AI Captures the Emotion, But Misses the Angle: A Look at Facial Expressions in AI-Generated Images with Leonardo-ai
- 9 minutes read - 1814 wordsTable of Contents
Facial expressions are a powerful tool for conveying emotion and storytelling. In the realm of AI-generated imagery, capturing these nuances is crucial for creating compelling and relatable visuals. This study explores the capabilities of a generative AI model in depicting facial expressions across various scenes. While the model demonstrates a strong understanding of emotion, it faces challenges in accurately replicating camera angles, highlighting the ongoing evolution of AI in capturing the complexities of human expression.
Created with: leonardo-ai
Silhouetted Against the Storm: A Moment of Isolation and Power
A lone figure stands defiant on a windswept cliff, silhouetted against a dramatic stormy sky. The turbulent sea below churns with whitecaps, mirroring the emotional intensity of the scene. This powerful image evokes a sense of isolation and vulnerability, leaving the viewer to ponder the figure’s story.
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 stands on a cliff overlooking a wild and stormy sea, with dramatic clouds overhead.
Aesthetic Score : 0.8
Mood : dramatic, powerful, melancholic
Quality
Entropy : 6.46
Noise : 98
Prompt Clip Score : 0.29
AI Evaluation
Likelihood of AI : 0.10
Image errors : There are no noticeable image artifacts or errors.
Hero Stands Tall Amidst the Flames
A powerful image captures a superhero, possibly Superman, silhouetted against a burning cityscape. The dramatic contrast between the hero’s stoic figure and the destruction below evokes a sense of heroism and somber reflection.
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 stands in profile against a backdrop of a burning city skyline.
Aesthetic Score : 0.7
Mood : dramatic, heroic, apocalyptic
Quality
Entropy : 6.84
Noise : 98
Prompt Clip Score : 0.34
AI Evaluation
Likelihood of AI : 0.20
Image errors : Slight blurriness in some areas.
Man’s Outburst Ignites Tension in Dimly Lit Bar
A man’s heated outburst in a dimly lit bar creates a palpable sense of tension, his expression and pose radiating urgency and drama. The scene is focused on the man, capturing the intensity of the moment.
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 man is shouting in a bar, with other patrons behind him blurred in the background.
Aesthetic Score : 0.7
Mood : intense, dramatic, focused
Quality
Entropy : 6.67
Noise : 95
Prompt Clip Score : 0.31
AI Evaluation
Likelihood of AI : 0.20
Image errors : There is some slight noise and blur in the background, which may be due to a low light setting or a high ISO value.
The Gamer’s Focus: A Moment of Intense Concentration
A young man, lost in the digital world, sits in a dimly lit room, his eyes glued to the screen. The image captures the intensity and determination of a gamer fully immersed in their game, creating a sense of suspense and anticipation.
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 man is sitting at a desk in a dimly lit room, wearing a headset and looking intently at a computer screen. The screen is displaying a game, and the man is typing on a keyboard.
Aesthetic Score : 0.7
Mood : intense, focused, serious
Quality
Entropy : 6.25
Noise : 89
Prompt Clip Score : 0.26
AI Evaluation
Likelihood of AI : 0.10
Image errors : Some minor noise in the shadows and some slight blurring around edges.
Lost in Thought: A Moment of Solitude at the Cafe
A woman sits alone at a cafe table, her gaze lost in the window. The soft lighting and her pensive posture evoke a sense of quiet contemplation, while the blurred figure behind her hints at a world she’s momentarily left behind.
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 sits alone at a table in a coffee shop, staring out the window. Another person is visible in the background, sitting at a separate table. The cafe has a warm and inviting atmosphere, with wooden tables and chairs, a teal-colored banquette and large windows that let in natural light.
Aesthetic Score : 0.6
Mood : pensive, contemplative, quiet
Quality
Entropy : 6.72
Noise : 99
Prompt Clip Score : 0.30
AI Evaluation
Likelihood of AI : 0.20
Image errors : No notable errors
Lost in the Shadows
A solitary figure, cloaked in darkness, emerges from the urban labyrinth. The stark contrast of light and shadow creates a sense of mystery and intrigue, drawing the viewer into the heart of the city’s underbelly.
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 in a black leather jacket stands in a dimly lit alleyway with graffiti on the walls. The man is looking off to the side, and his face is partially shadowed.
Aesthetic Score : 0.6
Mood : mysterious, edgy, urban
Quality
Entropy : 6.58
Noise : 100
Prompt Clip Score : 0.25
AI Evaluation
Likelihood of AI : 0.30
Image errors : No obvious image errors
What’s Got Them So Intrigued?
Two men on a park bench, their expressions a mix of perplexity and intrigue, gaze towards something unseen. The lush greenery and blurred background add to the sense of mystery, leaving you wondering what has captured their attention.
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 : Two young men, possibly brothers, are sitting on a park bench. They are both looking away from each other, seemingly in an argument. The setting is a park, with lush greenery and a blurred background of people and trees.
Aesthetic Score : 0.6
Mood : tension, awkwardness, confusion
Quality
Entropy : 6.89
Noise : 105
Prompt Clip Score : 0.26
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image appears to be slightly overexposed, resulting in a loss of detail in the highlights. There is also some noise present in the image.
Lost in the Code: A Moment of Intense Focus
A young man sits hunched over his computer, his face illuminated by the screen’s glow. The dimly lit room adds to the dramatic atmosphere, highlighting his intense concentration as he navigates the digital world.
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 man, likely a gamer, is sitting at his computer in a dimly lit room, his face contorted in an expression of intense focus and frustration, possibly while playing a video game.
Aesthetic Score : 0.7
Mood : intense, focused, frustrated
Quality
Entropy : 6.22
Noise : 90
Prompt Clip Score : 0.28
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image appears to have minor artifacts and noise, particularly in the shadows.
Lost in the City’s Symphony
A solitary figure, cloaked in leather, navigates the bustling urban landscape. The blur of the crowd amplifies his isolation, creating a poignant atmosphere of contemplation and quiet introspection.
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 on a city street, with other people in the background, the street is wet and there are some puddles. There are buildings on both sides of the street.
Aesthetic Score : 0.6
Mood : urban, solitary, contemplative
Quality
Entropy : 6.71
Noise : 103
Prompt Clip Score : 0.27
AI Evaluation
Likelihood of AI : 0.10
Image errors : The image is slightly blurry, especially the people in the background. Some of the people are not well-defined, they look more like an out-of-focus mass.
Lost in the City Lights: A Moment of Contemplation
A man, silhouetted against the vibrant cityscape, gazes out a window, lost in thought. The urban landscape, illuminated by a million twinkling lights, creates a sense of isolation and contemplation, capturing a moment of quiet reflection amidst the bustling city.
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 man is looking out a window at a city skyline at night. The city lights are blurred in the background. The man is in the foreground, in focus, and has a serious expression on his face.
Aesthetic Score : 0.7
Mood : introspective, pensive, contemplative
Quality
Entropy : 6.34
Noise : 87
Prompt Clip Score : 0.26
AI Evaluation
Likelihood of AI : 0.10
Image errors : The image has a bit of noise in the shadows and some overexposure in the highlights.
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 0.31, 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 0.56, 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 0.02, which is considered very good. This means that the generated image closely matched the expected aesthetic style.
Overall, the model demonstrates a good understanding of the scene and shot composition, but needs improvement in accurately capturing the intended camera position. The aesthetic quality of the generated image is very good.
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://leonardo.ai