AI's Facial Expressions: A Mixed Bag of Success with Flux-pro
- 9 minutes read - 1789 wordsTable of Contents
Dramatic facial expressions are a powerful tool in storytelling, conveying emotions and intentions with a single glance. This blog explores the capabilities of a generative AI model in capturing these expressions across diverse scenes. We’ll examine how the model interprets scene descriptions, camera positions, and aesthetic expectations, highlighting its strengths and areas for improvement.
Created with: flux-pro
Shadows and Secrets: A Figure Lurks in the Darkness
A hooded figure, their face hidden by a mask, stands alone in a dimly lit corridor. The atmosphere is thick with suspense and mystery, leaving you wondering who they are and what secrets they hold.
Prompt
facial-expressions Fear: Unease, paranoia ; A lone figure; eye-level; Single Person; a dark, deserted alleyway; cinematic
Characteristic
Shot : A person in a hooded robe and mask walks down a dimly lit alleyway.
Aesthetic Score : 0.6
Mood : creepy, suspenseful, eerie
Quality
Entropy : 6.49
Noise : 73
Prompt Clip Score : 0.21
AI Evaluation
Likelihood of AI : 0.30
Image errors : The image is slightly blurry, and the mask is poorly lit.
Silhouette of Mystery: A Superhero Stands Watch Over the Fog-Shrouded City
A lone figure, cloaked in a cape, stands on a rooftop overlooking a city skyline veiled in mist. The silhouette evokes the image of a superhero, perhaps Batman, creating a sense of mystery and anticipation. The scene is both brooding and epic, leaving viewers to wonder what secrets lie hidden within the fog.
Prompt
facial-expressions Fear: Dread, anticipation ; A superhero standing alone on a rooftop; eye-level; Hero; a cityscape shrouded in fog; cinematic
Characteristic
Shot : A lone figure in a superhero cape stands on a rooftop overlooking a cityscape. The city is shrouded in fog, creating a mysterious and dramatic atmosphere.
Aesthetic Score : 0.6
Mood : mysterious, dramatic, contemplative
Quality
Entropy : 6.84
Noise : 74
Prompt Clip Score : 0.29
AI Evaluation
Likelihood of AI : 0.70
Image errors : The image has some minor artifacts, particularly around the edges of the figure and the buildings. The fog effect could be improved with more subtle transitions and less noise.
Lost in the Shadows
A solitary figure walks down a dimly lit street, their silhouette disappearing into the night. The image evokes a sense of loneliness and mystery, leaving the viewer to wonder about their journey and destination.
Prompt
facial-expressions Fear: Vulnerability, isolation ; A woman walking down a dimly lit street; eye-level; Normal Person; a deserted street with flickering streetlights; cinematic
Characteristic
Shot : A lone figure walks down a quiet, foggy street at night. The street is illuminated by a single streetlamp, casting long shadows.
Aesthetic Score : 0.6
Mood : mysterious, lonely, somber
Quality
Entropy : 6.26
Noise : 85
Prompt Clip Score : 0.31
AI Evaluation
Likelihood of AI : 0.20
Image errors : No major errors visible, but the image appears slightly over-sharpened.
Lost in the Game: A Moment of Intense Focus
A young woman, headphones on, is completely absorbed in a video game. The dramatic lighting and her focused expression create a sense of mystery and suspense, leaving you wondering what challenges await her in the dark and atmospheric world on the screen.
Prompt
facial-expressions Fear: Disquiet, unease ; A gamer hunched over their computer; close-up; Gamer; a flickering monitor displaying a disturbing image; cinematic
Characteristic
Shot : A young woman is sitting at a computer, wearing headphones, in a dimly lit room. She is focused on the computer screen. The computer screen shows a blurred image of a video game character.
Aesthetic Score : 0.7
Mood : focused, intense, digital
Quality
Entropy : 6.38
Noise : 71
Prompt Clip Score : 0.27
AI Evaluation
Likelihood of AI : 0.10
Image errors : The image has a slight blurriness, especially around the subject’s face. There is a slight amount of noise in the image, especially in the darker areas.
Lost in the Shadows of Despair
A poignant image captures the raw emotion of loneliness and sadness. The woman’s face, shrouded in darkness, speaks volumes about her inner turmoil. The dramatic focus on her expression evokes a sense of isolation and despair, leaving a lasting impression.
Prompt
facial-expressions Fear: Terror, helplessness ; hiding ; low-angle; Single Person; a dark room with shadows creeping in; cinematic
Characteristic
Shot : A woman is sitting in a dimly lit room with her head in her hands, looking distressed.
Aesthetic Score : 0.4
Mood : sad, somber, despair
Quality
Entropy : 6.23
Noise : 63
Prompt Clip Score : 0.23
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image is slightly underexposed, and there is some noise in the shadows.
David vs. Goliath: A Lone Warrior Faces a Monstrous Threat
A solitary warrior stands defiant against a colossal, monstrous creature in a desolate wasteland. The image captures the epic scale of the confrontation, highlighting the warrior’s vulnerability against the overwhelming power of the beast. The mood is tense and dramatic, leaving the viewer to wonder if the warrior can possibly prevail.
Prompt
facial-expressions Fear: Desperation, courage ; A hero facing a monstrous creature; eye-level; Hero; a crumbling battlefield with smoke and debris; cinematic
Characteristic
Shot : A lone warrior stands facing a giant, monstrous creature in a desolate, dust-filled wasteland. The creature’s imposing form fills the foreground, while the warrior appears small and vulnerable in the distance.
Aesthetic Score : 0.75
Mood : epic, dramatic, suspenseful
Quality
Entropy : 6.66
Noise : 76
Prompt Clip Score : 0.26
AI Evaluation
Likelihood of AI : 0.80
Image errors : The image has a slightly blurry appearance, particularly in the background. The textures of the creature and the warrior are somewhat generic and lack detail.
Lightning Strikes, Secrets Unfold
A group of people huddle in a dimly lit room, their faces obscured by shadows. A raging storm rages outside, casting flickering light through the window and adding a sense of mystery and tension to the scene. What secrets are they hiding?
Prompt
facial-expressions Fear: Anxiety, uncertainty ; A group of people huddled together in a darkened room; eye-level; Normal People; a storm raging outside with thunder and lightning; cinematic
Characteristic
Shot : A group of people are huddled together in a darkened room, lit only by the light from a window with a stormy sky outside. They are holding hands or are in close proximity to each other, perhaps praying or sharing a moment of comfort.
Aesthetic Score : 0.5
Mood : dramatic, suspenseful, somber
Quality
Entropy : 6.28
Noise : 79
Prompt Clip Score : 0.28
AI Evaluation
Likelihood of AI : 0.20
Image errors : No major artifacts or errors are present.
Startled by the Unexpected: A Moment of Shock Captured
A young person, headphones on, is completely engrossed in their computer screen. Their expression shifts from focused to startled, revealing a moment of surprise. The blurry figure in the background adds a layer of mystery, leaving the viewer wondering what caused the sudden shift in mood. The dramatic lighting enhances the intensity of the scene, capturing the raw emotion of the moment.
Prompt
facial-expressions Fear: Shock, adrenaline ; A gamer’s hands shaking as they play a horror game; close-up; Gamer; a screen displaying a jump scare; cinematic
Characteristic
Shot : A young person is looking at a computer screen with a shocked expression, wearing headphones, with a monitor in the background showing a blurry image of a character with white eyes.
Aesthetic Score : 0.6
Mood : intense, surprised, focused
Quality
Entropy : 6.50
Noise : 67
Prompt Clip Score : 0.31
AI Evaluation
Likelihood of AI : 0.20
Image errors : There are no noticeable artifacts or errors in the image.
Lost in the Vastness: A Solitary Figure Contemplates the Canyon’s Depths
A lone figure stands on a precipice, dwarfed by the immense canyon below. The cloudy sky and hazy air add to the sense of mystery and isolation, evoking a mood of melancholy and contemplation. The dramatic contrast between the figure and the vast landscape highlights the fragility of existence and the awe-inspiring power of nature.
Prompt
facial-expressions Fear: Loneliness, despair ; A lone figure standing at the edge of a cliff; eye-level; Single Person; a vast, empty landscape with a stormy sky; cinematic
Characteristic
Shot : A lone figure stands on the edge of a cliff overlooking a vast canyon. The sky is overcast with dramatic clouds, and the canyon is shrouded in mist. A thin river meanders through the bottom of the canyon.
Aesthetic Score : 0.7
Mood : melancholy, solitude, dramatic
Quality
Entropy : 6.68
Noise : 79
Prompt Clip Score : 0.27
AI Evaluation
Likelihood of AI : 0.90
Image errors : The image has some minor artifacts, but overall is technically sound.
Silhouette of Solitude: A Lone Figure Contemplates the Ashes
A solitary figure, cloaked in crimson, stands with their back to the viewer, gazing upon a city consumed by flames. The dramatic silhouette against the fiery backdrop evokes a sense of mystery and isolation, hinting at a world consumed by chaos and the unknown.
Prompt
facial-expressions Fear: Loss, determination ; A hero standing amidst a burning city; eye-level; Hero; a chaotic scene with smoke and flames; cinematic
Characteristic
Shot : A lone figure in a dark red cloak stands in a desolate cityscape. The background is engulfed in flames and smoke.
Aesthetic Score : 0.7
Mood : mysterious, foreboding, dramatic
Quality
Entropy : 6.68
Noise : 76
Prompt Clip Score : 0.27
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image has a slight graininess, particularly in the background.
Conclusion
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 the model didn’t fully capture the intended camera position described in the prompt.
- Shot Analysis: The model scored 0.55, falling within the “good” range. This indicates the model successfully understood the scene described in the prompt and created an image that reflects it.
- Aesthetic Analysis: The model scored 0.15, which is outside the “very good” range of -0.2 to 0.1. This suggests the generated image’s aesthetic deviated from the expected aesthetic described in the prompt.
Overall, the model shows promise in understanding scene descriptions and camera positions, but needs improvement in generating images that match the desired aesthetic.
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://fal.ai/models/fal-ai/flux-pro/api