AI's Facial Expressions: A Mixed Bag of Emotions with Scenario
- 9 minutes read - 1872 wordsTable of Contents
Facial expressions are a powerful tool in storytelling, conveying emotions and intentions without words. In the realm of generative AI, the ability to accurately depict these expressions is crucial for creating compelling and immersive narratives. This blog post delves into the performance of a generative AI model in capturing facial expressions, analyzing its strengths and weaknesses based on a series of prompts describing various scenes and characters.
Created with: scenario
Lost in the Storm: A Woman’s Solitary Contemplation
A lone figure, shrouded in darkness, stands defiant against the raw power of a stormy sea. The dramatic contrast between her small form and the vast, turbulent landscape evokes a sense of isolation and melancholic contemplation. This image captures the raw beauty of nature’s fury and the human spirit’s resilience in the face of adversity.
Prompt
facial-expressions Disagreement: Melancholy, isolated, conflicted ; A lone figure standing on a clifftop, looking out at a stormy sea; eye-level; Single Person; Dramatic, stormy sky with crashing waves; cinematic
Characteristic
Shot : A woman in a green coat stands on a cliff overlooking a stormy sea.
Aesthetic Score : 0.7
Mood : dramatic, melancholic, ominous
Quality
Entropy : 6.75
Noise : 95
Prompt Clip Score : 0.26
AI Evaluation
Likelihood of AI : 0.50
Image errors : The woman’s face is slightly blurry and the edges of the image are a bit soft. The sea is slightly overexposed and the waves are not very realistic.
Hope Amidst the Flames: Superhero Stands Tall Against City’s Ruin
A female superhero, silhouetted against a fiery explosion, stands defiant on a rooftop overlooking a city consumed by flames. The dramatic contrast between her heroic stance and the apocalyptic scene evokes a powerful sense of hope amidst the devastation.
Prompt
facial-expressions Disagreement: Urgent, conflicted, determined ; A superhero, cape billowing in the wind, standing in front of a burning building, looking at a group of people fleeing; eye-level; Hero; City skyline with smoke and flames; cinematic
Characteristic
Shot : A female superhero, in black suit with red cape, stands on a rooftop, looking at a burning city, fire and smoke in the background
Aesthetic Score : 0.7
Mood : dramatic, heroic, hopeful
Quality
Entropy : 6.66
Noise : 102
Prompt Clip Score : 0.29
AI Evaluation
Likelihood of AI : 0.80
Image errors : The city in the background looks a bit generic and lacks detail. The fire and smoke are a bit unrealistic.
A Silent Disagreement: The Look of Unspoken Tension
A couple shares a meal, but their gazes tell a different story. The woman’s intense expression and the man’s averted gaze hint at a brewing conflict, creating a palpable sense of tension amidst the casual intimacy of their dinner date.
Prompt
facial-expressions Disagreement: Angry, tense, frustrated ; A couple arguing in a crowded restaurant, their faces close together; close-up; Normal People; Busy restaurant interior with other diners; cinematic
Characteristic
Shot : A couple having dinner at a restaurant, the woman is looking to the side and the man is looking at her
Aesthetic Score : 0.7
Mood : dramatic, tense, uncomfortable
Quality
Entropy : 6.79
Noise : 102
Prompt Clip Score : 0.33
AI Evaluation
Likelihood of AI : 0.10
Image errors : No noticeable errors in the image, good quality
In the Zone: Gamer’s Intensity Under Dimly Lit Lights
A young woman, headphones on, is fully immersed in her game. The dimly lit room and her focused expression create a palpable sense of tension and suspense, highlighting the intensity of the gaming experience. The futuristic aesthetic adds a layer of intrigue to this captivating scene.
Prompt
facial-expressions Disagreement: Frustrated, intense, focused ; A gamer, hunched over a computer screen, furiously clicking a mouse; close-up; Gamer; Dark room with glowing computer screen and peripherals; cinematic
Characteristic
Shot : A young woman is sitting at a desk, wearing headphones and looking intently at a computer monitor. The room is dimly lit and the monitor screen is showing a blue and white abstract design.
Aesthetic Score : 0.6
Mood : focused, intense, digital
Quality
Entropy : 6.57
Noise : 87
Prompt Clip Score : 0.25
AI Evaluation
Likelihood of AI : 0.20
Image errors : No significant image errors
Lost in Thought: A Moment of Contemplation at the Cafe
A young woman finds solace in a quiet moment at a cafe, her gaze lost in thought as she talks on the phone. The soft lighting and her pensive expression create a sense of calm and solitude, capturing the essence of quiet reflection.
Prompt
facial-expressions Disagreement: Disappointed, lonely, withdrawn ; A woman sitting alone in a coffee shop, staring at a phone with a blank expression; eye-level; Single Person; Cozy coffee shop interior with other patrons; cinematic
Characteristic
Shot : A young woman with dark hair is sitting at a table in a cafe, talking on the phone. She has a cup of coffee in front of her, and the background is blurred.
Aesthetic Score : 0.8
Mood : thoughtful, contemplative, quiet
Quality
Entropy : 6.75
Noise : 86
Prompt Clip Score : 0.29
AI Evaluation
Likelihood of AI : 0.80
Image errors : There are some artifacts in the image, particularly in the woman’s hair and the background. The skin texture is a little bit too smooth.
Intriguing Gaze in a Concrete Jungle
A close-up portrait of a young woman with a neutral expression, captured in a dimly lit alleyway. Her gaze draws you in, creating a sense of mystery and intrigue. The soft lighting and the graffiti-covered background add to the edgy atmosphere.
Prompt
facial-expressions Disagreement: Confident, determined, defiant ; A hero, standing in a dark alleyway, looking at a villain with a determined expression; eye-level; Hero; Dark, gritty alleyway with shadows and graffiti; cinematic
Characteristic
Shot : A close-up portrait of a young woman with a serious expression. She is standing in a narrow alleyway with graffiti on the walls. Her hair is messy and she is wearing a black tank top.
Aesthetic Score : 0.7
Mood : serious, mysterious, alluring
Quality
Entropy : 6.73
Noise : 98
Prompt Clip Score : 0.22
AI Evaluation
Likelihood of AI : 0.90
Image errors : The image has a few minor artifacts, such as some aliasing around the edges of the woman’s hair and clothing. The skin texture is also slightly artificial looking.
Tension in the Park: A Silent Standoff
Four figures, three women and one man, stand frozen in a park, arms crossed and expressions serious. The air crackles with unspoken tension, leaving viewers to wonder what secrets lie beneath the surface. What are they waiting for, and what will happen next?
Prompt
facial-expressions Disagreement: Angry, frustrated, heated ; A group of friends arguing in a park, their voices raised; medium shot; Normal People; Sunny park with trees and benches; cinematic
Characteristic
Shot : Four people stand in a park, arms crossed, looking serious. They are likely having an argument. The background is out of focus, suggesting a park with trees.
Aesthetic Score : 0.6
Mood : serious, tense, conflicted
Quality
Entropy : 6.79
Noise : 91
Prompt Clip Score : 0.27
AI Evaluation
Likelihood of AI : 0.30
Image errors : There are no visible errors in the image, but there is some noise in the background.
The Thrill of Victory: Gamer’s Focused Excitement
A young woman, immersed in her video game, embodies the intensity and excitement of the gaming experience. Her clenched fist and focused gaze reveal the thrill of a hard-won victory, capturing the essence of competitive gaming.
Prompt
facial-expressions Disagreement: Frustrated, angry, defeated ; A gamer, slamming his fist on a desk, yelling at the computer screen; close-up; Gamer; Brightly lit gaming room with multiple monitors; cinematic
Characteristic
Shot : A woman is sitting in a chair, facing a computer screen, with her fist clenched in anger. The image is likely depicting a moment of frustration or anger during gameplay.
Aesthetic Score : 0.7
Mood : intense, frustrated, determined
Quality
Entropy : 6.63
Noise : 88
Prompt Clip Score : 0.30
AI Evaluation
Likelihood of AI : 0.90
Image errors : The image has a slight blurriness around the edges and some of the details are not as sharp as they could be. The woman’s face appears a bit artificial and lacks a realistic texture.
Lost in the City’s Symphony
A young man stands alone in the bustling city, his pensive gaze lost in the blur of passing faces. The soft focus of the background emphasizes his isolation and introspective mood, capturing the essence of urban contemplation.
Prompt
facial-expressions Disagreement: Sad, lonely, rejected ; A man walking away from a group of people, his head down; long shot; Single Person; Busy city street with people walking by; cinematic
Characteristic
Shot : A young man standing on a cobbled street in a city, looking lost and pensive. The background is blurred, with a lot of people walking by. The image is taken during a hazy day, and the mood is melancholic and mysterious.
Aesthetic Score : 0.6
Mood : melancholic, mysterious
Quality
Entropy : 6.79
Noise : 92
Prompt Clip Score : 0.26
AI Evaluation
Likelihood of AI : 0.20
Image errors : No visible errors in the image.
Silhouetted Dreams: A Moment of Contemplation at Sunset
A young woman stands on a rooftop, bathed in soft light, gazing out at the city skyline as the sun sets. The scene evokes a dreamy, contemplative mood, with the contrasting lighting creating a dramatic effect.
Prompt
facial-expressions Disagreement: Thoughtful, conflicted, determined ; A hero, standing on a rooftop, looking at a city skyline with a conflicted expression; eye-level; Hero; City skyline at night with twinkling lights; cinematic
Characteristic
Shot : A young woman with dark hair and rosy cheeks gazes out at a cityscape at dusk. She’s wearing a white tank top and has a relaxed posture, suggesting a moment of quiet contemplation.
Aesthetic Score : 0.8
Mood : dreamy, melancholic, serene
Quality
Entropy : 6.68
Noise : 88
Prompt Clip Score : 0.29
AI Evaluation
Likelihood of AI : 0.90
Image errors : The image has a very smooth and almost artificial look. This is due to the high level of detail and the lack of natural imperfections.
Conclusion
The analysis shows mixed results for the generative AI model’s performance.
- Camera Position: The model scored 0.35, which is below average. This suggests the model struggles to accurately interpret and implement camera positions specified in the prompts.
- Shot Analysis: The model scored 0.58, which is good. This indicates the model is capable of understanding and translating the scene descriptions in the prompts into visually coherent shots.
- Aesthetic Analysis: The model scored -0.05, which is very good. This means the generated image closely matches the expected aesthetic style, indicating the model’s ability to capture the desired visual style.
Overall, the model demonstrates strengths in understanding scene descriptions and achieving the desired aesthetic, but it needs improvement in accurately interpreting 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