AI's Artistic Struggle: Capturing the Essence of a Scene with Scenario
- 10 minutes read - 1956 words
Table of Contents
In the realm of artificial intelligence, the ability to generate images based on textual descriptions is a rapidly evolving field. This blog post delves into the results of an experiment where an AI model was tasked with creating images based on detailed scene descriptions, exploring its strengths and weaknesses in capturing the essence of a scene. The results reveal a fascinating insight into the current state of AI’s artistic capabilities, highlighting its ability to understand camera position and shot composition, but struggling to achieve the desired aesthetic. This exploration sheds light on the ongoing challenges in bridging the gap between technical understanding and artistic expression in AI.
Created with: scenario
Silhouettes of Solitude: A Woman Contemplates Ruins in Golden Light
A lone figure in a flowing robe sits on a rocky ledge, gazing out at a ruined ancient city. The setting sun casts a warm, golden glow, highlighting the woman’s silhouette against the crumbling cityscape. The scene evokes a sense of melancholy, wistfulness, and contemplation, as the woman appears lost in thought amidst the remnants of a bygone era.
Prompt
poses looking-back: Melancholy, yet hopeful ; Lone figure in a tattered cloak; wide shot; Heroism; Ruins of a fallen city bathed in the golden light of a setting sun; cinematic
Characteristic
Shot : A woman in a long, flowing robe sits on a rock overlooking an ancient ruined city at sunset. The scene is bathed in warm golden light.
Aesthetic Score : 0.7
Mood : serene, melancholic, contemplative
Quality
Entropy : 6.67
Noise : 93
Prompt Clip Score : 0.27
AI Evaluation
Likelihood of AI : 0.20
Image errors : Some minor artifacts are visible in the background, especially around the edges of the ruined buildings. The overall sharpness of the image could be improved, particularly in the background.
Lost in the Jungle: A Temple Beckons
A lone explorer stands on a rocky outcrop, gazing at a majestic, ancient temple swallowed by the vibrant jungle. The scene evokes a sense of mystery, adventure, and tranquility, with the contrast between the lush greenery and the weathered stone creating a captivating sense of wonder.
Prompt
poses looking-back: Excited, adventurous ; A group of explorers; medium shot; Adventure; Lush jungle with ancient temples in the distance; cinematic
Characteristic
Shot : A woman stands on a rocky outcrop, gazing at a large, overgrown temple in the distance. The temple is surrounded by lush jungle, and mountains rise up in the background. The sky is a clear blue with fluffy white clouds.
Aesthetic Score : 0.7
Mood : mysterious, adventurous, serene
Quality
Entropy : 6.70
Noise : 111
Prompt Clip Score : 0.22
AI Evaluation
Likelihood of AI : 0.80
Image errors : Some of the textures in the image appear slightly blurry and artificial, particularly on the leaves and rocks.
Cyberpunk Focus: A Woman in the Digital Labyrinth
A young woman, clad in black leather, navigates the digital world with intense focus. The vibrant, futuristic lighting casts an air of mystery and intrigue, highlighting her serious expression as she works diligently at her multi-monitor setup. This image captures the essence of a cyberpunk world, where technology and human ambition collide.
Prompt
poses looking-back: Intense, focused ; A gamer’s hands on a keyboard; close-up; Gaming; Neon lights reflecting on the screen, displaying a virtual world; cinematic
Characteristic
Shot : A young woman is sitting in front of a computer, typing on a keyboard. The room is lit by purple and pink neon lights. She is wearing a black leather jacket.
Aesthetic Score : 0.7
Mood : cyberpunk, futuristic, focused
Quality
Entropy : 6.51
Noise : 85
Prompt Clip Score : 0.31
AI Evaluation
Likelihood of AI : 0.20
Image errors : There are no visible errors in the image.
Solitude and Wonder: A Figure Silhouetted Against a Majestic Sunset
A lone figure stands on a mountaintop, their long coat blending with the shadows cast by the setting sun. The vast mountain range stretches before them, a breathtaking panorama of snow-capped peaks and a valley bathed in golden light. This serene and dramatic scene evokes a sense of solitude and wonder, inviting contemplation of the vastness of nature and the mysteries it holds.
Prompt
poses looking-back: Awe-inspiring, peaceful ; A lone traveler standing on a mountain peak; long shot; Tourism; Breathtaking panoramic view of a snow-capped mountain range; cinematic
Characteristic
Shot : A lone woman stands on a mountaintop, looking out over a vast, snowy mountain range in the distance. The sun is setting, casting a warm glow over the landscape.
Aesthetic Score : 0.8
Mood : serene, awe-inspiring, contemplative
Quality
Entropy : 6.70
Noise : 103
Prompt Clip Score : 0.28
AI Evaluation
Likelihood of AI : 0.20
Image errors : No noticeable artifacts or errors.
Silhouettes of Hope in the Desert Sunset
A solitary figure, cloaked in a long coat and hat, walks along a desolate train track as the sun dips below the horizon. The woman’s silhouette against the fiery sky evokes a sense of melancholy, peace, and a glimmer of hope amidst the vast emptiness.
Prompt
poses looking-back: Nostalgic, adventurous ; A vintage train speeding through a desert landscape; medium shot; Travel; Sun setting over the horizon, casting long shadows; cinematic
Characteristic
Shot : A woman in a trench coat and hat walks away from the camera on railroad tracks toward the setting sun.
Aesthetic Score : 0.7
Mood : melancholy, contemplative, hopeful
Quality
Entropy : 6.73
Noise : 92
Prompt Clip Score : 0.30
AI Evaluation
Likelihood of AI : 0.20
Image errors : No visible errors.
Urban Joy: Capturing Moments of Laughter and Light
A vibrant collage of photos showcasing the joy and carefree spirit of city life. Candid moments of laughter and smiles paint a picture of happiness and optimism in the urban landscape.
Prompt
poses looking-back: Joyful, carefree ; A group of friends laughing and talking; medium shot; Groups; A bustling city street with vibrant street art; cinematic
Characteristic
Shot : A collage of three images, each featuring a different person or group of people. The first image shows a woman in a denim jumpsuit standing on a city street, smiling and looking up. The second image shows two women standing on a city street, smiling and laughing. The third image shows a man standing on a city street, smiling and looking to the right. The street is lined with buildings and a graffiti wall.
Aesthetic Score : 0.6
Mood : happy, joyful, carefree
Quality
Entropy : 6.82
Noise : 99
Prompt Clip Score : 0.25
AI Evaluation
Likelihood of AI : 0.20
Image errors : No artifacts or errors.
A Moment of Awe: Astronaut Gazes at Earth from the Void
A lone astronaut floats in the vast expanse of space, their gaze fixed directly on the camera. Earth, a vibrant blue marble, hangs in the distance, creating a powerful sense of awe and isolation. This image captures the wonder and fragility of our planet, reminding us of the vastness of the universe and the importance of preserving our home.
Prompt
poses looking-back: Awe-inspiring, contemplative ; A lone astronaut floating in space; long shot; Heroism; Earth hanging in the distance, a blue marble against the black void; cinematic
Characteristic
Shot : A lone astronaut floating in space, with Earth in the background.
Aesthetic Score : 0.7
Mood : awe, isolation, wonder
Quality
Entropy : 6.52
Noise : 104
Prompt Clip Score : 0.23
AI Evaluation
Likelihood of AI : 0.70
Image errors : The astronaut’s suit appears slightly blurry, and there are some artifacts visible on the Earth’s clouds. The clouds in the background look unrealistic.
Friends Conquer Rapids on an Epic River Adventure
Experience the thrill of whitewater rafting with a group of friends as they navigate through stunning mountain scenery. The rapids add a sense of danger and excitement, making for an unforgettable adventure.
Prompt
poses looking-back: Thrilling, exhilarating ; A group of adventurers on a raft; medium shot; Adventure; Rapids churning whitewater, a sense of danger and excitement; cinematic
Characteristic
Shot : A group of people on a raft ride through rapids in a mountainous river. The sun is shining and the sky is blue. The people in the raft are all smiling and having fun.
Aesthetic Score : 0.7
Mood : joyful, adventurous, sunny
Quality
Entropy : 6.50
Noise : 108
Prompt Clip Score : 0.31
AI Evaluation
Likelihood of AI : 0.80
Image errors : The image appears to be a bit blurry, especially in the background. The colors are also a bit oversaturated.
Silhouetted Against the Sunset: A Lone Warrior’s Solitude
A lone female figure in futuristic armor stands on a rocky mountain peak, gazing out over a vast, snow-capped mountain range at sunset. The dramatic lighting of the sunset and the figure’s silhouette against the mountains create a sense of isolation and grandeur, evoking a mood of solitude, adventure, and futuristic wonder.
Prompt
poses looking-back: Triumphant, accomplished ; A gamer’s avatar standing on a virtual mountain peak; close-up; Gaming; A vast, fantastical landscape stretching out before them; cinematic
Characteristic
Shot : A woman in futuristic armor stands on a rocky mountain peak, looking out at a snow-covered mountain range in the distance. The sky is a soft orange and pink, suggesting a sunset or sunrise.
Aesthetic Score : 0.7
Mood : epic, adventurous, contemplative
Quality
Entropy : 6.60
Noise : 81
Prompt Clip Score : 0.26
AI Evaluation
Likelihood of AI : 0.90
Image errors : The woman’s clothing and the mountain range in the distance appear somewhat blurry. The lighting in the scene is a little artificial, and the overall image has a slightly synthetic feel.
Sunset Romance on the Beach
A couple strolls hand-in-hand along a tranquil beach as the sun dips below the horizon, casting a warm glow and creating a breathtaking silhouette. The scene evokes a sense of romantic intimacy and peaceful serenity.
Prompt
poses looking-back: Romantic, peaceful ; A couple walking hand-in-hand on a beach; long shot; Tourism; Sunset painting the sky in vibrant hues of orange and pink; cinematic
Characteristic
Shot : A couple walking hand-in-hand on a beach at sunset. The woman is wearing a pink dress and the man is wearing a pink shirt and white shorts.
Aesthetic Score : 0.7
Mood : romantic, dreamy, peaceful
Quality
Entropy : 6.00
Noise : 99
Prompt Clip Score : 0.32
AI Evaluation
Likelihood of AI : 0.80
Image errors : The image is slightly blurry, particularly in the background. The colors are also a bit oversaturated, which gives the image a slightly artificial look.
Conclusion
The results show 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 0.37, 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 0.61, falling within the “good” range. This indicates that the model was able to understand the scene and create a shot that was generally consistent with the prompt.
- Aesthetic Analysis: The model scored 0.07, which is far from the “very good” range of -0.2 to 0.1. This suggests that the generated image’s aesthetic significantly deviated from the expected aesthetic described in the prompt.
Overall, the model demonstrated a decent understanding of the scene and shot composition, but struggled to achieve 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