AI Captures the Drama, But Misses the Aesthetics with Scenario
- 9 minutes read - 1865 wordsTable of Contents
Dramatic poses are a powerful tool in storytelling, used to convey emotion, action, and tension. They often involve dynamic movement, exaggerated expressions, and striking compositions. This experiment aimed to test an AI model’s ability to generate images based on descriptions of dramatic poses and scenes. The results reveal both strengths and weaknesses in the model’s capabilities, highlighting the ongoing evolution of AI in image generation.
Created with: scenario
A City in Flames, A Solitary Figure Watches
A lone woman, cloaked in darkness, stands on a cliff overlooking a city consumed by fire. The scene is a powerful blend of drama and melancholy, capturing the devastation of an apocalyptic event. The contrast of light and shadow, the billowing smoke, and the fiery reflection on the river create a truly impactful image.
Prompt
poses falling: Epic, desperate, hopeful ; A lone figure in a tattered cape; wide shot; Heroism; A burning city skyline; cinematic
Characteristic
Shot : A lone woman in a black cloak stands on a rooftop overlooking a city engulfed in flames and smoke. The setting sun casts a warm glow on the scene, but the overall mood is dark and ominous.
Aesthetic Score : 0.7
Mood : dark, ominous, apocalyptic
Quality
Entropy : 6.80
Noise : 98
Prompt Clip Score : 0.26
AI Evaluation
Likelihood of AI : 0.80
Image errors : Some of the buildings and smoke look a bit artificial, possibly generated by AI. The overall lighting and color grading are a bit too saturated and unrealistic.
Suspended in Wonder: A Young Woman Contemplates the Misty Jungle Canyon
A young woman, clad in sporty attire, hangs precariously over a misty jungle canyon, suspended by ropes. The image evokes a sense of adventure, mystery, and contemplation, with the vast and enigmatic landscape adding to the drama and suspense. The use of mist and fog creates an atmosphere of wonder and intrigue.
Prompt
poses falling: Suspenseful, thrilling, determined ; A lone explorer clinging to a rope ladder; close-up; Adventure; A vast, misty jungle canyon; cinematic
Characteristic
Shot : A woman is hanging from ropes over a large misty canyon, with lush greenery and cliff faces surrounding her.
Aesthetic Score : 0.7
Mood : adventurous, daring, mysterious
Quality
Entropy : 6.69
Noise : 92
Prompt Clip Score : 0.29
AI Evaluation
Likelihood of AI : 0.30
Image errors : The image has some minor artifacts, particularly around the edges of the woman’s figure. There is also a slight blurriness in the background, which may be due to the use of a shallow depth of field.
Neon Dreams: A Woman Navigates a Futuristic Cityscape
A young woman strides through a vibrant, futuristic city, bathed in the glow of neon lights and towering structures. Her position in the frame captures a sense of movement and excitement, perfectly embodying the energetic mood of this futuristic world.
Prompt
poses falling: Energetic, chaotic, playful ; A pixelated character plummeting through a digital landscape; medium shot; Gaming; A neon-lit cityscape with glowing buildings; cinematic
Characteristic
Shot : A woman is walking in a cyberpunk city, the scene is a mix of neon lights and futuristic buildings
Aesthetic Score : 0.7
Mood : futuristic, urban, mysterious
Quality
Entropy : 6.78
Noise : 93
Prompt Clip Score : 0.28
AI Evaluation
Likelihood of AI : 0.90
Image errors : the city buildings look slightly distorted, as if they were generated by a computer
A Moment of Serenity Above the Snowy Peaks
A woman finds peace and adventure as she floats in a hot air balloon, dwarfed by the majestic snow-capped mountains. The vastness of the landscape and the serenity of the scene create a powerful sense of isolation and beauty.
Prompt
poses falling: Exhilarating, awe-inspiring, carefree ; A hot air balloon basket with tourists; long shot; Tourism; A breathtaking view of a mountain range with snow-capped peaks; cinematic
Characteristic
Shot : A woman is sitting in a hot air balloon basket, looking out over a snowy mountain range. There are other hot air balloons in the distance.
Aesthetic Score : 0.7
Mood : serene, adventurous, whimsical
Quality
Entropy : 6.62
Noise : 100
Prompt Clip Score : 0.31
AI Evaluation
Likelihood of AI : 0.30
Image errors : The image quality is good, but there are some minor artifacts and blurring in the background, particularly around the mountains.
Leap of Faith: Woman Takes the Plunge From a Clifftop
A young woman, fueled by adventure, takes a daring leap from a cliff, her small figure silhouetted against the vast landscape. The image captures the thrill and danger of the moment, showcasing the raw courage of the individual against the backdrop of nature’s grandeur.
Prompt
poses falling: Adrenaline-fueled, chaotic, humorous ; A backpacker tumbling down a rocky hillside; close-up; Travel; A lush green valley with a winding river; cinematic
Characteristic
Shot : A young woman with a backpack jumps off a cliff overlooking a valley with a winding river.
Aesthetic Score : 0.7
Mood : adventurous, daring, courageous
Quality
Entropy : 6.69
Noise : 90
Prompt Clip Score : 0.27
AI Evaluation
Likelihood of AI : 0.30
Image errors : No significant image errors, some minor color banding in the sky.
Three Women on a Cliff, Gazing at a Stormy Sea
A serene yet melancholic scene unfolds as three women in dresses stand on a cliff, their gaze fixed on the vast, turbulent sea. The contrast between their calm presence and the stormy waters creates a sense of longing and wistful contemplation.
Prompt
poses falling: Heart-stopping, terrifying, bonding ; A group of friends holding hands, falling from a cliff; wide shot; Groups; A dramatic ocean coastline with crashing waves; cinematic
Characteristic
Shot : Three women in dresses stand on a cliff overlooking the ocean. The waves are crashing against the rocks below and the sky is cloudy.
Aesthetic Score : 0.7
Mood : tranquil, peaceful, wistful
Quality
Entropy : 6.74
Noise : 94
Prompt Clip Score : 0.27
AI Evaluation
Likelihood of AI : 0.20
Image errors : Slight noise and grain in the image
Hope Soars Amidst the Ruins
A female superhero, clad in a vibrant blue and red suit, cuts through the smoke and debris of a ravaged cityscape. The setting sun casts a dramatic glow, highlighting her determined flight as she brings hope to a world in chaos.
Prompt
poses falling: Dramatic, heroic, determined ; A superhero in mid-air, falling towards a collapsing building; close-up; Heroism; A cityscape with smoke and debris; cinematic
Characteristic
Shot : A female superhero in a blue and red suit is flying through the air, surrounded by smoke and debris. The background shows a city skyline.
Aesthetic Score : 0.7
Mood : dramatic, heroic, powerful
Quality
Entropy : 6.85
Noise : 89
Prompt Clip Score : 0.29
AI Evaluation
Likelihood of AI : 0.80
Image errors : There are no visible errors in the image. The smoke looks a bit artificial, however.
Adrenaline Rush: Rock Climbers Defy Gravity on a Majestic Cliff
Two climbers dangle precariously from a sheer cliff face, their daring descent framed by towering mountains and a sprawling forest. The wide-angle perspective emphasizes the scale of the challenge and the breathtaking beauty of the natural world. This image captures the essence of adventure, risk, and awe-inspiring landscapes.
Prompt
poses falling: Thrilling, adventurous, daring ; A group of adventurers rappelling down a sheer rock face; long shot; Adventure; A towering mountain peak with a breathtaking view; cinematic
Characteristic
Shot : Two climbers rappelling down a steep cliff face. The cliff is very high up and there is a deep valley with forest below. The sky is clear and the sun is shining.
Aesthetic Score : 0.8
Mood : adventurous, daring, dramatic
Quality
Entropy : 6.65
Noise : 104
Prompt Clip Score : 0.28
AI Evaluation
Likelihood of AI : 0.10
Image errors : No visible errors
A Dreamy Escape: Woman Gazes Upon a Fantasy Landscape
This ethereal scene captures a woman in a blue dress standing on a rock, overlooking a breathtaking valley with a flowing river. The distant mountains and a large planet in the sky add to the sense of wonder and mystery. The woman’s pose and the expansive view create a dramatic effect, transporting you to a world of fantasy and dreams.
Prompt
poses falling: Magical, surreal, exciting ; A player character falling through a virtual world; medium shot; Gaming; A vibrant, fantastical landscape with glowing flora; cinematic
Characteristic
Shot : A woman in a blue dress stands on a rock in a fantastical landscape, with a large planet in the background. The landscape is filled with rolling hills, a river, and blooming flowers.
Aesthetic Score : 0.75
Mood : dreamy, ethereal, whimsical
Quality
Entropy : 6.76
Noise : 106
Prompt Clip Score : 0.27
AI Evaluation
Likelihood of AI : 0.90
Image errors : The woman’s hair is a bit too smooth and lacks detail, and there are some artifacts in the background.
A Whimsical Journey Above a Charming European Village
Experience the magic of a warm evening as a colorful hot air balloon floats serenely above a quaint European village. Bathed in golden light, the town reveals its charm with red-tiled roofs, lush greenery, and cobblestone streets. This enchanting scene evokes a sense of wonder and nostalgia, inviting you to escape into a world of dreams.
Prompt
poses falling: Romantic, nostalgic, heartwarming ; A family in a hot air balloon, falling towards a picturesque village; long shot; Tourism; A charming village with cobblestone streets and colorful houses; cinematic
Characteristic
Shot : A picturesque aerial view of a charming European village, featuring a hot air balloon hovering above the town. The setting sun casts a warm glow over the rooftops and the lush greenery surrounding the village.
Aesthetic Score : 0.8
Mood : serene, whimsical, nostalgic
Quality
Entropy : 6.73
Noise : 104
Prompt Clip Score : 0.28
AI Evaluation
Likelihood of AI : 0.80
Image errors : The edges of the image are slightly blurry and there is a slight halo effect around the hot air balloon.
Conclusion
The results show that the generative AI model performed well in terms of camera position and shot analysis, but struggled with aesthetic analysis.
Here’s a breakdown:
- Camera Position: The model scored 0.5, which falls within the “good” range (0.5 to 0.75). This means the model was able to accurately capture the camera position described in the prompt.
- Shot Analysis: The model scored 0.6, also within the “good” range. This indicates the model understood the scene described in the prompt and created an image that reflects that understanding.
- Aesthetic Analysis: The model scored 0.06, which is significantly lower than the “very good” range (-0.2 to 0.1). This suggests that the generated image’s aesthetic deviated from the expected aesthetic described in the prompt.
Overall, the model demonstrates a good understanding of camera position and shot composition, but needs improvement in capturing the desired aesthetic.
Sources:
- https://www.writerswrite.co.za/cheat-sheets-for-writing-body-language/
- https://mads3df.wordpress.com/2013/09/04/storytelling-poses/
- https://www.pinterest.com/pegasister890/character-poses/
- https://www.youtube.com/watch?v=udky6ANxWws
- https://maven.com/articles/storytelling-techniques
- https://www.scenario.com