displays showcasing historical moments; cinematic
Characteristic
Shot : A lone figure stands in a city square at night, surrounded by large, transparent screens displaying abstract patterns and figures. The screens are illuminated with a vibrant blue light, casting a futuristic glow over the scene. The cityscape in the background is visible through the screens, adding depth and scale to the composition.
Aesthetic Score : 0.7
Mood : futuristic, surreal, lonely
Quality
Entropy : 6.63
Noise : 80
Prompt Clip Score : 0.30
AI Evaluation
Likelihood of AI : 0.80
Image errors : The image is slightly blurry, especially in the background, indicating potential noise reduction or compression artifacts. The screens appear to be somewhat unrealistic, lacking the depth and detail of real-world displays.
Awe-Inspiring Journey Through the Cosmos
A futuristic spaceship soars through an alien landscape, casting a dramatic silhouette against the vast, dark sky. Two colossal planets loom in the background, creating a sense of awe and wonder. This mysterious and adventurous scene evokes a sense of exploration and the unknown.
Prompt
style-aesthetic Futuristic: mysterious, adventurous ; A futuristic spaceship landing on a distant planet; wide shot; adventure; a desolate, alien planet with strange landscapes and a futuristic spaceship; cinematic
Characteristic
Shot : A futuristic spaceship flying over an alien landscape with two large planets in the background.
Aesthetic Score : 0.7
Mood : mysterious, futuristic, adventurous
Quality
Entropy : 6.78
Noise : 56
Prompt Clip Score : 0.31
AI Evaluation
Likelihood of AI : 0.90
Image errors : The planets look slightly blurry, possibly due to over-smoothing. The lighting on the spaceship looks a bit unnatural.
Silhouette of Despair: A Lone Figure Contemplates a Burning City
A solitary figure, cloaked in black, stands on a rooftop overlooking a city consumed by flames. The dramatic silhouette against the apocalyptic backdrop evokes a sense of desolation and the weight of unimaginable loss.
Prompt
style-aesthetic Futuristic: dramatic, heroic ; A futuristic hero standing on a rooftop overlooking a city in flames; medium shot; heroism; a burning cityscape with smoke and flames engulfing the buildings; cinematic
Characteristic
Shot : A lone figure in a black coat and helmet stands on a rooftop, looking out at a burning city. The cityscape is engulfed in flames and smoke, creating a sense of chaos and destruction.
Aesthetic Score : 0.7
Mood : dark, dramatic, apocalyptic
Quality
Entropy : 6.69
Noise : 56
Prompt Clip Score : 0.35
AI Evaluation
Likelihood of AI : 0.90
Image errors : The smoke and flames have a slightly unrealistic, almost cartoonish appearance. The buildings in the background are repetitive and lack detail.
Conclusion
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 0.35, indicating a moderate ability to react to camera positions in the prompt. This is considered average, as a score between 0.5 and 0.75 is considered good, and above 0.75 is very good.
- Shot Analysis: The model scored 0.48, also indicating a moderate ability to understand the scene in the prompt. This is considered average, as a score between 0.5 and 0.75 is considered good, and above 0.75 is very good.
- Aesthetic Analysis: The model scored 0.32, indicating a significant difference between the expected aesthetic and the actual aesthetic of the generated image. This is considered below average, as a score between -0.2 and 0.1 is considered very good.
Overall, the model shows promise in understanding the scene and camera position, but needs improvement in generating images that match 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://deepmind.google/technologies/imagen-3/