AI's Facial Expressions: A Mixed Bag with Midjourney
- 9 minutes read - 1881 wordsTable of Contents
The ability to generate realistic facial expressions is a crucial aspect of creating compelling and engaging images. This blog post examines the performance of a generative AI model in this area, analyzing its ability to capture the nuances of facial expressions within various scenes and camera positions. We’ll explore how the model excels in capturing the overall aesthetic and shot composition, but struggles with accurately replicating the desired camera position. Through a series of examples, we’ll delve into the model’s strengths and weaknesses, providing insights into the current state of AI-generated facial expressions.
Created with: midjourney
A Moment of Whimsical Delight at the Carnival
A young woman, bathed in soft light, gazes up at a Ferris wheel, her floral dress swirling around her. The scene evokes a sense of joy, whimsy, and nostalgia, capturing the magic of a summer carnival.
Prompt
Amusement Smiling, laughing, eyes sparkling with amusement: Playful, carefree ; A lone woman; eye-level; Single Person; a bustling carnival with bright lights and colorful tents; cinematic
Characteristic
Shot : A young woman is smiling at the camera, standing in front of a Ferris wheel at a carnival. The background is blurred, creating a dreamy feel.
Aesthetic Score : 0.8
Mood : happy, playful, romantic
Quality
Entropy : 6.58
Noise : 105
Prompt Clip Score : 0.27
AI Evaluation
Likelihood of AI : 0.20
Image errors : There is some minor graininess in the image.
Superhero Smiles Bright at the Carnival
A costumed hero stands proudly before a vibrant carnival, radiating joy and playful energy. The Ferris wheel, rollercoaster, and carousel blur into a colorful backdrop, adding a touch of dramatic flair to this cheerful scene.
Prompt
Amusement Grinning, eyes full of joy, a mischievous twinkle: Exuberant, triumphant ; A superhero in a vibrant costume; eye-level; Hero; a crowded amusement park with roller coasters and Ferris wheels in the background; cinematic
Characteristic
Shot : A man dressed as a superhero stands in front of an amusement park with a Ferris wheel and roller coaster in the background. He is smiling and looking at the camera. The man is wearing a blue and red suit with a yellow star on the chest.
Aesthetic Score : 0.6
Mood : joyful, playful, whimsical
Quality
Entropy : 6.78
Noise : 79
Prompt Clip Score : 0.30
AI Evaluation
Likelihood of AI : 0.20
Image errors : No visible artifacts, but the image may be slightly over-sharpened.
Sun-Kissed Memories: Friends, Picnics, and a Carousel
A group of friends bask in the warm glow of a sunny afternoon, enjoying a carefree picnic in a park. The nostalgic charm of a carousel in the background adds a touch of whimsy to the scene, while the sunlight filtering through the trees creates a warm and inviting atmosphere.
Prompt
Amusement Smiling, laughing, enjoying each other’s company: Relaxed, happy ; A group of friends; eye-level; Normal People; a picnic blanket under a shady tree in a park, with a carousel in the distance; cinematic
Characteristic
Shot : A group of friends is having a picnic in a park. There is a carousel in the background.
Aesthetic Score : 0.7
Mood : happy, carefree, summery
Quality
Entropy : 6.55
Noise : 123
Prompt Clip Score : 0.31
AI Evaluation
Likelihood of AI : 0.20
Image errors : There are some minor artifacts in the image, particularly around the edges of the trees and the carousel.
Victory Dance in Neon Lights: Gamer Celebrates Triumph
A young gamer, bathed in vibrant pink and blue lighting, throws their hands in the air in a triumphant celebration after a hard-fought victory. The dynamic pose and energetic lighting capture the intensity and excitement of the moment.
Prompt
Amusement Concentrated, eyes glued to the screen, a slight grin: Focused, excited ; A gamer; close-up; Gamer; a dimly lit room with a computer screen displaying a vibrant video game, a controller in their hand; cinematic
Characteristic
Shot : A young man in a gaming chair, wearing headphones, is yelling with excitement while playing a video game. Neon pink and blue lighting illuminate the scene.
Aesthetic Score : 0.6
Mood : intense, excited, energetic
Quality
Entropy : 6.19
Noise : 69
Prompt Clip Score : 0.24
AI Evaluation
Likelihood of AI : 0.20
Image errors : The lighting is a bit harsh and the colors are overly saturated, leading to a slightly artificial look. There is some slight noise in the image, particularly in the darker areas.
A Moment of Wonder at the Carousel
A young girl with blonde hair stands beside a carousel pole, her gaze fixed upwards with a wistful expression. The blurred background, featuring a white carousel horse, adds to the dreamy and nostalgic atmosphere. This image captures a moment of pure anticipation and hope, as the girl dreams of the magical ride ahead.
Prompt
Amusement Awe, excitement, a touch of fear: Magical, innocent ; A young girl; eye-level; Single Person; a carousel with brightly painted horses, her eyes wide with wonder; cinematic
Characteristic
Shot : A young girl, dressed in a pink jacket, is holding onto a carousel pole and looking up. The carousel horse is partially visible in the background.
Aesthetic Score : 0.8
Mood : nostalgia, wonder, innocence
Quality
Entropy : 6.90
Noise : 106
Prompt Clip Score : 0.30
AI Evaluation
Likelihood of AI : 0.10
Image errors : No noticeable errors
Swinging into Joy: Capturing Childhood’s Unbridled Fun
This heartwarming image captures the pure joy of childhood as three children swing carefree on a playground. Their infectious laughter and smiles, combined with the dynamic blur of motion, create a vibrant and energetic scene. The blurred background adds a sense of depth and emphasizes the playful energy of the moment.
Prompt
Amusement Giggling, running, playing with abandon: Joyful, carefree ; A group of children; eye-level; Normal People; a playground with swings, slides, and a sandbox, their laughter echoing in the air; cinematic
Characteristic
Shot : Three children on swings, one in the center is in motion, with hair flying, the other two are still and looking at the camera. The children are on a playground, in the background there are other swings, blurry figures and trees
Aesthetic Score : 0.8
Mood : joyful, playful, innocent
Quality
Entropy : 6.60
Noise : 102
Prompt Clip Score : 0.25
AI Evaluation
Likelihood of AI : 0.20
Image errors : no visible artifacts or errors
Lost in the Storm’s Embrace
A solitary figure finds solace on a storm-battered pier, the crashing waves mirroring the turmoil within. The melancholic scene evokes a sense of isolation and quiet contemplation, leaving the viewer to ponder the depths of their own emotions.
Prompt
Amusement Thoughtful, a hint of sadness, a wistful smile: Melancholy, contemplative ; A lone man; eye-level; Single Person; a deserted boardwalk at night, the sound of crashing waves in the background; cinematic
Characteristic
Shot : A lonely figure sits on a bench on a pier, overlooking a stormy sea at night. The scene is illuminated by streetlights, casting long shadows on the wet wooden planks.
Aesthetic Score : 0.7
Mood : melancholy, contemplative, moody
Quality
Entropy : 6.03
Noise : 93
Prompt Clip Score : 0.28
AI Evaluation
Likelihood of AI : 0.20
Image errors : Some slight noise and banding are present in the image, particularly in the water and sky.
Man Plunges Towards Doom as City Explodes
A dramatic scene unfolds as a man falls from a building, the city behind him engulfed in flames. The image captures the raw intensity and urgency of a catastrophic event, leaving viewers breathless with suspense.
Prompt
Amusement Determined, focused, a sense of urgency: Thrilling, heroic ; A superhero in action; dynamic shot; Hero; a cityscape with towering buildings, a dramatic explosion in the background; cinematic
Characteristic
Shot : A man falls from a building engulfed in flames. The city around him is in ruins, with debris and smoke filling the air.
Aesthetic Score : 0.6
Mood : dramatic, chaotic, desperate
Quality
Entropy : 6.95
Noise : 114
Prompt Clip Score : 0.25
AI Evaluation
Likelihood of AI : 0.90
Image errors : The fire and debris are slightly unrealistic, and the man’s pose appears stiff.
Screaming with Joy: A Family’s Thrilling Roller Coaster Ride
Capture the exhilaration of a family’s roller coaster adventure. The wide-angle lens and motion blur perfectly convey the speed and excitement, while the screaming faces and windblown hair tell a story of pure joy and thrill.
Prompt
Amusement Screaming, laughing, holding on tight: Exhilarating, bonding ; A family; eye-level; Normal People; a crowded amusement park, their faces lit up with joy as they ride a roller coaster; cinematic
Characteristic
Shot : A family of four is riding a rollercoaster, they are all laughing and enjoying the ride. The rollercoaster is in motion and the image captures a moment of excitement.
Aesthetic Score : 0.7
Mood : joyful, exciting, thrilling
Quality
Entropy : 6.78
Noise : 91
Prompt Clip Score : 0.31
AI Evaluation
Likelihood of AI : 0.90
Image errors : There are some slight artifacts in the image, particularly in the background, these are mostly minor and do not detract much from the overall impact. The lighting and shadows seem a bit unnatural.
Lost in the Digital World: A Moment of Intense Focus
A young man sits in a dimly lit room, his face illuminated by the blue glow of a computer screen. The dramatic shadow cast by the light highlights his intense focus, capturing a moment of deep concentration in the digital age.
Prompt
Amusement Excitement, joy, a sense of accomplishment: Triumphant, exhilarating ; A gamer; close-up; Gamer; a dimly lit room, their hands moving rapidly on a keyboard, a triumphant shout escaping their lips; cinematic
Characteristic
Shot : A young man is sitting in front of a computer, looking intently at the screen. The image is lit with blue and orange hues, creating a moody atmosphere.
Aesthetic Score : 0.7
Mood : intense, focused, futuristic
Quality
Entropy : 6.31
Noise : 84
Prompt Clip Score : 0.23
AI Evaluation
Likelihood of AI : 0.10
Image errors : The image appears slightly blurry and lacks sharpness. The lighting is uneven, with the background being too dark compared to the subject.
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 0.2, indicating it’s not very good at reacting to camera positions in the prompt. This means the generated image’s camera position significantly deviates from what was requested.
- Shot Analysis: The model scored 0.51, which is good. This means the generated image’s shot composition is fairly close to what was described in the prompt.
- Aesthetic Analysis: The model scored 0.06, which is very good. This means the generated image’s aesthetic is very close to what was expected.
Overall, the model seems to be better at understanding the scene and its aesthetic than it is at accurately capturing 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