AI's Facial Expressions: A Mixed Bag of Emotions with Scenario
- 9 minutes read - 1831 wordsTable of Contents
Facial expressions are a powerful tool for conveying emotions and intentions. In the realm of AI-generated images, capturing these nuances is a significant challenge. This blog post explores a case study where an AI model was tasked with generating images based on specific scene descriptions, including details about facial expressions. The results reveal both the model’s progress and areas for further development in understanding and replicating the complexities of human emotions.
Created with: scenario
Smiling at the Carnival: A Moment of Joy and Romance
A young woman radiates happiness, standing against a blurred carnival backdrop. Her stylish hair and beige sweater add to the carefree and romantic mood. The soft lighting and dreamy background create a captivating scene.
Prompt
facial-expressions Amusement: Playful, carefree ; A lone woman; eye-level; Single Person; a bustling carnival with bright lights and colorful tents; cinematic
Characteristic
Shot : A close-up portrait of a woman with freckles, smiling, in a fairground with colorful tents in the background.
Aesthetic Score : 0.8
Mood : happy, cheerful, carefree
Quality
Entropy : 6.78
Noise : 90
Prompt Clip Score : 0.25
AI Evaluation
Likelihood of AI : 0.50
Image errors : The woman’s skin appears slightly smooth, and there are some artifacts around her hair.
Joyful Moments at the Carnival
A young woman with long brown hair radiates happiness as she gazes up at the sky, standing before a vibrant carnival ride. The image captures a carefree spirit and the playful energy of the fair.
Prompt
facial-expressions Amusement: Exuberant, triumphant ; A superhero in a vibrant costume; eye-level; Hero; a crowded amusement park with roller coasters and Ferris wheels in the background; cinematic
Characteristic
Shot : A woman with long brown hair is wearing a red and blue costume, she is smiling and looking up, the background is blurred and shows a carnival with a Ferris wheel in the background
Aesthetic Score : 0.8
Mood : happy, playful, joyful
Quality
Entropy : 6.71
Noise : 89
Prompt Clip Score : 0.30
AI Evaluation
Likelihood of AI : 0.90
Image errors : Some artifacts around the woman’s hair, blur is too much on the background
Golden Hour Picnic Under the Tree
A group of friends share laughter and memories under the shade of a sprawling tree, the warm glow of the setting sun casting a nostalgic hue over their picnic. A distant fairground adds a touch of whimsy to the scene, capturing the carefree spirit of the moment.
Prompt
facial-expressions Amusement: Relaxed, happy ; A group of friends; eye-level; Normal People; a picnic blanket under a shady tree in a park, with a carousel in the distance; cinematic
Characteristic
Shot : A group of young people are having a picnic under a large tree in a park. There are horses in the background, suggesting a fair or festival.
Aesthetic Score : 0.7
Mood : happy, nostalgic, cheerful
Quality
Entropy : 6.64
Noise : 105
Prompt Clip Score : 0.23
AI Evaluation
Likelihood of AI : 0.80
Image errors : The image appears to be a digital painting, with some slight inconsistencies in the brushwork and textures. There are no significant artifacts or errors.
Level Up Your Joy: This Gamer’s Smile Is Contagious
A young woman, headphones on and controller in hand, beams at the camera with pure gaming joy. The low lighting adds a touch of drama to her intense gaze, capturing the thrill of the moment.
Prompt
facial-expressions Amusement: Focused, excited ; A gamer; close-up; Gamer; a dimly lit room with a computer screen displaying a vibrant video game, a controller in their hand; cinematic
Characteristic
Shot : A young woman is wearing a headset and holding a video game controller in front of a gaming monitor.
Aesthetic Score : 0.7
Mood : excited, playful, focused
Quality
Entropy : 6.83
Noise : 86
Prompt Clip Score : 0.21
AI Evaluation
Likelihood of AI : 0.20
Image errors : The lighting on the subject’s face appears somewhat uneven, and the colors seem slightly oversaturated.
Lost in the Whirlwind of Memories
A young girl, her brown hair flowing, sits atop a carousel horse, her gaze lost in the dreamy blur of lights and motion. The scene evokes a sense of nostalgia and wonder, capturing the fleeting magic of childhood.
Prompt
facial-expressions Amusement: Magical, innocent ; A young girl; eye-level; Single Person; a carousel with brightly painted horses, her eyes wide with wonder; cinematic
Characteristic
Shot : A young girl with blonde hair is sitting on a carousel horse, looking up with a thoughtful expression. The carousel is in motion, and the background is blurred.
Aesthetic Score : 0.8
Mood : dreamy, nostalgic, whimsical
Quality
Entropy : 6.77
Noise : 83
Prompt Clip Score : 0.31
AI Evaluation
Likelihood of AI : 0.20
Image errors : There is a slight blur in the background of the image, but it does not detract from the overall aesthetic.
Childhood Joy: Laughter and Freedom on the Playground
A heartwarming scene of four children running and laughing on a playground, capturing the pure joy and carefree spirit of childhood. The swing set in the background adds to the playful atmosphere, creating a moment of pure happiness.
Prompt
facial-expressions Amusement: Joyful, carefree ; A group of children; eye-level; Normal People; a playground with swings, slides, and a sandbox, their laughter echoing in the air; cinematic
Characteristic
Shot : A group of children are playing on a swing set in a park. They are all laughing and having fun. The swings are made of rope and metal. The children are wearing casual clothing. The background is a sunny day with a blue sky and green grass.
Aesthetic Score : 0.8
Mood : joyful, playful, carefree
Quality
Entropy : 6.48
Noise : 88
Prompt Clip Score : 0.26
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image is well-composed and there are no noticeable errors.
Solitude by the Moonlit Sea
A lone figure, shrouded in darkness, stands at the edge of a wooden pier, gazing out at the tranquil ocean bathed in moonlight. The scene evokes a sense of melancholy and introspection, highlighting the man’s isolation and the vastness of the sea.
Prompt
facial-expressions Amusement: Melancholy, contemplative ; A lone man; eye-level; Single Person; a deserted boardwalk at night, the sound of crashing waves in the background; cinematic
Characteristic
Shot : A solitary figure in a long coat and hat stands on a wooden walkway that leads towards the ocean. The figure is facing the ocean and is silhouetted against the bright moon. The scene is peaceful and contemplative.
Aesthetic Score : 0.8
Mood : melancholy, contemplative, serene
Quality
Entropy : 6.67
Noise : 95
Prompt Clip Score : 0.25
AI Evaluation
Likelihood of AI : 0.70
Image errors : The image has a slight artificial feel, as if it was painted digitally. The details are too perfect and the colors are a bit too saturated.
Superhero Soars Through Fire and Fury
A female superhero, clad in blue and gold, cuts through the sky above a bustling city, leaving a fiery explosion in her wake. The dynamic pose and intense action capture the hero’s power and determination in this thrilling moment.
Prompt
facial-expressions Amusement: Thrilling, heroic ; A superhero in action; dynamic shot; Hero; a cityscape with towering buildings, a dramatic explosion in the background; cinematic
Characteristic
Shot : A woman in a superhero costume flies over a city skyline with a fiery explosion behind her. The city looks like New York, with the Empire State Building visible in the background.
Aesthetic Score : 0.7
Mood : heroic, powerful, dramatic
Quality
Entropy : 6.83
Noise : 102
Prompt Clip Score : 0.23
AI Evaluation
Likelihood of AI : 0.80
Image errors : There are some minor artifacts in the image, particularly in the explosion. The woman’s hair also appears to be a bit too perfect and smooth. Some additional detail and variation in the hair would make it look more natural.
Family Fun on the Roller Coaster!
A family of four enjoys a thrilling roller coaster ride, their laughter echoing through the amusement park. The Ferris wheel in the background adds to the festive atmosphere, capturing the joy and excitement of a perfect day out.
Prompt
facial-expressions Amusement: Exhilarating, bonding ; A family; eye-level; Normal People; a crowded amusement park, their faces lit up with joy as they ride a roller coaster; cinematic
Characteristic
Shot : A family of four is riding a rollercoaster at an amusement park. They are all smiling and laughing, enjoying the ride.
Aesthetic Score : 0.7
Mood : joyful, exhilarating, happy
Quality
Entropy : 6.75
Noise : 94
Prompt Clip Score : 0.28
AI Evaluation
Likelihood of AI : 0.20
Image errors : Slight blurring of the subjects’ faces and the rollercoaster, potentially caused by camera shake or motion blur. Some minor color saturation issues.
A Radiant Smile: Capturing Innocent Happiness
Experience the warmth of a genuine smile from a young woman with brown hair and sparkling green eyes. This close-up portrait exudes sweetness and innocence, as she gazes directly at the camera. The soft lighting and blurred background, adorned with framed pictures, create an intimate and inviting atmosphere.
Prompt
facial-expressions Amusement: Triumphant, exhilarating ; A gamer; close-up; Gamer; a dimly lit room, their hands moving rapidly on a keyboard, a triumphant shout escaping their lips; cinematic
Characteristic
Shot : A young woman with short brown hair is looking at the camera with a soft smile. The background is blurred with a soft golden hue.
Aesthetic Score : 0.8
Mood : sweet, gentle, hopeful
Quality
Entropy : 6.64
Noise : 85
Prompt Clip Score : 0.17
AI Evaluation
Likelihood of AI : 0.90
Image errors : The image seems overly airbrushed and the hair and skin look unrealistically smooth.
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 0.2, indicating a fairly low ability to accurately represent the camera position described in the prompt. This suggests the model may not be very good at understanding and implementing specific camera angles.
- Shot Analysis: The model scored 0.59, which is considered good. This means the model was able to understand the scene described in the prompt and create an image that reflects it reasonably well.
- Aesthetic Analysis: The model scored 0.0, which is considered very good. This means the generated image closely matched the expected aesthetic style, indicating the model is capable of producing visually appealing images.
Overall, the model shows promise in understanding scene descriptions and creating visually pleasing images. However, it needs improvement in accurately representing camera positions.
Sources:
- https://dramaresource.com/storytelling/
- https://seedsoftellers.eu/resources/the-body-language-for-young-tellers/
- https://digitalcollections.sit.edu/cgi/viewcontent.cgi?article=1288&context=sandanona&filename=1&type=additional
- https://citeseerx.ist.psu.edu/document?doi=7f842882e9bb1fa2c0e96939bc8d2c37e34e17c0&repid=rep1&type=pdf
- https://www.twinkl.co.uk/search?q=drama+facial+expression
- https://www.scenario.com