AI's Facial Expressions: A Mixed Bag of Success with Midjourney
- 9 minutes read - 1849 wordsTable of Contents
Facial expressions are a powerful tool in storytelling, conveying emotions and intentions without words. In the realm of AI, generating realistic and expressive faces is a challenging task. This analysis explores the capabilities of a generative AI model in creating images with specific facial expressions, focusing on its ability to understand scene descriptions, camera angles, and aesthetic styles. We’ll delve into the model’s strengths and weaknesses, providing insights into the current state of AI-generated facial expressions.
Created with: midjourney
Lost in the Neon Glow: A Solitary Figure Walks the Wet City Streets
A lone figure navigates the glistening, neon-drenched streets of a city at night. The dramatic lighting and sense of isolation create a mood that is both gloomy and mysterious, leaving the viewer wondering about the figure’s story.
Prompt
Contempt 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 lone man walks down a wet, neon-lit street in a city at night. The street is lined with buildings and reflects the colorful glow of the signs.
Aesthetic Score : 0.8
Mood : nostalgic, atmospheric, urban
Quality
Entropy : 6.37
Noise : 110
Prompt Clip Score : 0.24
AI Evaluation
Likelihood of AI : 0.90
Image errors : The image appears to be slightly blurry, particularly in the background.
Heroic Silhouette Against a Fiery Sky
A superhero, cloaked in red, stands tall on a rooftop, silhouetted against a breathtaking sunset. The vibrant orange and red hues of the sky create a dramatic backdrop, emphasizing the hero’s power and the epic scale of the scene.
Prompt
Contempt 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 superhero standing on a rooftop overlooking a cityscape at sunset
Aesthetic Score : 0.6
Mood : dramatic, epic, hopeful
Quality
Entropy : 6.40
Noise : 105
Prompt Clip Score : 0.28
AI Evaluation
Likelihood of AI : 0.80
Image errors : Some of the buildings in the background appear blurry and the overall image seems to be slightly overexposed.
The Weight of Decisions: A Man’s Pensive Walk Through a Corporate Labyrinth
A man in a suit navigates a dimly lit office, his posture heavy with contemplation. The atmosphere is thick with tension, hinting at a weighty decision looming ahead. The lighting and his somber demeanor create a sense of mystery, leaving the viewer to wonder what secrets lie within the shadows.
Prompt
Contempt 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 down a corporate office hallway. The background is blurry, focusing the attention on the man.
Aesthetic Score : 0.6
Mood : serious, corporate, professional
Quality
Entropy : 6.45
Noise : 105
Prompt Clip Score : 0.25
AI Evaluation
Likelihood of AI : 0.20
Image errors : Slight noise visible in the image, especially in the shadows.
Lost in the Glow: A Young Man’s Intense Focus
A young man sits hunched over his keyboard, bathed in a vibrant pink and red light. The dramatic lighting casts him into a world of mystery and intrigue, highlighting his intense focus and the unknown depths of his digital realm.
Prompt
Contempt 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 man is sitting at his desk in a dimly lit room, focused on a computer screen. The room is lit with red and purple lights.
Aesthetic Score : 0.6
Mood : intense, focused, dark
Quality
Entropy : 6.24
Noise : 111
Prompt Clip Score : 0.23
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image has some noise and artifacts, particularly in the shadows.
Lost in the Rain: A Moment of Melancholy
A young woman finds solace in contemplation as she watches the rain fall, her wistful gaze reflecting a sense of distance and isolation. The raindrops on the windowpane create a poignant visual metaphor for her inner state.
Prompt
Contempt 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 young woman is sitting at a table in a cafe looking out the window. The window is wet with rain and there are lights visible through the window.
Aesthetic Score : 0.7
Mood : melancholy, contemplative, wistful
Quality
Entropy : 6.60
Noise : 98
Prompt Clip Score : 0.27
AI Evaluation
Likelihood of AI : 0.20
Image errors : There is some noise in the image, especially in the shadows.
Lost in the Fog: A Figure Walks into the Unknown
A solitary figure navigates a shadowy alleyway shrouded in mist, the faint glow of a distant light hinting at a mystery waiting to unfold. This noir-inspired scene evokes a sense of suspense and intrigue, leaving the viewer wondering what secrets lie ahead.
Prompt
Contempt 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 lone figure walks down a dark, narrow alleyway, shrouded in fog and rain, with a single lamppost illuminating the scene from above.
Aesthetic Score : 0.7
Mood : mysterious, suspenseful, noir
Quality
Entropy : 5.83
Noise : 78
Prompt Clip Score : 0.25
AI Evaluation
Likelihood of AI : 0.70
Image errors : The image exhibits slight blurriness and graininess, particularly in the background. The fog and rain seem somewhat artificial and lack depth.
Lost in the Crowd: A Moment of Melancholy in the Mall
A woman, shrouded in a tan jacket, stands amidst the bustling chaos of a shopping mall. The shallow depth of field blurs the surrounding crowd, isolating her in a moment of quiet contemplation. Her expression speaks of a pensive mood, hinting at a story waiting to be told.
Prompt
Contempt 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 woman stands in a crowded shopping mall with her arms crossed, looking slightly annoyed. There are other people in the background, but they are blurred.
Aesthetic Score : 0.6
Mood : melancholy, thoughtful, pensive
Quality
Entropy : 6.18
Noise : 93
Prompt Clip Score : 0.25
AI Evaluation
Likelihood of AI : 0.10
Image errors : There is some graininess in the image.
Lost in the Game: A Young Man’s Intense Battle
A young man, covered in fake blood, is fully immersed in a video game. The intense expression on his face and the explosions in the background create a sense of drama and excitement, highlighting the gritty and immersive nature of the game.
Prompt
Contempt 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 : A young man, covered in fake blood, is intensely focused on playing a video game. The scene is set in a dimly lit room with a gaming monitor in the background.
Aesthetic Score : 0.5
Mood : intense, dramatic, edgy
Quality
Entropy : 6.50
Noise : 94
Prompt Clip Score : 0.26
AI Evaluation
Likelihood of AI : 0.80
Image errors : The image has some minor artifacts, such as a slight blur on the gaming monitor.
Silhouetted in the Setting Sun: A Moment of Solitude
A solitary figure walks through a park bathed in the golden light of the setting sun. The man’s silhouette against the fading light evokes a sense of melancholy and contemplation, highlighting the themes of loneliness and isolation.
Prompt
Contempt 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 solitary figure walks through a park, silhouetted against the setting sun, the shadows of trees stretching out around him.
Aesthetic Score : 0.7
Mood : melancholy, contemplative, lonely
Quality
Entropy : 6.42
Noise : 107
Prompt Clip Score : 0.26
AI Evaluation
Likelihood of AI : 0.10
Image errors : The image has some slight graininess, which is common in older photographs. There’s also a little bit of blurring around the edges.
The Last Stand: A Soldier’s Haunting Solitude in a Battlefield of Despair
A lone soldier stands amidst the carnage of a war-torn field, his stoic expression a stark contrast to the grim reality surrounding him. The scene evokes a haunting sense of loss and the weight of sacrifice, leaving a lasting impression of the devastating consequences of conflict.
Prompt
Contempt 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 lone soldier stands amidst a battlefield, with fallen comrades scattered around him. The scene is grim and desolate, with a sense of heavy loss and quiet reflection.
Aesthetic Score : 0.7
Mood : grim, somber, reflective
Quality
Entropy : 6.97
Noise : 114
Prompt Clip Score : 0.26
AI Evaluation
Likelihood of AI : 0.00
Image errors : No visible artifacts or errors
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 0.15, indicating a fairly low ability to accurately represent the camera position described in the prompt. This suggests the model may not be very good at understanding and implementing specific camera angles.
- Shot Analysis: The model scored 0.5, indicating a good ability to understand the scene described in the prompt. This means the model was able to create an image that generally matched the scene described, but there may be some discrepancies in details.
- Aesthetic Analysis: The model scored 0.08, indicating a very good ability to match the expected aesthetic of the image. This means the image created by the model closely aligns with the desired aesthetic style.
Overall, the model shows promise in understanding the scene and achieving the desired aesthetic, but needs improvement in accurately representing camera positions.
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://midjourney.com