The dramatic aesthetic, characterized by its use of light and shadow, composition, and emotional impact, is a powerful tool in visual storytelling. It’s often used in film, photography, and even video games to create a sense of grandeur, mystery, or tension. But can AI models effectively capture this aesthetic? In this blog post, we’ll explore the results of an experiment that tested an AI model’s ability to generate images with a dramatic aesthetic, analyzing its strengths and weaknesses.
Created with: titan-g1
Silhouetted Solitude: A Moment of Contemplation
A lone figure stands against the fiery backdrop of a setting sun, casting a long shadow across a desolate landscape. The image evokes a sense of melancholy and contemplation, highlighting the beauty and isolation of the moment.
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 stands on a hilltop overlooking a vast landscape at sunset. The sun is setting in the distance, casting a warm glow over the scene. The figure is silhouetted against the sky, adding to the sense of solitude and contemplation.
Aesthetic Score : 0.6
Mood : serene, contemplative, peaceful
Quality
Entropy : 6.67
Noise : 85
Prompt Clip Score : 0.18
AI Evaluation
Likelihood of AI : 0.10
Image errors : The image has some minor artifacts and noise, particularly in the sky. The color balance is slightly off, and the image could benefit from some post-processing to improve the contrast and color saturation.
One Step Away from the Abyss
A hand reaches out towards a rickety rope bridge, suspended high above a dizzying drop. The perspective is raw, placing you right in the climber’s shoes, feeling the intensity and suspense of the moment. This image captures the thrill and danger of adventure, leaving you breathless with anticipation.
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 reaching out towards a rope bridge high up on a mountain cliff. The background is blurred and out of focus, with the cliff face and some greenery visible.
Aesthetic Score : 0.7
Mood : suspenseful, daring, adventurous
Quality
Entropy : 6.69
Noise : 107
Prompt Clip Score : 0.27
AI Evaluation
Likelihood of AI : 0.20
Image errors : There is some blurriness around the edges of the image, likely due to the lens’s depth of field.
Lost in the Game: A Player’s Focus Under Blue Light
A solitary figure, bathed in the blue glow of their computer screen, is completely engrossed in a video game. The dark room amplifies the intensity of their focus, creating a sense of both playfulness and tension.
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 playing a video game on a computer. The image is focused on the person’s hands holding a controller, with the computer screen in the background.
Aesthetic Score : 0.5
Mood : focused, intense, concentrated
Quality
Entropy : 6.84
Noise : 97
Prompt Clip Score : 0.20
AI Evaluation
Likelihood of AI : 0.10
Image errors : The image is slightly blurry and the lighting is uneven. The background is also somewhat distracting.
Vibrant Street Market Bustles with Color and Life
A bustling street market comes alive with color and energy. Vendors display their colorful textiles and goods, while shoppers browse and interact. The scene is captured with a focus on depth and perspective, creating a lively and inviting atmosphere.
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 in a city, with people walking and shopping among colorful stalls selling various goods. The scene is captured from a high vantage point, giving a bird’s eye view perspective.
Aesthetic Score : 0.6
Mood : vibrant, lively, bustling
Quality
Entropy : 6.76
Noise : 108
Prompt Clip Score : 0.22
AI Evaluation
Likelihood of AI : 0.10
Image errors : Some slight blurring and artifacting are present in the image, particularly around the edges.
Tranquility in Motion: A Train Races Through Rural Serenity
A peaceful scene unfolds as a train speeds through a vast, open landscape. The blue sky and rolling hills create a sense of tranquility, while the train’s rapid movement adds a touch of excitement and freedom. This image captures the beauty of nature and the thrill of travel, leaving a lasting impression of serenity and wonder.
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 travelling through a countryside landscape with rolling hills and fields.
Aesthetic Score : 0.6
Mood : calm, peaceful, nostalgic
Quality
Entropy : 6.75
Noise : 103
Prompt Clip Score : 0.32
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image has a slight blur around the edges, which might be due to a slight camera movement while shooting.
Warmth and Laughter Fill the Room
A family gathers around a beautifully set table, bathed in candlelight. Their laughter and conversation create a joyful and intimate atmosphere, captured in this warm and inviting image.
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 for a meal. There are three people at the table, including a young boy and a young girl. They are all smiling and laughing, which suggests that they are enjoying each other’s company. The table is set with a variety of foods, including fruit, vegetables, and bread. There is also a lit candle on the table. The background of the image is a kitchen, which is dimly lit and has a warm, inviting atmosphere.
Aesthetic Score : 0.7
Mood : joyful, cozy, familial
Quality
Entropy : 6.85
Noise : 106
Prompt Clip Score : 0.25
AI Evaluation
Likelihood of AI : 0.20
Image errors : There are no major image errors. The shadows in the background might be slightly clipped from too much dynamic range, but there is no significant noise or artifacts.
A Moment of Mystery: A Family’s Pensive Gathering
A young boy, his hand covering his nose, gazes intently at something unseen. His parents sit beside him, their expressions hinting at a shared curiosity. The scene evokes a sense of domesticity tinged with a touch of mystery, leaving the viewer wondering what has captured the boy’s attention.
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 young boy is sitting between a man and a woman, looking down and covering his nose with his hand. The lighting is soft and warm, and the background is blurred.
Aesthetic Score : 0.6
Mood : tender, concerned, introspective
Quality
Entropy : 6.84
Noise : 107
Prompt Clip Score : 0.19
AI Evaluation
Likelihood of AI : 0.20
Image errors : There are no visible artifacts or errors in the image.
Campfire Camaraderie: Laughter and Joy Under the Stars
A group of friends gather around a crackling campfire, their smiles and laughter radiating warmth and joy. The soft lighting and serene forest setting create a peaceful and inviting atmosphere, capturing the essence of friendship and shared experiences.
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 people are gathered around a campfire in a forest, smiling and laughing, creating a warm and inviting atmosphere.
Aesthetic Score : 0.6
Mood : joyful, friendly, adventurous
Quality
Entropy : 6.65
Noise : 107
Prompt Clip Score : 0.25
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image has some slight graininess and noise. The colors are a bit muted, and the contrast could be enhanced to make the scene more vibrant.
Solitude by the Sea: A Man Contemplates the Vastness
A solitary figure stands on a windswept cliff, silhouetted against the stormy ocean. The crashing waves and overcast sky create a sense of dramatic loneliness, while the vastness of the sea evokes a feeling of contemplation and serenity.
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 shores and a cloudy sky.
Aesthetic Score : 0.7
Mood : tranquil, contemplative, serene
Quality
Entropy : 6.81
Noise : 104
Prompt Clip Score : 0.26
AI Evaluation
Likelihood of AI : 0.20
Image errors : No visible errors
A Hand Holds Time: A Nostalgic Glimpse into the Past
A black and white photograph, held gently in a hand, evokes a sense of nostalgia and somber reflection. The image, featuring three individuals standing before a building, is surrounded by other memories, creating a poignant tableau of a bygone era. The intimacy of the hand holding the photo adds a personal touch, inviting viewers to share in the quiet contemplation of the past.
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 holding a photograph of three people standing in front of a house. The photo is surrounded by other photos and papers, creating a sense of nostalgia and family history.
Aesthetic Score : 0.6
Mood : nostalgic, warm, sentimental
Quality
Entropy : 6.88
Noise : 104
Prompt Clip Score : 0.31
AI Evaluation
Likelihood of AI : 0.10
Image errors : The image is slightly blurry and the colors are muted.
Conclusion
The results show that the generative AI model performed well in understanding the scene and camera position, but struggled with the aesthetic. Here’s a breakdown:
- Camera Position: The model scored 0.38, 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 in the prompt.
- Shot Analysis: The model scored 0.495, also below the “good” range. This indicates that the model didn’t fully understand the scene described in the prompt.
- Aesthetic Analysis: The model scored 0.14, which is within the “very good” range of -0.2 to 0.1. This means the generated image’s aesthetic closely matched the expected aesthetic.
Overall, the model seems to be better at capturing the desired aesthetic than understanding the scene and camera position.