AI Captures the Nuance of Human Emotion in Images with Freepik
- 9 minutes read - 1843 wordsTable of Contents
The ability to capture and convey human emotion is a hallmark of great art. Now, AI is stepping into this realm, attempting to generate images that evoke a range of feelings. In this blog post, we explore a case study where an AI model was tasked with creating images based on descriptions of facial expressions and scenes. While the model excelled at capturing the aesthetic of the scenes, it struggled with accurately replicating the intended camera angles. This highlights the ongoing challenges and potential of AI in understanding and replicating the nuances of human expression.
Created with: freepik
Lost in the City’s Embrace
A solitary figure, shrouded in a hooded coat, stands alone on a rain-slicked city street. The dim glow of streetlights casts long shadows, amplifying the sense of isolation and melancholic mood. This image captures the raw emotion of loneliness in a bustling urban landscape.
Prompt
facial-expressions Shame: Desolate, lonely, regretful ; A lone figure, hunched over, walking down a deserted street; eye-level; Single Person; Rain-slicked pavement and flickering streetlights; cinematic
Characteristic
Shot : A lone man in a hooded coat stands on a wet, empty street at night. The street is illuminated by streetlights, and there is a slight fog in the air.
Aesthetic Score : 0.7
Mood : lonely, somber, mysterious
Quality
Entropy : 6.83
Noise : 78
Prompt Clip Score : 0.28
AI Evaluation
Likelihood of AI : 0.20
Image errors : No noticeable image errors
The Dark Knight Rises Above the City
A brooding superhero, silhouetted against the dusk-painted cityscape, gazes out with glowing eyes. The scene evokes a sense of mystery and heroism, promising a thrilling adventure to come.
Prompt
facial-expressions Shame: Melancholy, disillusioned, burdened ; A superhero, their mask removed, revealing a face etched with pain; eye-level; Hero; A cityscape bathed in the glow of a setting sun; cinematic
Characteristic
Shot : A superhero standing on a rooftop overlooking a city at sunset
Aesthetic Score : 0.7
Mood : dramatic, mysterious, hopeful
Quality
Entropy : 6.80
Noise : 52
Prompt Clip Score : 0.26
AI Evaluation
Likelihood of AI : 0.70
Image errors : The image has some slight blurring and artifacts, particularly in the background.
Lost in the Yellow Light: A Moment of Solitude
A young woman sits alone in a dimly lit diner, her face etched with melancholy. The soft yellow lights and blurred background create a sense of isolation, highlighting her introspective mood. The image captures a poignant moment of loneliness, leaving the viewer to ponder her thoughts and feelings.
Prompt
facial-expressions Shame: Embarrassed, defeated, self-loathing ; A woman, her face buried in her hands, sitting alone at a crowded diner table; eye-level; Normal Person; The bustling activity of the diner, a stark contrast to her isolation; cinematic
Characteristic
Shot : A young woman sits alone at a diner, looking sad and pensive, with a blurred background of other people at the diner.
Aesthetic Score : 0.6
Mood : melancholy, lonely, reflective
Quality
Entropy : 6.90
Noise : 51
Prompt Clip Score : 0.28
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image has some minor noise and a slight softness in the focus, but it’s not distracting.
The Intensity of Focus: A Gamer’s World
A young man, lost in the digital realm, sits intently with headphones on and controller in hand. The image captures the focused, serious, and intense mood of a gamer fully immersed in their virtual world, creating a sense of suspense and excitement.
Prompt
facial-expressions Shame: Empty, defeated, lost in a digital world ; A gamer, staring blankly at a screen, his controller lying idle; eye-level; Gamer; A dimly lit room filled with gaming paraphernalia, a sense of disconnection; cinematic
Characteristic
Shot : A young man wearing headphones is sitting in a chair and playing video games. The scene is lit with a soft, warm light, giving it a cozy and intimate feel.
Aesthetic Score : 0.6
Mood : focused, intense, thoughtful
Quality
Entropy : 6.52
Noise : 45
Prompt Clip Score : 0.29
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image has a slightly blurry background, which could be due to the low light conditions or the camera settings. The subject’s hair appears slightly unnatural, possibly due to post-processing.
A Moment of Pure Joy Captured
This image radiates happiness! A young man, beaming with excitement, stands amidst a lively crowd. The warm lighting and blurred background suggest a festive gathering, capturing a moment of pure joy and anticipation.
Prompt
facial-expressions Shame: Anxious, self-conscious, out of place ; A man, standing in a crowded room, his eyes darting nervously around; eye-level; Single Person; A party scene, filled with laughter and conversation, but he feels isolated; cinematic
Characteristic
Shot : A man is standing in a crowd of people, looking surprised and excited. There are string lights in the background.
Aesthetic Score : 0.6
Mood : joyful, surprised, candid
Quality
Entropy : 6.87
Noise : 56
Prompt Clip Score : 0.25
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image is slightly overexposed, causing some of the details in the background to be lost. The colors are a bit washed out.
Silhouettes of Solitude: A Man’s Melancholy at Dusk
A solitary figure stands on a rooftop, their silhouette stark against the cityscape as dusk descends. The scene evokes a sense of melancholic contemplation, highlighting the isolation and urban loneliness of the moment.
Prompt
facial-expressions Shame: Disheartened, disillusioned, questioning his purpose ; A hero, standing on a rooftop, looking down at the city below; not too close; Hero; A panoramic view of the city, but he feels small and insignificant; cinematic
Characteristic
Shot : A man in a leather jacket standing on a rooftop overlooking a city skyline at dusk.
Aesthetic Score : 0.7
Mood : melancholy, contemplative, urban
Quality
Entropy : 6.85
Noise : 50
Prompt Clip Score : 0.24
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image is slightly overexposed, and the colors are a bit washed out.
The Weight of Loneliness
A young woman sits alone in a dimly lit kitchen, her forlorn expression and untouched plate of food painting a picture of profound melancholy and isolation.
Prompt
facial-expressions Shame: Depressed, unmotivated, lost in her thoughts ; A woman, sitting at her kitchen table, staring at a plate of untouched food; eye-level; Normal Person; A cluttered kitchen, a reflection of her inner turmoil; cinematic
Characteristic
Shot : A young woman sits at a kitchen table, her face expressionless, looking directly at the viewer. She has a plate of food in front of her, and there are two other plates with food on the table, though they are empty. The kitchen is lit dimly by overhead lights.
Aesthetic Score : 0.6
Mood : melancholy, contemplative, somber
Quality
Entropy : 6.88
Noise : 59
Prompt Clip Score : 0.31
AI Evaluation
Likelihood of AI : 0.20
Image errors : No visible errors.
Lost in the Code: A Moment of Intense Focus
A young man sits hunched over his keyboard, bathed in the soft glow of the screen. The dim lighting and his unwavering gaze create an atmosphere of mystery and intrigue, hinting at a world of secrets hidden within the code.
Prompt
facial-expressions Shame: Despair, addiction, a sense of being lost ; A gamer, hunched over his keyboard, his fingers flying across the keys, but his eyes are filled with sadness; eye-level; Gamer; A brightly lit gaming room, but he feels trapped in a digital world; cinematic
Characteristic
Shot : A young man is working on a computer in a dimly lit room. He is focused on his task and his expression is intense. The room is cluttered with electronic equipment, and the lighting creates a sense of mystery and intrigue.
Aesthetic Score : 0.6
Mood : intense, focused, mysterious
Quality
Entropy : 6.53
Noise : 53
Prompt Clip Score : 0.27
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image is slightly blurry, especially in the background, and the lighting is uneven.
Lost in the City’s Anonymous Embrace
A solitary figure walks away from the camera, swallowed by the bustling city streets. The shallow depth of field isolates him, emphasizing his loneliness amidst the urban anonymity.
Prompt
facial-expressions Shame: Rejected, isolated, a sense of being unwanted ; A man, walking away from a group of people, his head down, his shoulders slumped; eye-level; Single Person; A bustling street, but he feels alone and invisible; cinematic
Characteristic
Shot : A man is walking down a crowded street, his back is turned to the camera. The scene is blurred and out of focus, suggesting movement and a sense of anonymity.
Aesthetic Score : 0.6
Mood : lonely, anonymous, urban
Quality
Entropy : 6.87
Noise : 64
Prompt Clip Score : 0.26
AI Evaluation
Likelihood of AI : 0.20
Image errors : There are no noticeable errors in the image.
A Knight’s Tale of Ruin and Mystery
A lone knight, shrouded in shadow and armor, stands amidst the crumbling remnants of a once-great city. The scene is a testament to war and desolation, with a somber mood and gritty atmosphere. The knight’s pose and the dramatic lighting create an air of mystery and intrigue, leaving the viewer to ponder the story behind this solitary figure.
Prompt
facial-expressions Shame: Guilt, regret, a sense of responsibility ; A hero, standing in the ruins of a battle, his armor dented and his face covered in grime; not too close; Hero; A scene of destruction, a reminder of the cost of his actions; cinematic
Characteristic
Shot : A lone knight in armor stands amidst the ruins of a battle-scarred city.
Aesthetic Score : 0.7
Mood : dark, somber, heroic
Quality
Entropy : 6.91
Noise : 71
Prompt Clip Score : 0.29
AI Evaluation
Likelihood of AI : 0.20
Image errors : No significant errors visible in the image.
Conclusion
The analysis shows that the generative AI model performed well in understanding the camera position and shot composition, but struggled with the aesthetic aspect. Here’s a breakdown:
- Camera Position: The model scored 0.25, which is considered below average. This suggests that the generated image didn’t accurately reflect the camera position described in the prompt.
- Shot Analysis: The model scored 0.57, which is considered good. This indicates that the model was able to understand the scene and create a shot that was somewhat aligned with the prompt.
- Aesthetic Analysis: The model scored 0.15, which is considered very good. This means that the generated image’s aesthetic was very close to the expected aesthetic described in the prompt.
Overall, the model seems to be better at understanding the scene and creating a visually appealing image than accurately capturing the intended 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://www.freepik.com