AI's Facial Expressions: A Mixed Bag of Success with Midjourney
- 9 minutes read - 1915 wordsTable of Contents
Facial expressions are a powerful tool in storytelling, conveying emotions and intentions without words. In the realm of AI-generated imagery, capturing these nuances accurately is crucial for creating compelling and relatable scenes. This blog post delves into the performance of a generative AI model in understanding and generating facial expressions across various scenes. We’ll explore its strengths and weaknesses, analyzing its ability to capture the essence of a scene and its aesthetic, while examining its struggles with camera position. Join us as we uncover the fascinating world of AI-generated facial expressions and their potential to enhance storytelling.
Created with: midjourney
Lost in the Neon Glow: A Silhouette of Solitude
A lone figure walks through a rain-soaked, neon-lit city street, their silhouette stark against the vibrant cityscape. The bustling background and dramatic lighting create a sense of urban energy and isolation, capturing a futuristic mood of solitude.
Prompt
Skepticism Skeptical, resigned: Melancholy, disillusioned ; A lone figure, back turned, walking away from a brightly lit city skyline; eye-level; Single Person; Urban, neon signs, bustling crowds; cinematic
Characteristic
Shot : A lone figure walks down a busy, wet city street at night, surrounded by neon lights and blurred crowds.
Aesthetic Score : 0.7
Mood : lonely, urban, futuristic
Quality
Entropy : 6.52
Noise : 90
Prompt Clip Score : 0.23
AI Evaluation
Likelihood of AI : 0.80
Image errors : The image appears to be AI-generated, with some slight blurring and artifacts around the edges of the figure and the city lights.
Hope Amidst the Ashes: A Lone Figure Stands Against the Burning City
A solitary figure, cloaked in red, stands defiant on a rooftop overlooking a city consumed by flames. The smoke, billowing and obscuring the cityscape, creates a sense of apocalyptic despair. Yet, the figure’s presence, bathed in the fiery glow, offers a glimmer of hope amidst the destruction.
Prompt
Skepticism Frowning, questioning: Doubtful, conflicted ; A superhero, cape billowing, standing on a rooftop, looking down at a city in chaos; eye-level; Hero; Smoke, fire, destruction; cinematic
Characteristic
Shot : A lone figure in a red cape stands on the edge of a rooftop overlooking a burning city.
Aesthetic Score : 0.7
Mood : dark, heroic, ominous
Quality
Entropy : 6.65
Noise : 107
Prompt Clip Score : 0.29
AI Evaluation
Likelihood of AI : 0.80
Image errors : Some blurring in the background, potentially from post processing.
A Moment of Reflection: Mystery in the Cafe
A young woman with brown hair and glasses, lost in the pages of a newspaper, exudes an air of thoughtful observation. Her expression, tinged with a hint of mystery, draws the viewer into her world, leaving them wondering what secrets she holds.
Prompt
Skepticism Rolling eyes, skeptical smirk: Cynical, disbelieving ; A woman, dressed in everyday clothes, holding a newspaper with a sensational headline; eye-level; Normal People; Coffee shop, people going about their day; cinematic
Characteristic
Shot : A young woman is reading a newspaper in a coffee shop. The background is blurred and the woman is the main focus of the image.
Aesthetic Score : 0.7
Mood : thoughtful, contemplative, casual
Quality
Entropy : 6.94
Noise : 105
Prompt Clip Score : 0.30
AI Evaluation
Likelihood of AI : 0.10
Image errors : No noticeable errors
The Weight of Decision: A Late Night of Focus
A young man sits bathed in the glow of his computer screen, his expression intense and focused. The dimly lit room and scattered remnants of a late-night meal add to the sense of urgency and mystery surrounding his task. What decision is he about to make? What secrets lie hidden in the digital shadows?
Prompt
Skepticism Squinting, furrowed brow: Suspicious, wary ; A gamer, hunched over a computer screen, surrounded by empty pizza boxes and energy drink cans; close-up; Gamer; Dark room, flashing lights, gaming peripherals; cinematic
Characteristic
Shot : A young man is sitting at a desk in a dimly lit room, looking intently at a computer screen. There are several cans and a pizza box on the desk in front of him.
Aesthetic Score : 0.7
Mood : intense, focused, introspective
Quality
Entropy : 6.00
Noise : 86
Prompt Clip Score : 0.22
AI Evaluation
Likelihood of AI : 0.30
Image errors : Slight graininess in the image, especially in the shadows.
Neon Shadows, Lonely Thoughts
A man sits alone at a bar, bathed in the glow of neon lights, a drink before him. Rain streaks the window behind him, mirroring the melancholy mood that hangs heavy in the air. The dramatic lighting highlights his solitary figure, lost in contemplation.
Prompt
Skepticism Lost in thought, questioning: Doubtful, introspective ; A man, sitting alone in a dimly lit bar, staring into his drink; eye-level; Single Person; Empty bar, flickering neon lights, rain outside; cinematic
Characteristic
Shot : A man sitting at a bar counter, looking at the camera with a contemplative expression. There is a glass of amber liquid on the counter. The scene is illuminated by neon lights in red and blue, creating a moody atmosphere. The background shows a city street at night, with rain falling on the window.
Aesthetic Score : 0.7
Mood : dark, brooding, mysterious
Quality
Entropy : 6.60
Noise : 103
Prompt Clip Score : 0.25
AI Evaluation
Likelihood of AI : 0.40
Image errors : Some noise is visible in the image, particularly in the shadows. The rain on the window looks a bit artificial.
Captain America: A Silhouette of Hope
A dramatic image captures Captain America standing tall, his back to the camera, facing a cheering crowd. The iconic hero, bathed in backlighting, creates a powerful silhouette, emphasizing his isolation and the gravity of the moment. This image evokes a sense of intensity, heroism, and the weight of responsibility.
Prompt
Skepticism Worried, conflicted: Uncertain, hesitant ; A hero, standing in front of a crowd, holding a weapon, but looking conflicted; eye-level; Hero; cheering crowd, bright lights, stage; cinematic
Characteristic
Shot : Captain America stands in front of a crowd of cheering fans, his back to the viewer, a weapon in his hand.
Aesthetic Score : 0.7
Mood : dramatic, powerful, heroic
Quality
Entropy : 6.41
Noise : 88
Prompt Clip Score : 0.26
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image is slightly overexposed, and there is some noise in the background.
A Moment of Shared Secrets
A group of friends gather around a table, bathed in warm light, their expressions hinting at a conversation filled with intimacy and intrigue. The soft focus and low-key lighting create a cozy atmosphere, leaving the viewer wondering what secrets they are sharing.
Prompt
Skepticism Raised eyebrows, smirks: Disbelieving, amused ; A group of friends, gathered around a table, listening to a story with skeptical expressions; eye-level; Normal People; Cozy living room, warm lighting, snacks; cinematic
Characteristic
Shot : A group of friends are sitting at a table, eating and talking. The scene is lit by warm, intimate light.
Aesthetic Score : 0.6
Mood : cozy, friendly, relaxed
Quality
Entropy : 6.42
Noise : 81
Prompt Clip Score : 0.25
AI Evaluation
Likelihood of AI : 0.10
Image errors : There are no significant errors in the image. The lighting is slightly uneven, but this adds to the overall mood of the scene.
In the Zone: Gamer’s Face Lit by the Glow of Victory
A young man is completely immersed in his video game, his face illuminated by the vibrant blue and red lights of his screen. His intense focus and serious expression tell a story of dedication and the thrill of the competition.
Prompt
Skepticism Grimacing, shaking head: Frustrated, doubtful ; A gamer, staring intently at a screen, but with a look of frustration; close-up; Gamer; Brightly lit room, gaming setup, controller in hand; cinematic
Characteristic
Shot : A young man is playing a video game. He is focused and intense, with his eyebrows furrowed and his eyes wide. The scene is lit with a combination of blue and orange light, which creates a dramatic and moody atmosphere.
Aesthetic Score : 0.6
Mood : intense, focused, dramatic
Quality
Entropy : 6.58
Noise : 105
Prompt Clip Score : 0.28
AI Evaluation
Likelihood of AI : 0.10
Image errors : The image has some noise and grain, but it’s not too distracting. There’s a slight blur around the edges of the image, which could be due to the camera lens or post-processing.
Lost in the City’s Blur
A solitary figure navigates the bustling urban landscape, her anonymity amplified by the motion blur that surrounds her. The scene evokes a sense of mystery and loneliness, leaving the viewer to ponder her story.
Prompt
Skepticism Nervous, wary: Paranoid, distrustful ; A woman, walking through a crowded street, looking around with suspicion; eye-level; Single Person; Busy city street, people rushing by, street vendors; cinematic
Characteristic
Shot : A young woman walks through a bustling city street. The crowd is blurred, making her stand out.
Aesthetic Score : 0.6
Mood : mysterious, urban, lonely
Quality
Entropy : 6.01
Noise : 93
Prompt Clip Score : 0.21
AI Evaluation
Likelihood of AI : 0.20
Image errors : Some slight motion blur is present, though it is a stylistic choice.
Lost in the City Lights: A Moment of Contemplation
A solitary figure stands on a rooftop, bathed in the soft blue glow of the night. The city lights twinkle in the distance, creating a sense of vastness and isolation. This evocative image captures a moment of melancholy contemplation in the heart of the urban landscape.
Prompt
Skepticism Sad, contemplative: Isolated, disillusioned ; A hero, standing on a rooftop, looking out at a city skyline, but with a sense of loneliness; eye-level; Hero; City lights, distant sounds of the city; cinematic
Characteristic
Shot : A solitary figure stands on a rooftop overlooking a city skyline at night. The city is lit up by the lights of the buildings, and the sky is a dark blue. The figure is silhouetted against the skyline, and the overall mood is one of loneliness and isolation.
Aesthetic Score : 0.8
Mood : loneliness, isolation, melancholy
Quality
Entropy : 6.65
Noise : 110
Prompt Clip Score : 0.24
AI Evaluation
Likelihood of AI : 0.90
Image errors : There are some slight artifacts in the image, particularly in the sky and the buildings. These are not very noticeable, but they are present.
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 it’s not very good at reacting to camera positions in the prompt. This suggests the generated image might not accurately reflect the intended camera angle or perspective.
- Shot Analysis: The model scored 0.46, which is considered good. This means the generated image is fairly close to the scene described in the prompt.
- Aesthetic Analysis: The model scored 0.04, which is considered very good. This means the generated image’s aesthetic is very close to the expected aesthetic.
Overall, the model seems to be better at understanding the scene and its aesthetic than it is at 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