AI's Facial Expressions: A Mixed Bag of Emotions with Midjourney
- 9 minutes read - 1806 wordsTable of Contents
In the realm of artificial intelligence, the ability to generate realistic and expressive images is a coveted skill. One area of particular interest is the creation of facial expressions, which can convey a wide range of emotions and enhance the storytelling potential of AI-generated content. This blog post delves into the performance of a generative AI model in creating images with specific facial expressions, camera positions, and scenes. We’ll explore the model’s strengths and weaknesses, highlighting its ability to capture the nuances of human emotion through visual representation.
Created with: midjourney
Rainy Day Blues: A Moment of Contemplation
A young woman finds solace in a cafe, her gaze lost in the rain-streaked window. The scene evokes a sense of melancholy and introspection, capturing the quiet solitude of a rainy day.
Prompt
Worry Worry, furrowed brow, lip biting: melancholy, lonely ; Single woman; eye-level; Single Persons; dimly lit coffee shop with rain outside; cinematic
Characteristic
Shot : A young woman sits at a table in a cafe, looking out the window at the rainy street. A cup of coffee is on the table.
Aesthetic Score : 0.75
Mood : melancholy, contemplative, moody
Quality
Entropy : 6.29
Noise : 106
Prompt Clip Score : 0.26
AI Evaluation
Likelihood of AI : 0.20
Image errors : There are no visible artifacts or errors.
Shadowed Hero: A Silhouette of Determination
A lone figure in a vibrant red and black costume stands amidst the urban darkness, his gaze fixed on an unseen horizon. The low-key lighting casts long shadows, emphasizing the hero’s resolute expression and the mystery surrounding his mission.
Prompt
Worry Worry, determined, eyes narrowed: intense, burdened ; Man in a superhero costume; medium shot; Heroes; cityscape at night with flashing sirens; cinematic
Characteristic
Shot : A man in a red and black superhero costume stands in a city street at night, looking intensely at the camera. The background is blurred out with city lights and buildings in the distance.
Aesthetic Score : 0.6
Mood : intense, mysterious, dramatic
Quality
Entropy : 5.94
Noise : 97
Prompt Clip Score : 0.25
AI Evaluation
Likelihood of AI : 0.20
Image errors : No major errors, but the lighting is somewhat uneven.
Lost in the Blur: A Moment of Solitude on the Subway
A woman stands amidst the bustling chaos of a crowded subway, her gaze fixed on something beyond the frame. The blur of the background emphasizes her isolation, creating a poignant image of melancholy and contemplation.
Prompt
Worry Worry, nervous, fidgeting: anxious, overwhelmed ; Young woman in a crowded subway; eye-level; Normal People; blurred faces of commuters; cinematic
Characteristic
Shot : A young woman stands in a crowded subway car, looking out at the viewer. The background is blurred, creating a sense of motion and claustrophobia.
Aesthetic Score : 0.7
Mood : melancholy, introspective, uncertain
Quality
Entropy : 5.59
Noise : 92
Prompt Clip Score : 0.33
AI Evaluation
Likelihood of AI : 0.10
Image errors : Slight blurriness in the image, but it is likely intentional for effect.
Lost in the Code: A Young Man’s Intense Focus Under Colorful Light
A young man, headphones on, stares intently at a computer screen, his face bathed in vibrant, colorful light. The scene exudes a sense of focused intensity and seriousness, with the dramatic lighting drawing the viewer’s eye to the subject’s captivating expression.
Prompt
Worry Worry, concentrated, furrowed brow: intense, focused ; Gamer with headphones on; close-up; Gamer; dimly lit room with glowing computer screen; cinematic
Characteristic
Shot : A young man wearing headphones is looking intently at a computer screen. He is illuminated by a combination of blue and red light, creating a dramatic and moody atmosphere.
Aesthetic Score : 0.7
Mood : intense, focused, dramatic
Quality
Entropy : 5.66
Noise : 79
Prompt Clip Score : 0.28
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image is slightly grainy. This could be due to the low-light conditions in which the image was taken.
Autumn Tranquility: A Moment of Solitude
A lone figure finds peace amidst the vibrant hues of autumn. The image captures a sense of tranquility and melancholy, with the solitary figure silhouetted against a backdrop of golden leaves. The muted colors and the figure’s back-turned pose create a subtle dramatic effect, inviting contemplation of the beauty and fleeting nature of the season.
Prompt
Worry Worry, lost in thought, staring into the distance: sad, reflective ; Man sitting alone on a park bench; long shot; Single Persons; empty park with falling leaves; cinematic
Characteristic
Shot : A solitary figure sits on a bench in a park, with a backdrop of trees and fallen leaves. The scene is tranquil and slightly melancholic.
Aesthetic Score : 0.6
Mood : tranquil, melancholic, contemplative
Quality
Entropy : 6.92
Noise : 107
Prompt Clip Score : 0.27
AI Evaluation
Likelihood of AI : 0.20
Image errors : No visible artifacts or errors
Silhouette of Hope Amidst the Flames
A lone woman stands defiant on a rooftop, her calm presence a stark contrast to the fiery cityscape behind her. The setting sun casts an orange glow on the smoke-filled sky, creating a dramatic and melancholic scene of impending doom.
Prompt
Worry Worry, grim, jaw clenched: determined, resolute ; Heroine standing on a rooftop; medium shot; Heroes; cityscape with smoke and fire in the distance; cinematic
Characteristic
Shot : A woman stands in the foreground, silhouetted against a smoky cityscape with a building on fire in the background. The setting is likely a war-torn city.
Aesthetic Score : 0.7
Mood : dramatic, somber, apocalyptic
Quality
Entropy : 6.28
Noise : 89
Prompt Clip Score : 0.29
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image has some slight blurriness, particularly in the background, and the lighting appears a bit artificial.
Kitchen Confrontation: A Couple’s Heated Argument
A tense scene unfolds in a cluttered kitchen as a couple engages in a heated argument. The man stands with outstretched arms, while the woman faces him defensively, their angry expressions and dynamic poses amplifying the tension. The dramatic lighting illuminates their faces, highlighting the conflict brewing between them.
Prompt
Worry Worry, anger, tears: tense, frustrated ; Couple arguing in a kitchen; eye-level; Normal People; cluttered kitchen with dirty dishes; cinematic
Characteristic
Shot : A man and a woman are arguing in a kitchen. The man is wearing a black t-shirt and khaki pants, and the woman is wearing a red t-shirt and a black skirt. They are both standing with their arms outstretched, and they are both shouting. There is a kitchen counter behind them with a dishtowel hanging from a cabinet door.
Aesthetic Score : 0.6
Mood : angry, tense, dramatic
Quality
Entropy : 6.84
Noise : 111
Prompt Clip Score : 0.28
AI Evaluation
Likelihood of AI : 0.70
Image errors : The image is somewhat blurry, particularly in the background. Some of the edges in the image, such as the kitchen cabinets, are slightly pixelated.
The Dance of Fingers: Intensity in Every Keystroke
A close-up shot captures the focused energy of hands typing on a keyboard with vibrant backlighting. The computer monitor in the background adds to the digital atmosphere, creating a sense of intense concentration and the thrill of the digital world.
Prompt
Worry Worry, concentrated, sweating: intense, focused ; Gamer’s hands on a keyboard; close-up; Gamer; flashing lights and sounds from the game; cinematic
Characteristic
Shot : A person’s hands are typing on a keyboard with colorful lights, the background is blurred and shows a computer monitor and desk.
Aesthetic Score : 0.6
Mood : focused, intense, digital
Quality
Entropy : 6.42
Noise : 109
Prompt Clip Score : 0.23
AI Evaluation
Likelihood of AI : 0.10
Image errors : No significant errors, slight blurriness in the background.
Lost in the Shadows: A Woman’s Solitary Journey
A lone figure walks through a dimly lit, cobblestone street, her silhouette stark against the darkness. The scene evokes a sense of mystery and melancholy, leaving the viewer to ponder her story and destination.
Prompt
Worry Worry, scared, looking over her shoulder: lonely, vulnerable ; Woman walking alone at night; long shot; Single Persons; deserted street with streetlights; cinematic
Characteristic
Shot : A lone woman walks down a dark, narrow alleyway lit by dim lampposts.
Aesthetic Score : 0.7
Mood : mysterious, lonely, urban
Quality
Entropy : 6.03
Noise : 86
Prompt Clip Score : 0.29
AI Evaluation
Likelihood of AI : 0.20
Image errors : No noticeable artifacts or errors in the image.
Lone Soldier Amidst the Flames
A solitary soldier, clad in military garb, kneels on a battlefield, studying a map. The flickering flames of a distant fire cast an ominous glow, adding a sense of urgency and danger to the scene. His focused expression and the dramatic lighting create a palpable tension, hinting at the intensity of the moment.
Prompt
Worry Worry, thoughtful, furrowed brow: serious, strategic ; Hero looking at a map; medium shot; Heroes; war-torn battlefield with smoke and debris; cinematic
Characteristic
Shot : A soldier in a worn, brown uniform sits on the ground, intently studying a map. The setting is a battlefield, with a fire burning in the background. The image evokes a sense of urgency and seriousness.
Aesthetic Score : 0.7
Mood : serious, somber, urgent
Quality
Entropy : 6.45
Noise : 82
Prompt Clip Score : 0.33
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image has minimal noise in some areas, particularly in the shadows. The subject’s face appears slightly overexposed.
Conclusion
The results show that the generative AI model performed well in terms of 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 below the “good” range of 0.5 to 0.75. This suggests that the model didn’t fully capture the intended camera position described in the prompt.
- Shot Analysis: The model scored 0.42, also below the “good” range. This indicates that the model didn’t fully understand the scene described in the prompt and didn’t create an image that accurately reflects it.
- Aesthetic Analysis: The model scored 0.09, which is within the “very good” range of -0.2 to 0.1. This means the generated image’s aesthetic closely matched the expected aesthetic described in the prompt.
Overall, the model seems to be better at understanding the desired aesthetic than the scene and camera position. It might need further training to improve its ability to accurately interpret and translate camera positions and scene descriptions into images.
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