AI's Artistic Struggle: Capturing the 'Dramatic' Aesthetic with Flux-pro
- 9 minutes read - 1848 wordsTable of Contents
The ‘dramatic’ aesthetic, characterized by strong contrasts, heightened emotions, and a sense of grandeur, is a powerful tool in visual storytelling. It’s often used to evoke feelings of awe, suspense, or even tragedy. But can AI truly capture this complex aesthetic? In this blog post, we explore the challenges and successes of AI in generating images with a dramatic feel, analyzing its strengths and weaknesses through a recent experiment.
Created with: flux-pro
Silhouetted Against the Sunset: A Moment of Contemplation
A lone figure walks across a hilltop, their silhouette stark against the vibrant hues of a setting sun. The scene evokes a sense of melancholy, hope, and contemplation, leaving the viewer to ponder the figure’s journey and the mysteries of the fading light.
Prompt
Dogme 95: Epic, hopeful ; A lone figure, silhouetted against a setting sun; long shot; Heroism; A vast, desolate landscape; cinematic
Characteristic
Shot : A lone figure walks into the setting sun, holding a long staff over their shoulder. The scene is framed by a distant mountain range and a sky filled with fluffy clouds.
Aesthetic Score : 0.7
Mood : melancholy, contemplative, dramatic
Quality
Entropy : 6.40
Noise : 98
Prompt Clip Score : 0.16
AI Evaluation
Likelihood of AI : 0.10
Image errors : No noticeable errors in the image
On the Edge: A Hand Grasps for Survival
A close-up shot captures the intensity of a climber’s grip on a rope, the blurred mountainside behind hinting at the perilous heights and the thrill of the adventure. The image evokes a sense of suspense and danger, leaving the viewer wondering what lies ahead.
Prompt
Dogme 95: Suspenseful, thrilling ; A hand reaching out to grasp a rope ladder dangling from a cliff face; close-up; Adventure; A rocky, treacherous mountainside; cinematic
Characteristic
Shot : A close-up of a rope attached to a rock face. The rope is secured with a knot. The background is a blurry view of a mountain range.
Aesthetic Score : 0.6
Mood : serious, adventurous, suspenseful
Quality
Entropy : 6.77
Noise : 84
Prompt Clip Score : 0.23
AI Evaluation
Likelihood of AI : 0.10
Image errors : The image has a slight blur and a few artifacts, especially around the edges. The color balance also seems a bit off.
Lost in the Game: A Moment of Focused Intensity
A player’s hands grip the controller, their focus unwavering as they navigate the digital world. The low-key lighting and blurred background draw attention to the intensity of the gaming experience, capturing a moment of pure immersion.
Prompt
Dogme 95: Intense, focused ; A player’s hands frantically manipulating a joystick, their face illuminated by the screen; medium shot; Gaming; A dimly lit room with a computer monitor glowing brightly; cinematic
Characteristic
Shot : A person is sitting at a desk in a dimly lit room, playing a video game on a computer. The person is holding a controller in their hands and is focused on the game. The screen of the computer is reflecting light from the surrounding environment.
Aesthetic Score : 0.6
Mood : focused, intense, dark
Quality
Entropy : 6.13
Noise : 68
Prompt Clip Score : 0.22
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image is slightly blurry, and the person’s face is not fully in focus. The lighting is uneven, resulting in some areas being too dark and others too bright.
A Bustling Marketplace Under a Warm Sun
Experience the vibrant energy of a bustling marketplace, captured from a low angle that emphasizes the depth and scale of the scene. Warm lighting and colorful stalls create a sense of warmth and excitement, inviting you to explore the sights and sounds of this lively hub.
Prompt
Dogme 95: Energetic, lively ; A bustling marketplace, filled with vibrant colors and exotic goods; wide shot; Tourism; A crowded street in a foreign city; cinematic
Characteristic
Shot : A bustling marketplace in a city, filled with stalls selling fresh produce and other goods, a mix of people are shopping and moving around.
Aesthetic Score : 0.7
Mood : energetic, vibrant, crowded
Quality
Entropy : 6.63
Noise : 103
Prompt Clip Score : 0.25
AI Evaluation
Likelihood of AI : 0.20
Image errors : some blurriness in the background, suggesting a limited depth of field
Melancholy Journey Through a Cloudy Landscape
A train speeds through a rural landscape on a cloudy day, captured from the perspective of a passenger gazing out the window. The motion blur evokes a sense of dynamism and speed, while the overcast sky and muted colors create a melancholic and nostalgic atmosphere.
Prompt
Dogme 95: Nostalgic, contemplative ; A train speeding through a countryside landscape, blurring the scenery; long shot; Travel; Rolling hills and fields passing by; cinematic
Characteristic
Shot : A train moving through a rural landscape, as seen from the window of a train car.
Aesthetic Score : 0.6
Mood : melancholy, nostalgic, journey
Quality
Entropy : 6.67
Noise : 85
Prompt Clip Score : 0.27
AI Evaluation
Likelihood of AI : 0.20
Image errors : Some slight noise in the image, minor color cast
The Joy of Shared Meals: A Moment of Connection and Warmth
This image captures the essence of togetherness, showcasing a group of friends or family enjoying a cozy meal. The warm lighting, inviting atmosphere, and relaxed expressions create a sense of intimacy and shared joy. It’s a reminder of the importance of connecting with loved ones over delicious food and meaningful moments.
Prompt
Dogme 95: Warm, intimate ; A family gathered around a dinner table, sharing a meal and laughter; medium shot; Family; A cozy, well-worn kitchen; cinematic
Characteristic
Shot : A group of four people are seated around a table, enjoying a meal together in a warm and inviting setting. The scene is filled with natural light and the ambiance is cozy.
Aesthetic Score : 0.7
Mood : warm, cheerful, comfortable
Quality
Entropy : 6.56
Noise : 79
Prompt Clip Score : 0.27
AI Evaluation
Likelihood of AI : 0.10
Image errors : There is a slight blurring in the background, which could be a result of the camera settings or the lighting conditions.
Unspoken Bond: A Tale of Two Children in the Gloom
In a dimly lit room, two children stand close, their eyes locked in an intense gaze. The mysterious atmosphere and intimate setting create a sense of tension, drawing the viewer into their unspoken bond.
Prompt
Dogme 95: Sad, poignant ; A single tear rolling down a child’s cheek as they watch their parents argue; close-up; Family; A dimly lit living room; cinematic
Characteristic
Shot : Two children, a girl and a boy, are facing each other in a dimly lit room, likely a bedroom. A lamp casts a warm glow on the scene, highlighting their faces.
Aesthetic Score : 0.6
Mood : intense, suspenseful, introspective
Quality
Entropy : 6.36
Noise : 52
Prompt Clip Score : 0.22
AI Evaluation
Likelihood of AI : 0.10
Image errors : There are no significant image errors or artifacts.
Campfire Camaraderie: Friends Gather for a Night of Laughter and Warmth
A group of friends share stories and laughter around a crackling campfire, bathed in the warm glow of the flames. The scene evokes a sense of joy, intimacy, and friendship, capturing the essence of a perfect evening in the woods.
Prompt
Dogme 95: Joyful, communal ; A group of friends huddled together around a campfire, sharing stories and laughter; medium shot; Adventure; A dark forest with flickering flames; cinematic
Characteristic
Shot : A group of friends gathered around a campfire in a forest at night
Aesthetic Score : 0.7
Mood : warm, cozy, friendly
Quality
Entropy : 6.38
Noise : 73
Prompt Clip Score : 0.25
AI Evaluation
Likelihood of AI : 0.20
Image errors : No significant errors in the image, however the slight blur of some faces might be distracting for a viewer.
Lost in the Vastness: A Moment of Solitude by the Sea
A solitary figure contemplates the endless horizon, their silhouette stark against the crashing waves. The image evokes a sense of melancholy and isolation, capturing the raw beauty of a moment spent alone with the vastness of the ocean.
Prompt
Dogme 95: Awe-inspiring, contemplative ; A lone traveler gazing out at a vast ocean, their face filled with wonder; long shot; Travel; A dramatic coastline with crashing waves; cinematic
Characteristic
Shot : A solitary figure stands on a rocky cliff overlooking a vast, turquoise ocean.
Aesthetic Score : 0.7
Mood : tranquil, contemplative, melancholic
Quality
Entropy : 6.78
Noise : 63
Prompt Clip Score : 0.27
AI Evaluation
Likelihood of AI : 0.10
Image errors : No noticeable artifacts or errors.
A Moment Lost in Time
A faded photograph, held in a weathered hand, evokes a sense of nostalgia and melancholy. The blurry image and muted colors whisper of a past long gone, leaving a lingering sense of longing and a question of what stories lie hidden within the faded memories.
Prompt
Dogme 95: Melancholy, nostalgic ; A hand holding a worn photograph, the image blurred and faded; close-up; Family; A cluttered attic filled with old memories; cinematic
Characteristic
Shot : A hand is holding a vintage photo of a woman. The background is blurred and out of focus. There are other vintage photos in the background.
Aesthetic Score : 0.5
Mood : nostalgic, melancholic, intimate
Quality
Entropy : 6.79
Noise : 72
Prompt Clip Score : 0.28
AI Evaluation
Likelihood of AI : 0.10
Image errors : The image has some blurriness, especially in the background. The photo being held is slightly out of focus.
Conclusion
The results indicate that the generative AI model performed well in terms of understanding the scene and camera position, but struggled with achieving the desired aesthetic. Here’s a breakdown:
- Camera Position: The model scored 0.45, which is below the “good” range of 0.5 to 0.75. This suggests that the model didn’t perfectly capture the intended camera position described in the prompt.
- Shot Analysis: The model scored 0.56, 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 aligns with it.
- Aesthetic Analysis: The model scored 0.08, 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 the scene and camera position, 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://fal.ai/models/fal-ai/flux-pro/api