AI's Facial Expressions: A Mixed Bag of Success with Midjourney
- 9 minutes read - 1847 wordsTable of Contents
Facial expressions are a powerful tool for conveying emotions and intentions. In the realm of generative AI, the ability to create realistic and expressive faces is a crucial step towards generating truly immersive and engaging content. This blog post explores the capabilities of a generative AI model in capturing the nuances of facial expressions across a range of scenes and contexts. We’ll examine the model’s performance in terms of understanding camera position, scene analysis, and aesthetic style, highlighting both its strengths and limitations.
Created with: midjourney
Intense Gaze: A Man’s Anger Fills the Frame
A close-up shot captures the raw emotion of a man’s anger, his eyes burning with intensity. The dramatic framing and serious expression create a palpable sense of tension, leaving the viewer questioning what lies behind this powerful gaze.
Prompt
Disagreement Frowning, furrowed brow, determined: Melancholy, isolated, conflicted ; people; eye-level; close-up; Single Person; cinematic
Characteristic
Shot : Close-up of a man’s face with an angry expression. The image is in black and white, and the man’s eyes are narrowed.
Aesthetic Score : 0.3
Mood : intense, angry, aggressive
Quality
Entropy : 6.81
Noise : 116
Prompt Clip Score : 0.23
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image has a bit of a blurry effect, and the skin texture looks a little artificial.
Superman’s Gaze: Intensity Meets Heroism
A close-up shot captures Superman’s determined face, his gaze intense as he surveys a cityscape engulfed in flames. The dramatic lighting and smoke create a powerful sense of urgency and heroism.
Prompt
Disagreement Concerned, determined, resolute: Urgent, conflicted, determined ; A superhero; close-up; eye-level; Hero; City skyline with smoke and flames; cinematic
Characteristic
Shot : A man in a superhero costume with a determined expression stares into the camera. A cityscape is in the background, and an explosion or fire is happening in the foreground.
Aesthetic Score : 0.6
Mood : intense, heroic, dramatic
Quality
Entropy : 6.45
Noise : 106
Prompt Clip Score : 0.21
AI Evaluation
Likelihood of AI : 0.70
Image errors : The image has a slight pixelation and some artifacts in the background. The fire and smoke are a bit too uniform and lack detail.
Caught in the Crossfire: Restaurant Argument Erupts
A couple’s heated argument unfolds in a crowded restaurant, their yelling mouths capturing the raw intensity of the moment. The tight composition draws viewers into the intimate scene, leaving them to wonder what sparked the confrontation.
Prompt
Disagreement Angry, shouting, accusatory: 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 arguing at a restaurant table. The woman is shouting at the man and both are in a heated argument. There is another person blurred in the background.
Aesthetic Score : 0.5
Mood : intense, argumentative, frustrated
Quality
Entropy : 6.80
Noise : 88
Prompt Clip Score : 0.30
AI Evaluation
Likelihood of AI : 0.10
Image errors : The image has some minor artifacts, such as slight noise in the shadows and some chromatic aberration in the edges of the frame.
The Frustration is Palpable
A man, bathed in blue and red light, hunches over his keyboard, his face contorted in a grimace. The low-light and close-up framing amplify the intensity of his frustration, creating a palpable sense of tension.
Prompt
Disagreement Frustrated, concentrated, determined: 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 is playing a video game. He is wearing a headset and is looking intensely at the screen. He is gripping the keyboard with both hands, and his mouth is open in a yell. The lighting is dark, but the man is illuminated by a blue and red glow.
Aesthetic Score : 0.5
Mood : intense, focused, frustrated
Quality
Entropy : 6.30
Noise : 105
Prompt Clip Score : 0.16
AI Evaluation
Likelihood of AI : 0.30
Image errors : The image has some minor image errors. The edges of the image are slightly blurred. The lighting is also not perfect. There is a lot of blue light reflecting on the man’s face.
A Moment of Melancholy in the Cafe
A young woman sits alone in a dimly lit cafe, her concerned expression and the phone in her hand hinting at a difficult conversation. The intimate atmosphere and soft lighting create a sense of melancholy, drawing the viewer into her private moment.
Prompt
Disagreement Sad, blank, uninterested: 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 woman is sitting alone at a cafe table, talking on a phone. She is looking down at the phone with a serious expression.
Aesthetic Score : 0.7
Mood : pensive, melancholic, contemplative
Quality
Entropy : 6.67
Noise : 77
Prompt Clip Score : 0.21
AI Evaluation
Likelihood of AI : 0.20
Image errors : There is some noise in the image, particularly in the shadows.
Shadows and Secrets: A Man in the Dark Alley
A solitary figure, cloaked in darkness, stands in a shadowy alleyway. His serious expression and the play of light and shadow create an atmosphere of mystery and intrigue. This image evokes a sense of danger and the unknown, leaving the viewer to wonder what secrets lie hidden in the darkness.
Prompt
Disagreement Determined, focused, serious: 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 jacket is standing in a dark alleyway, looking over his shoulder at the camera.
Aesthetic Score : 0.7
Mood : mysterious, moody, intense
Quality
Entropy : 5.72
Noise : 70
Prompt Clip Score : 0.19
AI Evaluation
Likelihood of AI : 0.10
Image errors : There are no visible artifacts or errors in the image.
Anger Erupts in the Park
A tense moment unfolds as a woman unleashes her fury in a public park, her yelling and dramatic gestures drawing attention from the surrounding group. The close-up framing intensifies the emotional intensity of the scene.
Prompt
Disagreement Angry, shouting, gesturing: 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 : Four people are arguing in a park. The woman in the center is yelling with her mouth open, while the other three people are looking at her with different expressions.
Aesthetic Score : 0.5
Mood : intense, confrontational, dramatic
Quality
Entropy : 6.82
Noise : 91
Prompt Clip Score : 0.23
AI Evaluation
Likelihood of AI : 0.20
Image errors : There are no significant image errors.
The Thrill of Victory: Gamer’s Raw Emotion Captured in a Single Shot
A young man, bathed in the glow of his monitor, screams in pure excitement as he experiences a pivotal moment in his video game. The intensity of his emotion is palpable, his wide eyes and raised fist conveying the sheer joy of victory. This image captures the raw, unfiltered passion of gaming, a moment of pure exhilaration frozen in time.
Prompt
Disagreement Angry, frustrated, defeated: 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 man is sitting in front of a computer, yelling in excitement. He is likely playing a video game. The scene is lit with neon lights, creating a dynamic and energetic atmosphere.
Aesthetic Score : 0.7
Mood : intense, exciting, victorious
Quality
Entropy : 6.55
Noise : 64
Prompt Clip Score : 0.22
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image has some noise and artifacts in the background, particularly around the monitors.
Lost in the City’s Blur
A solitary figure, shrouded in a black jacket, walks through a bustling city street, his head down, lost in thought. The blurred background emphasizes his isolation and the somber mood of the scene.
Prompt
Disagreement Sad, defeated, withdrawn: 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 in a black jacket is walking down a city street. The man is looking down and the background is blurred. The image is in a blue tone.
Aesthetic Score : 0.6
Mood : melancholy, lonely, somber
Quality
Entropy : 5.98
Noise : 83
Prompt Clip Score : 0.20
AI Evaluation
Likelihood of AI : 0.10
Image errors : The image is slightly overexposed and the background is out of focus, likely due to the low lighting.
Silhouetted Against the City Lights
A lone figure stands on a rooftop, their silhouette stark against the dazzling cityscape. The scene evokes a sense of mystery, solitude, and contemplation, with the urban backdrop adding a touch of drama.
Prompt
Disagreement Concerned, thoughtful, determined: 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 lone figure stands on a rooftop overlooking a city skyline at night. The city lights are blurred in the background, creating a dreamy effect.
Aesthetic Score : 0.7
Mood : melancholy, solitude, urban
Quality
Entropy : 6.67
Noise : 111
Prompt Clip Score : 0.21
AI Evaluation
Likelihood of AI : 0.60
Image errors : The city lights in the background appear slightly pixelated. There is also some blurriness in the foreground, particularly on the rooftop surface.
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 0.15, 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 0.455, which is considered good. This means the model was able to understand the scene described in the prompt and create an image that reflects it reasonably well.
- Aesthetic Analysis: The model scored 0.16, which is considered very good. This means the generated image closely matched the expected aesthetic style.
Overall, the model seems to be better at understanding the scene and achieving the desired aesthetic than accurately representing the camera position.
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