AI's Facial Expressions: A Mixed Bag of Emotions with Stable-diffusion
- 9 minutes read - 1789 wordsTable of Contents
Facial expressions are a powerful tool in storytelling, conveying a wide range of emotions and adding depth to characters. In the realm of AI-generated imagery, capturing realistic and expressive faces is a significant challenge. This blog post examines the performance of a generative AI model in creating images with specific facial expressions, exploring its strengths and weaknesses in capturing the nuances of human emotion.
Created with: stability-ai-core
The Laundry Pile Weighs Heavy
A man sits amidst a mountain of laundry, his weary expression reflecting the mundane frustration of a never-ending chore. The cluttered laundry room adds a subtle dramatic effect, highlighting the weight of the task at hand.
Prompt
facial-expressions Frustration: Overwhelmed and defeated ; A single person; eye-level; Single Persons; A cluttered apartment with overflowing laundry baskets and takeout containers.; cinematic
Characteristic
Shot : A man sits in a laundry room, holding a pile of clean laundry in his lap. There are laundry baskets around him, and a washing machine is visible in the background.
Aesthetic Score : 0.3
Mood : melancholy, mundane, introspective
Quality
Entropy : 6.89
Noise : 71
Prompt Clip Score : 0.22
AI Evaluation
Likelihood of AI : 0.10
Image errors : There are no noticeable artifacts or errors in the image.
Superman’s Shadow: A Moment of Suspense
A brooding Superman, shrouded in darkness, stares directly at the camera, creating an atmosphere of mystery and tension. The low lighting and intense gaze hint at a dramatic moment unfolding in the shadows.
Prompt
facial-expressions Frustration: Powerless and angry ; A superhero; close-up; Heroes; A dark alley with flickering streetlights, the hero’s cape billowing in the wind.; cinematic
Characteristic
Shot : A man dressed as Superman is standing in a dimly lit city street, looking directly at the camera. The scene is split into three panels, showing the man from different angles.
Aesthetic Score : 0.6
Mood : serious, determined, dramatic
Quality
Entropy : 6.51
Noise : 70
Prompt Clip Score : 0.25
AI Evaluation
Likelihood of AI : 0.20
Image errors : There are some slight artifacts present in the image, particularly around the edges of the man’s costume. The lighting appears slightly uneven, with some areas being darker than others.
Chaos on the Subway: Man’s Outburst Sparks Tension
A tense atmosphere fills a crowded subway car as a man’s shouting and aggressive gestures create a sense of unease among passengers. The close-up shot captures the anxiety on their faces, highlighting the dramatic effect of the situation.
Prompt
facial-expressions Frustration: Impatient and stressed ; A businessman; eye-level; Normal People; A crowded train with people pushing and shoving, the businessman trapped in the middle.; cinematic
Characteristic
Shot : A man in a suit is surrounded by people on a subway train. The scene is tense and chaotic.
Aesthetic Score : 0.6
Mood : intense, claustrophobic, suspenseful
Quality
Entropy : 6.83
Noise : 82
Prompt Clip Score : 0.30
AI Evaluation
Likelihood of AI : 0.10
Image errors : There are some minor artifacts and errors in the image, such as the shadows around the man’s head.
The Weight of Focus: A Young Man Battles Through a Task
In a dimly lit room, a young man sits hunched over his computer, headphones on, fingers flying across the keyboard. His expression is intense, his focus unwavering. The atmosphere is thick with tension, hinting at a task of great importance or a deadline looming large.
Prompt
facial-expressions Frustration: Focused but frustrated ; A gamer; close-up; Gamer; A dimly lit room with a computer screen displaying a frustratingly difficult level, the gamer’s hands shaking on the keyboard.; cinematic
Characteristic
Shot : A man is sitting at a desk in a dimly lit room, wearing headphones, and typing on a keyboard.
Aesthetic Score : 0.6
Mood : focused, intense, serious
Quality
Entropy : 5.74
Noise : 59
Prompt Clip Score : 0.21
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image has a slight amount of noise, and the colors are a bit muted. Some overexposure and contrast could be applied.
Lost in Thought Amidst Autumn’s Embrace
A young woman finds solace in the quiet solitude of a park, surrounded by fallen leaves. Her contemplative gaze and the muted hues of autumn create a poignant scene of melancholy and reflection.
Prompt
facial-expressions Frustration: Lonely and isolated ; A young woman; eye-level; Single Persons; A deserted park bench, the woman staring blankly at the ground, her phone lying forgotten beside her.; cinematic
Characteristic
Shot : A young woman sits on a park bench, talking on the phone. The background is a park setting with trees in autumn colors and leaves on the ground.
Aesthetic Score : 0.6
Mood : melancholy, contemplative, autumnal
Quality
Entropy : 6.90
Noise : 73
Prompt Clip Score : 0.24
AI Evaluation
Likelihood of AI : 0.10
Image errors : The image is slightly overexposed, resulting in a loss of detail in the highlights, particularly in the background trees. The background is a bit distracting.
Firefighters Brave the Blaze: A Moment of Courage and Determination
Two firefighters in full gear stand resolute against a backdrop of raging flames and billowing smoke. Their expressions and posture convey a sense of unwavering determination as they face the intense heat and danger. This powerful image captures the heroism and bravery of those who risk their lives to protect others.
Prompt
facial-expressions Frustration: Urgent and desperate ; A firefighter; close-up; Heroes; A burning building with smoke billowing out, the firefighter struggling to open a door.; cinematic
Characteristic
Shot : Two firefighters in full gear stand in front of a burning building, one looking directly at the camera.
Aesthetic Score : 0.7
Mood : serious, dramatic, tense
Quality
Entropy : 6.69
Noise : 78
Prompt Clip Score : 0.31
AI Evaluation
Likelihood of AI : 0.20
Image errors : There are no obvious artifacts or errors in the image.
The Focused Student: A Moment of Quiet Intensity
A young woman, surrounded by fellow students in a bustling library, sits at her desk, deeply engrossed in her studies. Her focused expression and determined gaze convey a sense of quiet intensity and dedication. The image captures the essence of a studious mind, lost in the pursuit of knowledge.
Prompt
facial-expressions Frustration: Overwhelmed and anxious ; A student; eye-level; Normal People; A crowded library with students hunched over books, the student staring at a blank page, their pen hovering over the paper.; cinematic
Characteristic
Shot : A young woman sits at a desk in a library, concentrating on her studies, surrounded by other students. The image focuses on her hand writing in a large textbook, with the library shelves in the background.
Aesthetic Score : 0.7
Mood : focused, studious, contemplative
Quality
Entropy : 6.85
Noise : 68
Prompt Clip Score : 0.27
AI Evaluation
Likelihood of AI : 0.10
Image errors : There are no visible errors in the image.
The Intensity of the Game
A young man, headphones on, is locked in a fierce video game battle. His focused gaze and tight grip on the controller convey the tension and anticipation of the moment.
Prompt
facial-expressions Frustration: Focused and intense ; A gamer; close-up; Gamer; A brightly lit gaming tournament stage, the gamer staring at the screen, their controller gripped tightly in their hands.; cinematic
Characteristic
Shot : A young man wearing headphones, sitting at a table and holding a game controller. He is focused on the game and has a determined expression on his face. The background is slightly blurred, showing other people also playing games.
Aesthetic Score : 0.7
Mood : focused, intense, competitive
Quality
Entropy : 6.54
Noise : 69
Prompt Clip Score : 0.29
AI Evaluation
Likelihood of AI : 0.10
Image errors : No visible artifacts or errors
Drowning in Dollars: Woman Overwhelmed by Wealth
A woman sits at a kitchen counter, her hands on her head, surrounded by stacks of money, her face etched with distress. The abundance of wealth seems to only amplify her anxiety, creating a stark contrast between material prosperity and emotional turmoil.
Prompt
facial-expressions Frustration: Exhausted and defeated ; A single mother; eye-level; Single Persons; A messy kitchen with dishes piled high in the sink, the single mother staring at a pile of bills, her shoulders slumped.; cinematic
Characteristic
Shot : A woman is sitting at a kitchen counter, surrounded by stacks of cash. She has her hands on her head, and looks distressed.
Aesthetic Score : 0.4
Mood : anxious, stressed, worried
Quality
Entropy : 6.88
Noise : 71
Prompt Clip Score : 0.27
AI Evaluation
Likelihood of AI : 0.10
Image errors : The image is slightly blurry, and there is some noise in the background.
Doctor’s Serious Gaze Fuels Suspense in Hospital Room
A close-up shot captures a doctor’s intense expression as he stares directly at the camera, creating a palpable sense of suspense and concern. The blurred background of a hospital room, including a medical monitor, further emphasizes the gravity of the situation.
Prompt
facial-expressions Frustration: Concerned and helpless ; A doctor; close-up; Heroes; A hospital room with a patient hooked up to machines, the doctor looking at a medical chart with a furrowed brow.; cinematic
Characteristic
Shot : A close-up shot of a doctor in a hospital, looking worried, with two other doctors in the background out of focus.
Aesthetic Score : 0.6
Mood : serious, concerned, medical
Quality
Entropy : 6.81
Noise : 66
Prompt Clip Score : 0.25
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image is slightly blurry, especially in the background, suggesting it was taken with a shaky camera or a low-quality lens.
Conclusion
The generative AI model performed well in terms of understanding the scene and camera position, but struggled with the aesthetic aspect. Here’s a breakdown:
- Camera Position: The model scored 0.25, indicating it’s not very good at reacting to camera positions in the prompt. This suggests the generated images might not accurately reflect the intended camera angles.
- Shot Analysis: The model scored 0.565, which is good. This means it’s able to understand the scene in the prompt and translate it into a visually coherent image.
- Aesthetic Analysis: The model scored 0.17, which is not very good. This means the generated image’s aesthetic deviates significantly from the expected aesthetic based on the prompt.
Overall, the model shows promise in understanding the scene and shot composition, but needs improvement in accurately capturing the desired aesthetic.
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://stability.ai