AI's Facial Expressions: A Mixed Bag of Success with Midjourney
- 9 minutes read - 1913 wordsTable of Contents
Facial expressions are a powerful tool in storytelling, conveying emotions and adding depth to characters. In the realm of AI-generated imagery, the ability to accurately depict facial expressions is crucial for creating realistic and engaging visuals. This blog post examines the performance of a generative AI model in capturing facial expressions, analyzing its strengths and weaknesses in understanding scene descriptions and translating them into visual representations. We’ll explore how the model handles camera position, shot analysis, and aesthetic quality, highlighting its progress towards achieving true realism in facial expressions.
Created with: midjourney
Lost in the Neon Glow: A Lonely Figure Walks the Wet Streets
A solitary figure traverses a deserted, rain-slicked street at night. The reflection of streetlights and neon signs in the puddles creates a melancholic atmosphere, emphasizing the feeling of isolation and loneliness. The figure walking away from the viewer adds to the sense of solitude, leaving the viewer to ponder their own thoughts and feelings.
Prompt
Surprise Surprise, fear: Eerie, suspenseful ; A lone figure walking down a deserted street; eye-level; Single Person; neon signs reflecting in puddles; cinematic
Characteristic
Shot : A lone figure walks down a wet street at night, with reflections of neon signs in a puddle in the foreground. The buildings lining the street are mostly out of focus, contributing to the lonely and atmospheric vibe.
Aesthetic Score : 0.7
Mood : melancholic, atmospheric, urban
Quality
Entropy : 6.57
Noise : 99
Prompt Clip Score : 0.30
AI Evaluation
Likelihood of AI : 0.10
Image errors : No visible artifacts or errors. The image is well-exposed and there is no noticeable noise.
Hope Shines Bright: A Superhero’s Night Watch
A lone figure stands tall, cloaked in red, against the backdrop of a glittering cityscape. The superhero’s silhouette, bathed in the glow of distant lights, evokes a sense of power and mystery. This epic scene whispers of hope and the promise of a brighter tomorrow.
Prompt
Surprise Surprise, determination: Triumphant, awe-inspiring ; A superhero standing on a rooftop, looking out over the city; eye-level; Hero; cityscape at night, with flashing lights and sirens in the distance; cinematic
Characteristic
Shot : A superhero stands on the edge of a rooftop in a city at night, looking out over the cityscape. The cape is billowing in the wind.
Aesthetic Score : 0.7
Mood : dramatic, heroic, hopeful
Quality
Entropy : 6.07
Noise : 101
Prompt Clip Score : 0.24
AI Evaluation
Likelihood of AI : 0.90
Image errors : The image has a few artifacts, including some noise in the sky and some blurry areas in the cityscape.
Dinner with a Monster: A Family’s Unknowing Terror
A seemingly ordinary family dinner takes a chilling turn as a monstrous creature lurks outside, watching their every move. The unsettling scene, captured with a masterful sense of suspense, leaves viewers questioning what horrors await.
Prompt
Surprise Surprise, fear: Innocent, unsettling ; A family having dinner together, unaware of the approaching danger; eye-level; Normal People; cozy kitchen, warm lighting; cinematic
Characteristic
Shot : A family is having dinner in a dimly lit kitchen, unaware of a monstrous creature lurking outside the window.
Aesthetic Score : 0.6
Mood : creepy, suspenseful, ominous
Quality
Entropy : 6.24
Noise : 83
Prompt Clip Score : 0.32
AI Evaluation
Likelihood of AI : 0.80
Image errors : Some of the edges and details are slightly blurred and pixelated, particularly in the creature’s face.
Caught in the Act: A Moment of Surprise at the Computer
A young man with curly hair sits at his computer desk, his surprised expression hinting at something unexpected on the screen. The dimly lit room, adorned with string lights, adds to the sense of intrigue and excitement.
Prompt
Surprise Surprise, excitement: Intense, focused ; A gamer sitting in a dimly lit room, eyes glued to the screen; close-up; Gamer; glowing monitor, keyboard, and mouse; cinematic
Characteristic
Shot : A young man wearing glasses is sitting in front of a computer in a dimly lit room. The room is decorated with fairy lights and there is a plant in the background. He is looking at the camera with a surprised expression.
Aesthetic Score : 0.7
Mood : surprised, intense, edgy
Quality
Entropy : 6.36
Noise : 89
Prompt Clip Score : 0.29
AI Evaluation
Likelihood of AI : 0.10
Image errors : The image has some minor noise in the shadows.
Lost in the Rush: A Woman’s Desperate Flight Through a Crowded Station
A woman, her face etched with worry, races through a bustling train station, clutching her purse tightly. The scene, painted in a realistic style, captures the tension and urgency of her frantic dash, leaving viewers to wonder what she’s running from and if she’ll find what she’s searching for.
Prompt
Surprise Surprise, panic: Panic, frantic ; A woman standing in a crowded train station, suddenly realizing she’s lost her purse; eye-level; Single Person; bustling crowd, hurried footsteps; cinematic
Characteristic
Shot : A woman in a blue jacket is running through a crowded train station, her face is filled with fear and anxiety, clutching her handbag tightly.
Aesthetic Score : 0.7
Mood : intense, chaotic, anxious
Quality
Entropy : 6.45
Noise : 116
Prompt Clip Score : 0.28
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image appears to be a painting, so the brushstrokes and texture of the paint are part of its style. However, some details, especially the face and the background, appear blurry and lacking in sharpness, potentially due to the artistic style or the scanning process.
Desperate Escape: Man Fleeing Fire With Child in Arms
A heart-wrenching scene unfolds as a man races through a narrow street, carrying a child to safety. The fire behind them rages, billowing smoke into the sky, creating a sense of urgency and danger. Despite the smoke obscuring his face, the man’s determined expression reveals his unwavering resolve to escape the inferno and protect the child.
Prompt
Surprise Surprise, relief: Brave, heroic ; A hero emerging from a burning building, carrying a child; eye-level; Hero; smoke and flames, collapsing structure; cinematic
Characteristic
Shot : A man is running away from a fire in a city, carrying a child. The scene is set in a narrow alleyway, with buildings on either side. The fire is raging in the background, and there is smoke and debris everywhere. The man is silhouetted against the fire, and his face is obscured by the smoke.
Aesthetic Score : 0.6
Mood : dramatic, intense, urgent
Quality
Entropy : 6.66
Noise : 93
Prompt Clip Score : 0.28
AI Evaluation
Likelihood of AI : 0.70
Image errors : There are some minor artifacts in the image, such as the jagged edges of the smoke.
Picnic with a Twist: Friends Gather Under a Mysterious Flying Saucer
A group of friends enjoy a carefree picnic in a park, their laughter and chatter punctuated by the curious presence of a hovering flying saucer. The scene evokes a sense of wonder and playful intrigue, leaving the viewer to ponder the possibilities of the unknown.
Prompt
Surprise Surprise, confusion: Peaceful, ominous ; A group of friends enjoying a picnic in a park, unaware of the strange object falling from the sky; eye-level; Normal People; sunny day, green grass, blue sky; cinematic
Characteristic
Shot : A group of people are having a picnic in a park with a UFO hovering overhead.
Aesthetic Score : 0.6
Mood : whimsical, curious, playful
Quality
Entropy : 6.63
Noise : 109
Prompt Clip Score : 0.30
AI Evaluation
Likelihood of AI : 0.90
Image errors : The edges of the leaves have some slight pixelation and aliasing, and the UFO appears somewhat flat and lacking in detail.
The Blur of Speed: A Gamer’s Focus
A pair of hands fly across the keyboard, the vibrant, blurred background hinting at the intense, futuristic world of gaming. This image captures the energy and focus of a gamer in the heat of the action.
Prompt
Surprise Surprise, anger: Disbelief, frustration ; A gamer’s hands frantically moving across the keyboard, as a sudden glitch appears on the screen; close-up; Gamer; distorted screen, flashing lights; cinematic
Characteristic
Shot : A pair of hands typing on a keyboard in front of a glowing background of light. The image is heavily stylized with a zoom blur effect.
Aesthetic Score : 0.4
Mood : intense, fast-paced, energetic
Quality
Entropy : 6.79
Noise : 102
Prompt Clip Score : 0.25
AI Evaluation
Likelihood of AI : 0.80
Image errors : The zoom blur is overly applied and creates a sense of motion sickness.
Lost in the Face of Fear: A Man’s Journey Through a Surreal Forest
A solitary figure traverses a dense, overgrown forest, drawn towards a colossal, menacing face that looms over the landscape. The image evokes a sense of mystery and dread, highlighting the man’s vulnerability in the face of the unknown.
Prompt
Surprise Surprise, wonder: Mystical, awe-inspiring ; A man walking through a forest, suddenly finding himself face-to-face with a mythical creature; eye-level; Single Person; dense foliage, dappled sunlight; cinematic
Characteristic
Shot : A lone figure stands in a dense forest, seemingly dwarfed by a massive, mossy, and somewhat menacing creature. Sunlight streams through the canopy, casting dramatic light and shadows.
Aesthetic Score : 0.7
Mood : mysterious, eerie, awe
Quality
Entropy : 6.55
Noise : 117
Prompt Clip Score : 0.27
AI Evaluation
Likelihood of AI : 0.80
Image errors : The edges of the image appear slightly blurred and some of the textures in the creature’s mossy skin seem repetitive.
A Lone Figure in a World of Ashes
A solitary soldier traverses a desolate landscape, the silence broken only by the faint whispers of smoke. The scene evokes a profound sense of melancholy and isolation, a stark reminder of the devastating aftermath of war.
Prompt
Surprise Surprise, sadness: Melancholy, reflective ; A hero standing on a battlefield, surrounded by fallen enemies, realizing the true cost of victory; eye-level; Hero; smoke and debris, wounded soldiers; cinematic
Characteristic
Shot : A lone soldier walks through a war-torn landscape, smoke billowing in the background.
Aesthetic Score : 0.7
Mood : melancholy, somber, haunting
Quality
Entropy : 6.57
Noise : 110
Prompt Clip Score : 0.27
AI Evaluation
Likelihood of AI : 0.50
Image errors : No visible errors in the image
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, which is considered below average. This suggests that the model didn’t accurately capture the intended camera position described in the prompt.
- Shot Analysis: The model scored 0.6, which is considered good. This indicates that the model was able to understand the scene described in the prompt and create a shot that aligns with it.
- Aesthetic Analysis: The model scored 0.11, which is considered very good. This means that the generated image closely matched the expected aesthetic style.
Overall, the model demonstrates a good understanding of the scene and shot composition, but needs improvement in accurately capturing the intended camera position. The aesthetic quality of the generated image is very good.
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