AI's Artistic Journey: Capturing the Essence, Not the Angle with Flux-dev
- 10 minutes read - 1950 wordsTable of Contents
The ‘dramatic’ aesthetic, characterized by heightened emotions, striking visuals, and a sense of grandeur, is often employed in storytelling, photography, and even video games. This style aims to evoke powerful feelings in the viewer, drawing them into the narrative and leaving a lasting impression. In this blog post, we explore the capabilities of AI in generating images that embody this dramatic aesthetic. We’ll analyze a case study where an AI model was tasked with creating images based on specific prompts, focusing on its ability to capture the desired mood and style. We’ll also delve into the challenges the model faced, particularly in accurately translating camera positions, and discuss the implications for the future of AI-generated art.
Created with: flux-dev
Silhouettes of Togetherness: A Family’s Moment of Quiet Contemplation
A serene and intimate scene unfolds as a family of four stands silhouetted against a large window, gazing out at the vibrant city skyline. Their hands clasped together, they share a moment of quiet contemplation, creating a sense of drama and mystery against the backdrop of the bustling metropolis.
Prompt
style-aesthetic 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 of four silhouetted against a window looking out at a city skyline. The family is standing in a modern, light-filled room.
Aesthetic Score : 0.6
Mood : peaceful, contemplative, hopeful
Quality
Entropy : 6.58
Noise : 82
Prompt Clip Score : 0.25
AI Evaluation
Likelihood of AI : 0.20
Image errors : No obvious artifacts or errors
Lost in Transit: A Man’s Solitary Journey
A lone figure, shrouded in shadow, walks through an empty airport terminal, his suitcase the only companion in his melancholic journey. The stark contrast between his silhouette and the bright windows evokes a sense of mystery and isolation, leaving the viewer to ponder his destination and the weight of his solitude.
Prompt
style-aesthetic 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 in a long coat walks through an airport terminal, pulling a rolling suitcase behind him. The background is blurred, and other people are also walking by. The lighting is dim and moody.
Aesthetic Score : 0.6
Mood : lonely, contemplative, melancholic
Quality
Entropy : 6.80
Noise : 63
Prompt Clip Score : 0.27
AI Evaluation
Likelihood of AI : 0.30
Image errors : The image has some minor noise and artifacts, particularly in the background. The subject is also slightly out of focus.
A Lone Figure in the Fog: Hope Amidst the Ruins
A solitary superhero, cloaked in black, stands on a rooftop overlooking a misty cityscape. Their back turned towards the viewer, they gaze towards a distant plume of smoke, hinting at a world in turmoil. The silhouette against the foggy skyline evokes a sense of dramatic isolation and mystery, yet a glimmer of hope persists in their unwavering stance.
Prompt
style-aesthetic 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 lone figure, clad in a cape, stands on a rooftop overlooking a cityscape shrouded in fog and smoke. The figure is facing away from the viewer, gazing at the horizon.
Aesthetic Score : 0.6
Mood : mysterious, somber, brooding
Quality
Entropy : 6.40
Noise : 62
Prompt Clip Score : 0.28
AI Evaluation
Likelihood of AI : 0.80
Image errors : The image appears to be slightly grainy, with some blurring in the distance. The figure’s cape is also somewhat unnatural in its shape and flow.
Tiny Turtle Takes on the City
A playful green turtle figurine stands poised on a city street, its curious gaze and whimsical pose captivating the viewer. The out-of-focus background adds to the sense of wonder and anticipation, making this a charming and delightful scene.
Prompt
style-aesthetic 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 turtle-like character standing on a city street with a blurred background of cars and buildings
Aesthetic Score : 0.7
Mood : whimsical, friendly, nostalgic
Quality
Entropy : 6.84
Noise : 73
Prompt Clip Score : 0.26
AI Evaluation
Likelihood of AI : 0.90
Image errors : The image has a slight blur in the background and the character’s texture appears slightly grainy.
A Glimpse into the Past: Nostalgia and Warmth in a Vintage-Filled Room
Step into a room steeped in history and nostalgia, where an old-fashioned seascape painting captures the essence of a bygone era. Cluttered with antique suitcases and other vintage treasures, the space evokes a sense of cozy comfort and invites you to linger and imagine the stories it holds.
Prompt
style-aesthetic 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 old room with vintage furniture and a large painting of a sunset scene on the wall.
Aesthetic Score : 0.6
Mood : vintage, nostalgic, cozy
Quality
Entropy : 6.95
Noise : 108
Prompt Clip Score : 0.29
AI Evaluation
Likelihood of AI : 0.10
Image errors : There is some minor noise in the image and the edges of the furniture are slightly blurred.
Lost in the Mist, Guided by Technology
A hand emerges from the ethereal mist, clutching a smartphone displaying a map. The red pin beckons, promising adventure and mystery in the heart of the forest. This image captures the allure of the unknown, where technology and nature collide in a captivating dance.
Prompt
style-aesthetic 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 a map app open in a foggy forest
Aesthetic Score : 0.5
Mood : mysterious, eerie, suspenseful
Quality
Entropy : 6.65
Noise : 38
Prompt Clip Score : 0.29
AI Evaluation
Likelihood of AI : 0.50
Image errors : The image has a slight blur around the edges, which is likely due to the fog.
The Touch of Tomorrow: A Hand Reaches for the Future
A hand, bathed in a mesmerizing red and blue glow, extends towards a computer screen displaying a grid of data. The scene evokes a sense of mystery and anticipation, hinting at a future where technology and humanity intertwine in ways we can only begin to imagine.
Prompt
style-aesthetic 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 person’s hand interacting with a computer screen in a dimly lit room.
Aesthetic Score : 0.6
Mood : cyberpunk, futuristic, mysterious
Quality
Entropy : 6.74
Noise : 73
Prompt Clip Score : 0.20
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image appears to have some slight noise in the shadows and some minor artifacts around the edges of the screen.
Silhouette of Hope Against the Setting Sun
A solitary figure stands in silhouette against a vibrant sunset, the city skyline a distant backdrop. The scene evokes a sense of calm and hope, with the dramatic effect of the silhouette adding an element of mystery and contemplation.
Prompt
style-aesthetic 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 silhouette of a lone person standing against a bright red sunset, with the sun almost entirely visible in the sky, and a skyline in the distance.
Aesthetic Score : 0.7
Mood : tranquil, melancholic, hopeful
Quality
Entropy : 6.41
Noise : 42
Prompt Clip Score : 0.28
AI Evaluation
Likelihood of AI : 0.20
Image errors : No notable artifacts or errors are present in the image.
Joyful Gathering at an Asian Temple
A group of children and adults stand before a grand, ornate building, likely a temple or palace, with a distinct Asian aesthetic. The scene is vibrant and playful, capturing a moment of shared joy and wonder. The soft lighting and blurred background create a sense of depth and atmosphere, making the image both visually appealing and emotionally engaging.
Prompt
style-aesthetic 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 group of people standing in front of a large, ornate building. The building has a domed roof and is decorated with intricate details. The people are all dressed casually and appear to be enjoying themselves.
Aesthetic Score : 0.6
Mood : casual, vibrant, warm
Quality
Entropy : 6.75
Noise : 79
Prompt Clip Score : 0.32
AI Evaluation
Likelihood of AI : 0.20
Image errors : Slight blurriness around the edges of the image.
Lost in the Metaverse: A Glimpse into the Future of Play
Four friends gather in a dimly lit room, their faces obscured by VR headsets. They hold controllers, their expressions a mix of focus and excitement, as they explore a world beyond the physical. This image captures the playful curiosity and futuristic potential of virtual reality, leaving viewers eager to discover what awaits within the digital realm.
Prompt
style-aesthetic 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 : A group of friends are wearing VR headsets and playing a virtual reality game. The room is dimly lit with colorful neon lights.
Aesthetic Score : 0.6
Mood : futuristic, playful, competitive
Quality
Entropy : 6.72
Noise : 71
Prompt Clip Score : 0.25
AI Evaluation
Likelihood of AI : 0.20
Image errors : There are some minor image artifacts, particularly in the shadows and highlights.
Conclusion
The results indicate that the generative AI model performed well in understanding the scene and camera position, but struggled with achieving the desired aesthetic. Here’s a breakdown:
- Camera Position: The model scored 0.35, which is considered below average. This suggests that the model didn’t accurately translate the camera position described in the prompt into the generated image.
- Shot Analysis: The model scored 0.7, which is considered good. This indicates that the model was able to understand the scene described in the prompt and create a shot that aligns with it.
- Aesthetic Analysis: The model scored 0.11, which is considered very good. This means that the generated image’s aesthetic closely matched the expected aesthetic, despite the camera position issues.
Overall, the model shows promise in understanding scene descriptions and achieving the desired aesthetic, but needs improvement in accurately translating camera positions.
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://fal.ai/models/fal-ai/flux/dev/api