AI Captures the Emotion, But Misses the Angle: A Look at Facial Expressions in AI-Generated Images with Scenario
- 10 minutes read - 2013 wordsTable of Contents
Dramatic facial expressions are a powerful tool in storytelling, conveying a wide range of emotions and adding depth to characters. From the subtle twitch of a brow to a full-blown scream, these expressions can draw the viewer in and create a visceral connection. In the realm of generative AI, the ability to capture these nuances is a key indicator of progress. This blog post explores a recent experiment that tested the capabilities of an AI model in generating images with expressive faces, focusing on the interplay between emotion, camera position, and aesthetic style.
Created with: scenario
Lost in the Neon Rain
A solitary figure in a trench coat stands amidst the deserted, neon-lit alleyway, the wet streets reflecting the flickering lights. The scene evokes a sense of mystery, urban solitude, and melancholic beauty.
Prompt
facial-expressions Contempt: Alienation, isolation, detachment ; A lone figure, back turned to the camera; eye-level; Single Person; A bustling city street at night, neon signs reflecting in puddles; cinematic
Characteristic
Shot : A woman in a trench coat stands alone in a dimly lit, wet city street. Neon signs reflect off the wet pavement.
Aesthetic Score : 0.7
Mood : melancholy, mysterious, urban
Quality
Entropy : 6.65
Noise : 120
Prompt Clip Score : 0.26
AI Evaluation
Likelihood of AI : 0.80
Image errors : The image shows some technical errors: slight blurriness in some areas, and some unnatural reflections, especially on the woman’s coat.
Sunset Silhouette: A Woman of Mystery
A captivating image of a woman in a sleek black leather outfit, perched on a rooftop overlooking a city bathed in the golden hues of sunset. Her confident pose and the dramatic cityscape behind her evoke a sense of mystery and allure.
Prompt
facial-expressions Contempt: Disillusionment, weariness, cynicism ; A superhero, standing on a rooftop, looking down at the city; eye-level; Hero; A cityscape bathed in the golden light of sunset; cinematic
Characteristic
Shot : A woman in black leather pants and a top, sits on a rooftop overlooking a city skyline. The sun is setting, casting a warm glow over the scene.
Aesthetic Score : 0.7
Mood : urban, mysterious, sensual
Quality
Entropy : 6.65
Noise : 88
Prompt Clip Score : 0.27
AI Evaluation
Likelihood of AI : 0.80
Image errors : The image has a slight airbrush effect, which makes it look somewhat artificial.
A Man in Blue, Stepping Through Time
A solitary figure in a sharp blue suit navigates a bustling 1970s or 1980s office, the scene bathed in dramatic lighting and a sense of corporate seriousness. The blurred background and focused lighting draw the viewer’s eye to the man, creating a sense of mystery and nostalgia.
Prompt
facial-expressions Contempt: Apathy, boredom, resignation ; A man in a suit, walking through a crowded office; eye-level; Normal People; A sterile, corporate office environment, fluorescent lights casting harsh shadows; cinematic
Characteristic
Shot : A man in a suit walks through a busy office, his back to the viewer, with a slightly dramatic pose. It is likely a depiction of a corporate environment.
Aesthetic Score : 0.7
Mood : serious, confident, professional
Quality
Entropy : 6.68
Noise : 107
Prompt Clip Score : 0.25
AI Evaluation
Likelihood of AI : 0.80
Image errors : The image appears to be a painting, which might be intentional. However, the brushstrokes are visible and create a slightly artificial look. The image has a digital feel, and some details are slightly blurred.
Lost in a Digital Dream: A Gamer’s Journey Through a Mystical Portal
A young woman, captivated by the screen, navigates a fantastical world. The mysterious portal on her computer screen beckons, promising adventure and intrigue. This image captures the allure of digital escapism and the thrill of the unknown.
Prompt
facial-expressions Contempt: Obsessive, detached, nihilistic ; A gamer, hunched over a computer screen, eyes glued to the monitor; eye-level; Gamer; A dimly lit room, cluttered with gaming paraphernalia; cinematic
Characteristic
Shot : A young woman wearing headphones sits in front of a computer, focused on the screen, a gaming setup is visible
Aesthetic Score : 0.7
Mood : focused, determined, immersed
Quality
Entropy : 6.77
Noise : 91
Prompt Clip Score : 0.23
AI Evaluation
Likelihood of AI : 0.80
Image errors : Some slight artifacts are visible in the woman’s hair and skin, particularly around the edges. The lighting on the face appears slightly unnatural.
Rainy Day Blues: A Moment of Contemplation
A young woman finds herself lost in thought at a cafe, the rain outside mirroring the melancholy in her eyes. Her solitary figure and the empty cup of coffee suggest a moment of wistful reflection, capturing the essence of loneliness and longing.
Prompt
facial-expressions Contempt: Melancholy, loneliness, disillusionment ; A woman, sitting alone in a cafe, staring out the window; eye-level; Single Person; A rainy day, the cafe filled with the sound of rain and chatter; cinematic
Characteristic
Shot : A woman sits alone at a table in a cafe, looking out the window at the rainy street. There is a cup of coffee on the table in front of her.
Aesthetic Score : 0.8
Mood : melancholy, pensive, serene
Quality
Entropy : 6.84
Noise : 100
Prompt Clip Score : 0.30
AI Evaluation
Likelihood of AI : 0.90
Image errors : The woman’s skin has a slightly plastic-looking quality, and the background is somewhat blurry. There are no obvious errors in the image.
Mystery in the Shadows: A Woman’s Silhouette in a Dark Alley
A captivating image of a woman in a leather jacket, bathed in the ethereal glow of a single street lamp, evokes a sense of mystery and intrigue. The dramatic lighting and her enigmatic pose create a cool, urban atmosphere, leaving the viewer wondering about her story.
Prompt
facial-expressions Contempt: Superiority, arrogance, disdain ; A hero, standing over a defeated villain, looking down with disdain; not too close; Hero; A dark, gritty alleyway, lit by flickering streetlights; cinematic
Characteristic
Shot : A young woman in a leather jacket is standing in a narrow alleyway. There is a street lamp in the background, and the alleyway is lined with brick buildings. The image is in black and white.
Aesthetic Score : 0.8
Mood : mysterious, urban, cool
Quality
Entropy : 6.66
Noise : 115
Prompt Clip Score : 0.18
AI Evaluation
Likelihood of AI : 0.80
Image errors : The image has a slight amount of digital noise, particularly around the edges of the woman’s hair. The overall texture could be more organic.
Lost in the Mall: A Moment of Mystery
A close-up shot captures a group of individuals navigating a bustling shopping mall. The blurred background and diverse gazes create a sense of intrigue, leaving the viewer to ponder their stories and motivations. The image evokes a calm and contemplative mood, hinting at a subtle mystery unfolding within the everyday chaos.
Prompt
facial-expressions Contempt: Indifference, apathy, boredom ; A group of people, standing in a queue, looking bored and apathetic; eye-level; Normal People; A sterile, modern shopping mall, filled with the sounds of chatter and music; cinematic
Characteristic
Shot : A group of people standing in a shopping mall. The image is a close-up of the faces of the people, and the background is blurred.
Aesthetic Score : 0.7
Mood : melancholy, contemplative, somber
Quality
Entropy : 6.69
Noise : 104
Prompt Clip Score : 0.25
AI Evaluation
Likelihood of AI : 0.90
Image errors : The image is slightly blurry and has a few artifacts.
Tension Rises in Grayscale Comic Panel
A dramatic grayscale comic panel depicts a tense situation between two characters. The woman on the top panel appears concerned and ready for action, while the man below struggles with a device, hinting at a possible injury or conflict. The close-ups on their faces, dramatic lighting, and grayscale palette create a sense of suspense and urgency.
Prompt
facial-expressions Contempt: Desensitization, aggression, detachment ; A gamer, playing a violent video game, his face contorted in a grimace; not too close; Gamer; A dimly lit room, filled with the sounds of explosions and gunfire; cinematic
Characteristic
Shot : Two young people, a woman and a man, appear to be in some kind of a futuristic transport, or possibly a space ship or an escape pod; a window reveals a foggy background
Aesthetic Score : 0.7
Mood : intense, dramatic, suspenseful
Quality
Entropy : 6.46
Noise : 104
Prompt Clip Score : 0.21
AI Evaluation
Likelihood of AI : 0.80
Image errors : There are some artifacts in the image, such as the fog and smoke. The rendering of the characters’ hair is also a bit rough
Solitary Stroll Through a Hazy Afternoon
A man, shrouded in the long shadows of a sun-drenched park, walks down a path towards the horizon. The peaceful atmosphere and the mystery of his destination create a contemplative mood, inviting you to wonder about his journey.
Prompt
facial-expressions Contempt: Despair, loneliness, isolation ; A man, walking through a deserted park, his face etched with sadness; eye-level; Single Person; A park at dusk, the trees casting long shadows; cinematic
Characteristic
Shot : A lone man walks down a path in a park on a foggy day, with trees lining the path and lamp posts in the distance. The path is lit by the sun, casting long shadows.
Aesthetic Score : 0.7
Mood : melancholy, solitude, contemplative
Quality
Entropy : 6.77
Noise : 115
Prompt Clip Score : 0.27
AI Evaluation
Likelihood of AI : 0.60
Image errors : The image appears to be slightly blurry in some areas, particularly in the background. Some of the textures, like the ground and trees, look a little artificial.
Hope Amidst the Ruins: A Warrior’s Resolve
A young woman in armor stands defiant in a war-torn field, her gaze fixed on the horizon. The burning tank and distant soldiers paint a picture of destruction, yet her determined expression offers a glimmer of hope amidst the chaos.
Prompt
facial-expressions Contempt: Disillusionment, cynicism, weariness ; A hero, standing on a battlefield, surrounded by the carnage of war; not too close; Hero; A battlefield, littered with the bodies of fallen soldiers; cinematic
Characteristic
Shot : A young woman in armor looks up towards a burning tank with a somber expression on her face, the scene is a battlefield with soldiers in the background.
Aesthetic Score : 0.7
Mood : somber, dramatic, heroic
Quality
Entropy : 6.89
Noise : 106
Prompt Clip Score : 0.23
AI Evaluation
Likelihood of AI : 0.70
Image errors : The image has some artifacts and blurriness in the background, particularly around the soldiers. The lighting is a bit uneven, causing some areas to be overexposed.
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 0.25, 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 0.6, 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://www.scenario.com