AI's Facial Expressions: A Mixed Bag of Success with Dall-e-3
- 10 minutes read - 1945 wordsTable of Contents
Facial expressions are a powerful tool for conveying emotions and intentions in visual storytelling. Generative AI models are increasingly being used to create images with realistic facial expressions, but how well do they capture the nuances of human emotion? This blog post delves into the performance of a generative AI model in understanding and generating facial expressions across a range of scenes. We’ll explore how the model handles camera position, shot composition, and aesthetic, highlighting its strengths and weaknesses.
Created with: dall-e-3
A Solitary Figure Contemplates the Storm’s Fury
A lone figure stands defiant against the elements, silhouetted against a sky of swirling, ominous clouds. The turbulent sea below reflects the drama unfolding above, creating a scene of raw power and unsettling beauty.
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 lone figure in a long coat stands on a cliff overlooking a stormy sea. Behind him, a swirling mass of dark clouds dominates the sky.
Aesthetic Score : 0.7
Mood : mysterious, dramatic, melancholic
Quality
Entropy : 6.44
Noise : 91
Prompt Clip Score : 0.22
AI Evaluation
Likelihood of AI : 0.80
Image errors : The clouds appear somewhat artificial and repetitive, particularly the swirl. The figure is slightly blurry, and some of the elements are pixelated. The lighting is flat and lacks depth.
Hero of Fire and Ice: A City in Peril
A powerful superhero, engulfed in flames and ice, stands defiant amidst a burning cityscape. As terrified citizens flee, the hero’s dual nature is on full display, promising a dramatic and intense battle for the city’s survival.
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 superhero standing in the middle of a burning city, surrounded by fleeing civilians. He is engulfed in flames on one side and ice on the other, symbolizing his power.
Aesthetic Score : 0.7
Mood : dramatic, powerful, epic
Quality
Entropy : 6.89
Noise : 109
Prompt Clip Score : 0.32
AI Evaluation
Likelihood of AI : 0.80
Image errors : The fire and ice effects are a bit too artificial and the figures in the background lack detail. The buildings in the background look a bit pixelated.
The Argument: A Moment of Explosive Tension
A couple’s heated exchange in a dimly lit restaurant is captured in this dramatic image. The close-up on their angry faces and the blurred background create a palpable sense of tension and confrontation. The intimate lighting adds to the claustrophobic atmosphere, making the moment feel raw and intense.
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 is having a tense conversation in a dimly lit restaurant, while others are at a table in the background
Aesthetic Score : 0.4
Mood : tense, dramatic, conflicted
Quality
Entropy : 6.68
Noise : 91
Prompt Clip Score : 0.33
AI Evaluation
Likelihood of AI : 0.20
Image errors : No noticeable artifacts or errors
Lost in the Game: A Moment of Intense Focus
A man is completely absorbed in a video game, his face illuminated by the screen’s glow in a dimly lit room. The close-up shot captures his intense concentration, creating a sense of drama and suspense.
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 man, likely a gamer, is intensely focused on his computer screen while using a mouse. The scene is dark with only the glow of the screen illuminating his face.
Aesthetic Score : 0.7
Mood : intense, focused, dark
Quality
Entropy : 6.50
Noise : 87
Prompt Clip Score : 0.27
AI Evaluation
Likelihood of AI : 0.70
Image errors : The image appears to be over-sharpened and has some unnatural-looking highlights and shadows, which makes it seem less realistic.
Lost in Thought: A Moment of Melancholy in a Bustling Cafe
A young woman sits alone at a cafe table, her thoughtful gaze lost in the depths of her coffee cup. The low lighting and blurred background create a sense of mystery and intrigue, hinting at a story waiting to be told. This image captures the essence of melancholy and introspection, inviting viewers to ponder the woman’s thoughts and emotions.
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 is sitting in a dimly lit cafe, her face is resting on her hand, looking thoughtful and melancholic. In the background, other people are sitting at tables in a blurred fashion.
Aesthetic Score : 0.7
Mood : melancholy, contemplative, moody
Quality
Entropy : 6.56
Noise : 83
Prompt Clip Score : 0.32
AI Evaluation
Likelihood of AI : 0.10
Image errors : The image is slightly blurry and the lighting is uneven. The background is a little distracting with the out-of-focus people in the background.
Shadowed Figure in a Beam of Light
A man stands in a dark alley, illuminated by a single beam of light, creating an intense and suspenseful atmosphere. His gaze is fixed directly on the viewer, leaving a sense of mystery and intrigue.
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 man is standing in a dark alleyway, looking directly at the camera. The alleyway is lit by a single light source, creating a dramatic effect. There is a shadowy figure in the background
Aesthetic Score : 0.7
Mood : intense, mysterious, suspenseful
Quality
Entropy : 5.61
Noise : 84
Prompt Clip Score : 0.24
AI Evaluation
Likelihood of AI : 0.10
Image errors : The image is slightly grainy and the lighting is a bit uneven. The edges of the image appear soft and there is a noticeable border.
Friendships Fracture Under the Harsh Sun
A tense argument unfolds in a sun-drenched park, casting shadows on the faces of young adults locked in a heated confrontation. The scene is charged with dramatic tension, leaving the viewer wondering what sparked the conflict and what the outcome will be.
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 : A group of young people are arguing in a park. The scene is set in the afternoon, with the sun shining brightly. There are trees and buildings in the background.
Aesthetic Score : 0.4
Mood : tense, confrontational, angry
Quality
Entropy : 6.68
Noise : 103
Prompt Clip Score : 0.28
AI Evaluation
Likelihood of AI : 0.10
Image errors : There are no major artifacts or errors in the image.
In the Zone: Gamer’s Intensity Captures the Screen
A young woman, headphones on and eyes locked on the screen, embodies the focused intensity of a gamer in the heat of the game. The dimly lit room and dramatic composition heighten the sense of excitement and determination.
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 young woman is playing a video game, she is very focused and appears to be getting frustrated or excited about the game. Her face is contorted in a grimace, and her fist is clenched in the air. The scene is dark and blurry.
Aesthetic Score : 0.3
Mood : intense, focused, frustrated
Quality
Entropy : 6.64
Noise : 90
Prompt Clip Score : 0.30
AI Evaluation
Likelihood of AI : 0.10
Image errors : The image is blurry and noisy, especially the background. The colors are muted.
Lost in the City: A Moment of Melancholy
A solitary figure walks through a blurred cityscape, his posture and expression hinting at a heavy heart. The shallow depth of field emphasizes his isolation, capturing a moment of pensive reflection in the cool, grey urban landscape.
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 man walks alone down a city street, surrounded by other people. The street is narrow and the buildings are tall, creating a sense of claustrophobia. The light is dim and the air is thick with fog. The man’s face is obscured by his hood, and he appears to be lost in thought. The overall feeling is one of loneliness and isolation.
Aesthetic Score : 0.7
Mood : lonely, melancholic, isolated
Quality
Entropy : 6.81
Noise : 97
Prompt Clip Score : 0.25
AI Evaluation
Likelihood of AI : 0.80
Image errors : The image has some slight blur, and the lighting is a bit flat. The edges of the buildings and the people seem slightly pixelated and lacking in detail. The image feels more like a 3D render than a real photograph
Heroic Silhouette: A City’s Guardian Stands Tall
A powerful silhouette of a superhero, cloaked in a cape, dominates the cityscape. The dramatic lighting and the hero’s stance evoke a sense of strength and heroism, promising a thrilling story to unfold.
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 superhero in a dark blue suit and a red cape, standing on a rooftop, looking out at a cityscape at night.
Aesthetic Score : 0.7
Mood : heroic, powerful, hopeful
Quality
Entropy : 6.45
Noise : 108
Prompt Clip Score : 0.30
AI Evaluation
Likelihood of AI : 0.30
Image errors : Minor banding in the sky, some pixelation in the city background.
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 0.25, 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 0.525, 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 0.08, which is considered very good. This means that the generated image’s aesthetic closely matched the expected aesthetic described in the prompt.
Overall, the model demonstrated a good understanding of the scene and shot composition, but struggled with accurately capturing the intended camera position. The aesthetic of the generated image was very close to the expected 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://openai.com/index/dall-e-3/