AI's Facial Expressions: A Mixed Bag of Emotions with Flux-schnell
- 9 minutes read - 1884 wordsTable of Contents
In the realm of AI image generation, capturing the nuances of human facial expressions is a challenging task. This blog post examines the performance of a generative AI model in creating images with specific facial expressions. We explore the model’s ability to understand the scene, camera position, and aesthetic elements, analyzing its strengths and weaknesses. Through a detailed breakdown of the model’s performance metrics, we gain insights into the current state of AI image generation and its potential for creating realistic and emotionally evocative images.
Created with: flux-schnell
A Moment of Melancholy: A Young Man’s Introspective Gaze
A close-up shot captures a young man’s somber expression as he stares directly at the camera. The cluttered room behind him, with laundry baskets and a red and white striped container, adds to the sense of unease and introspection. The intimate framing and direct eye contact create a feeling of vulnerability, drawing the viewer into his melancholic state.
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 young man with a worried expression looking directly at the camera. The background is cluttered and out of focus, creating a sense of unease.
Aesthetic Score : 0.4
Mood : uneasy, worried, introspective
Quality
Entropy : 6.86
Noise : 89
Prompt Clip Score : 0.24
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image has some slight noise and artifacts, particularly in the darker areas. The edges of the frame are slightly distorted, possibly due to a wide-angle lens.
The Shadowed Gaze: A Man of Mystery and Intensity
A captivating portrait of a man shrouded in mystery. His determined expression and dramatic lighting create a sense of tension and suspense, leaving you wondering what secrets lie behind his shadowed gaze.
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 : Close-up portrait of a man with a determined expression, wearing a red cloak.
Aesthetic Score : 0.6
Mood : intense, serious, dramatic
Quality
Entropy : 6.64
Noise : 72
Prompt Clip Score : 0.27
AI Evaluation
Likelihood of AI : 0.20
Image errors : Some slight noise and pixelation in the image, particularly in the shadows.
A Man’s Intense Gaze in the Dimly Lit Train Car
A man in a suit sits on a train, his gaze fixed directly on the viewer. The scene is shrouded in shadows, creating an atmosphere of mystery and tension. His serious expression suggests a story waiting to unfold.
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 looking directly at the camera, standing on a crowded train. The scene is busy and has a high level of visual interest.
Aesthetic Score : 0.7
Mood : intense, serious, focused
Quality
Entropy : 6.83
Noise : 93
Prompt Clip Score : 0.25
AI Evaluation
Likelihood of AI : 0.20
Image errors : Some noise and grain is visible in the image, particularly in the shadows.
The Hacker in the Shadows
A man, shrouded in darkness, sits hunched over his computer, his intense focus illuminated only by the screen’s glow. The low lighting and his unwavering gaze create a palpable sense of suspense, hinting at a mission of critical importance.
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 person wearing a headset is gaming in a dark room. Their face is partially illuminated by the screen of the computer they’re using.
Aesthetic Score : 0.6
Mood : focused, intense, serious
Quality
Entropy : 5.65
Noise : 53
Prompt Clip Score : 0.22
AI Evaluation
Likelihood of AI : 0.20
Image errors : There is a slight amount of noise in the image, particularly in the darker areas.
Lost in Thought: A Moment of Contemplation in the Park
A young woman finds solace on a park bench, her pensive expression and posture hinting at a moment of deep reflection. The urban setting provides a backdrop for her introspective state, evoking a sense of solitude and contemplation.
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 in a contemplative pose, lost in thought. She is wearing a blue denim shirt and jeans, and has her long brown hair cascading down her back. The bench is made of wood and has a dark, weathered finish. The park itself is a quiet and serene setting, with trees lining the path and fallen leaves scattered on the ground.
Aesthetic Score : 0.6
Mood : melancholy, introspective, quiet
Quality
Entropy : 6.87
Noise : 109
Prompt Clip Score : 0.27
AI Evaluation
Likelihood of AI : 0.10
Image errors : The image is slightly blurry and there are some artifacts in the background.
In the Eye of the Fire: A Firefighter’s Determination
A close-up shot captures the intense focus of a firefighter, their face illuminated by the fiery blaze behind them. The image evokes a sense of urgency and danger, highlighting the bravery and dedication of those who face the flames.
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 : Close-up portrait of a firefighter in his helmet, looking intensely toward the camera. His expression is focused and slightly worried. The background is blurred and out of focus, likely a fire scene.
Aesthetic Score : 0.7
Mood : intense, focused, serious
Quality
Entropy : 6.18
Noise : 78
Prompt Clip Score : 0.31
AI Evaluation
Likelihood of AI : 0.10
Image errors : No noticeable errors.
Lost in Thought: A Moment of Contemplation in the Library
A young man sits at a desk in a library, bathed in soft light. His focused expression and the intimate framing of the shot draw you into his world of contemplation. The mood is one of quiet intensity, inviting you to share in his moment of reflection.
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 man is sitting at a desk in a library, focusing on something in front of him. There are bookshelves in the background, with other people sitting at desks in the distance.
Aesthetic Score : 0.6
Mood : serious, contemplative, focused
Quality
Entropy : 6.83
Noise : 89
Prompt Clip Score : 0.28
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image is slightly blurry, likely due to camera shake. There are also some minor artifacts in the background, likely due to compression.
Immersed in the Game: A Young Gamer’s Focused Intensity
A young man, illuminated by soft, colorful lights, is completely engrossed in his video game. His focused expression and the dramatic lighting create a sense of intense immersion, capturing the thrill of the gaming experience.
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 a headset and holding a game controller, likely playing a video game. The background is blurry with colorful lights.
Aesthetic Score : 0.7
Mood : intense, focused, determined
Quality
Entropy : 6.67
Noise : 67
Prompt Clip Score : 0.28
AI Evaluation
Likelihood of AI : 0.10
Image errors : The image quality appears slightly grainy. The lighting is uneven, creating a harsh contrast between the subject and the background. There is a slight color shift in the image.
The Weight of Bills: A Woman’s Struggle in the Kitchen
A young woman stands in her kitchen, her face etched with worry as she stares down at a towering pile of papers, likely bills. The image captures the overwhelming feeling of financial stress, amplified by the dramatic lighting and the woman’s concerned expression.
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 looking at papers in a kitchen, possibly bills or invoices. She appears stressed or overwhelmed.
Aesthetic Score : 0.4
Mood : tense, worried, frustrated
Quality
Entropy : 6.74
Noise : 84
Prompt Clip Score : 0.25
AI Evaluation
Likelihood of AI : 0.20
Image errors : Some slight blurriness in the background, suggesting a slightly out-of-focus shot. No significant artifacts.
Shadows of Concern: A Tense Moment in the Hospital
A dimly lit hospital room, where two men, one in a white coat, stand over a patient in a bed. Their faces are shadowed, reflecting the serious and somber mood. The lighting and expressions create a palpable sense of tension and uncertainty, leaving the viewer wondering about the patient’s fate.
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 : Two men, one older, one younger, are in a hospital room. The older man is in a hospital bed, while the younger man is standing next to him. The younger man has a serious expression on his face.
Aesthetic Score : 0.4
Mood : tense, somber, concerned
Quality
Entropy : 6.86
Noise : 91
Prompt Clip Score : 0.26
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image is slightly blurry. The lighting is a bit too dark.
Conclusion
The analysis shows 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 0.35, which is considered below average. This suggests that the model didn’t accurately capture the intended camera position described in the prompt.
- Shot Analysis: The model scored 0.605, which is considered good. This indicates that the model was able to understand the scene described in the prompt and create a shot that aligns with it.
- Aesthetic Analysis: The model scored 0.22, which is considered below average. This means that the generated image’s aesthetic deviated significantly from the expected aesthetic described in the prompt.
Overall, the model demonstrated a good understanding of the scene and shot composition, but struggled to match 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://fal.ai/models/fal-ai/flux/schnell/api