AI's Artistic Struggle: Capturing the 'Dramatic' Aesthetic with Freepik
- 9 minutes read - 1841 wordsTable of Contents
The ‘dramatic’ aesthetic is a powerful tool in visual storytelling, evoking strong emotions and creating a sense of grandeur. It often involves stark contrasts, dramatic lighting, and a focus on the emotional impact of the scene. But can AI truly capture this complex aesthetic? This article explores the challenges and successes of generative AI models in generating images with a ‘dramatic’ style. We’ll examine the results of a recent experiment, analyzing the model’s ability to understand the scene, camera position, and most importantly, the desired aesthetic. Through this analysis, we’ll gain insights into the current capabilities and limitations of AI in capturing the nuances of artistic expression.
Created with: freepik
Silhouetted Solitude: A Moment of Tranquility in the Desert
A lone figure, silhouetted against a vibrant orange sunset, contemplates the vast desert landscape. A small dog stands in the foreground, adding a touch of companionship to the scene. The image evokes a sense of tranquility and introspection, highlighting the beauty and solitude of the natural world.
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 in a long coat stands with their back to the viewer, gazing at a sunset over rolling hills. A small dog stands beside them.
Aesthetic Score : 0.7
Mood : tranquil, contemplative, serene
Quality
Entropy : 6.31
Noise : 68
Prompt Clip Score : 0.31
AI Evaluation
Likelihood of AI : 0.10
Image errors : The image appears to be slightly overexposed, making the sky and horizon somewhat washed out.
On the Edge: A Climber’s Daring Ascent
A lone climber grips a rope, clinging precariously to a sheer cliff face. The blurred mountain valley below emphasizes the height and danger of their ascent, creating a sense of suspense and adventure.
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 person’s hand holding onto a rope on a steep, rocky mountainside.
Aesthetic Score : 0.6
Mood : dramatic, intense, precarious
Quality
Entropy : 6.62
Noise : 88
Prompt Clip Score : 0.33
AI Evaluation
Likelihood of AI : 0.30
Image errors : The image is slightly blurry, especially in the background.
Lost in the Game: A Gamer’s Intense Focus
A young man sits in a dimly lit room, completely absorbed in his video game. His focused expression and the isolation of the setting create a powerful image of immersion and dedication.
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 young man sits at his desk, playing a video game on his computer.
Aesthetic Score : 0.6
Mood : focused, intense, casual
Quality
Entropy : 6.69
Noise : 61
Prompt Clip Score : 0.30
AI Evaluation
Likelihood of AI : 0.10
Image errors : No visible artifacts or errors
Golden Retriever Steals the Show in Bustling Market Street
A vibrant, bustling market street comes alive with color and energy. Fresh produce spills from stalls, lanterns cast a warm glow, and the crowd buzzes with activity. But it’s the golden retriever, perched serenely in the middle of the street, that truly captures the eye, adding a touch of whimsy to the scene.
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 market street lined with stalls selling fresh produce. The scene is framed by old buildings with hanging lanterns.
Aesthetic Score : 0.7
Mood : vibrant, lively, nostalgic
Quality
Entropy : 6.80
Noise : 109
Prompt Clip Score : 0.33
AI Evaluation
Likelihood of AI : 0.30
Image errors : There is a slight blurriness in the image, particularly in the background, which could be a result of motion blur or the use of a wide aperture. The lighting is a bit overexposed, causing some details in the fruit and vegetables to be washed out.
Nostalgia on Rails: A Vintage Train Disappears into the Green Valley
A tranquil scene of a vintage train winding through a lush green valley evokes a sense of nostalgia and peace. The train disappearing into the distance adds a touch of mystery, inviting you to imagine the journey ahead.
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 is traveling along the tracks in the countryside, with rolling hills and green fields in the background.
Aesthetic Score : 0.6
Mood : tranquil, nostalgic, peaceful
Quality
Entropy : 6.78
Noise : 89
Prompt Clip Score : 0.33
AI Evaluation
Likelihood of AI : 0.20
Image errors : No noticeable artifacts or errors.
Warm Glow of Family Togetherness
A heartwarming scene of a family gathered around a table, bathed in the warm light of candles and overhead lamps. The atmosphere is cozy and inviting, capturing the essence of shared joy and connection.
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 family is gathered around a table, enjoying a meal together. They are all smiling and laughing, and the atmosphere is warm and inviting. The table is set with food and drinks, and there are candles on the table, creating a cozy and intimate ambiance.
Aesthetic Score : 0.7
Mood : happy, warm, cozy
Quality
Entropy : 6.77
Noise : 71
Prompt Clip Score : 0.31
AI Evaluation
Likelihood of AI : 0.10
Image errors : There are minor artifacts in the background, potentially due to compression.
What’s Got Them So Hooked?
A group of siblings huddle together on a couch, their eyes glued to something unseen. The warm lighting and their intense expressions create a sense of anticipation and mystery. What could they be watching?
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 : A group of children, likely siblings, are sitting on a couch, looking intently at something off-screen. The lighting is warm and intimate, suggesting a cozy home environment.
Aesthetic Score : 0.6
Mood : suspenseful, curious, concerned
Quality
Entropy : 6.80
Noise : 67
Prompt Clip Score : 0.31
AI Evaluation
Likelihood of AI : 0.10
Image errors : There appears to be a slight blurriness in the background, and a few minor imperfections in the focus on the children’s faces. The lighting is slightly uneven, creating some shadows on the faces.
Campfire Glow: Intimacy and Laughter in the Forest
Four friends gather around a crackling campfire, their laughter echoing through the dark forest. The warm glow of the fire creates a cozy and intimate atmosphere, highlighting the joy and camaraderie of their shared moment.
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 : Four young women are sitting around a campfire in a forest. The fire is small but bright. The women are all smiling and talking to each other. The forest is dark and the trees are tall and dense.
Aesthetic Score : 0.7
Mood : warm, cozy, friendship
Quality
Entropy : 6.48
Noise : 85
Prompt Clip Score : 0.33
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image appears a little over-sharpened, particularly on the faces. There’s a hint of digital noise in the darker areas, but it’s not overly distracting.
Contemplating the Vastness: A Lone Figure on a Majestic Cliff
A solitary figure stands on a dramatic cliff, gazing out at the crashing waves of a boundless ocean. The scene evokes a sense of tranquility, majesty, and contemplation, as the power of nature meets the quiet introspection of the lone observer.
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 lone figure stands on a cliff overlooking a vast ocean, with rocky inlets and crashing waves in the distance. The sky is overcast, creating a dramatic and moody atmosphere.
Aesthetic Score : 0.8
Mood : dramatic, moody, contemplative
Quality
Entropy : 6.70
Noise : 81
Prompt Clip Score : 0.33
AI Evaluation
Likelihood of AI : 0.10
Image errors : No noticeable errors.
A Boy’s Journey Through Time: A Faded Photograph Whispers of a Bygone Era
A weathered photograph, held within a cluttered attic, captures a young boy walking down a deserted cobblestone street. The image evokes a sense of nostalgia, mystery, and melancholic longing, transporting viewers to a forgotten time and place.
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 holds a vintage photograph of a young boy walking down a deserted street lined with old buildings. The photograph is slightly worn and faded, giving it a nostalgic feel. The background is out of focus and shows a pile of old papers.
Aesthetic Score : 0.7
Mood : nostalgia, solitude, mystery
Quality
Entropy : 6.73
Noise : 62
Prompt Clip Score : 0.33
AI Evaluation
Likelihood of AI : 0.10
Image errors : There are no noticeable artifacts or errors in the image.
Conclusion
The results indicate that the generative AI model performed well in understanding the scene and camera position, but struggled with the aesthetic aspect. Here’s a breakdown:
- Camera Position: The model scored 0.4, which is below the “good” range of 0.5 to 0.75. This suggests that the model didn’t fully capture the intended camera position described in the prompt.
- Shot Analysis: The model scored 0.55, which falls within the “good” range. This means the model was able to understand the scene and create a shot that was somewhat aligned with the prompt.
- Aesthetic Analysis: The model scored 0.08, which is significantly below the “very good” range of -0.2 to 0.1. This indicates a significant difference between the expected aesthetic and the actual aesthetic of the generated image. The model likely didn’t capture the desired visual style.
Overall, the model shows promise in understanding the scene and camera position, but needs improvement in generating images that match 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://www.freepik.com