AI Captures the Essence of Emotion, But Struggles with Camera Angles with Dall-e-3
- 9 minutes read - 1905 wordsTable of Contents
Dramatic facial expressions are a powerful tool in storytelling, conveying a wide range of emotions and adding depth to characters. From the intense focus of a hero facing a villain to the subtle sadness of a character reflecting on a loss, facial expressions can speak volumes without a single word. This study explores how a generative AI model captures these nuances of human emotion and translates them into visual representations.
Created with: dall-e-3
Lost in the City Lights: A Moment of Melancholy
A young man stands alone in the rain, his face etched with sadness, as the vibrant city lights blur behind him. The scene captures a poignant moment of isolation and despair, highlighting the stark contrast between the bustling urban landscape and the man’s inner turmoil.
Prompt
facial-expressions Guilt: Desolate, regretful ; A lone figure; eye-level; Single Person; Empty street at night, rain falling; cinematic
Characteristic
Shot : A young man is standing in the rain, looking down and crying. He is in a dark alleyway, and the rain is coming down hard. There is a blurry car in the background, with lights on.
Aesthetic Score : 0.6
Mood : sad, lonely, melancholic
Quality
Entropy : 6.36
Noise : 95
Prompt Clip Score : 0.27
AI Evaluation
Likelihood of AI : 0.80
Image errors : The rain streaks look artificial, the lighting and the focus are a bit off. There is a strange, almost holographic, unnatural glow on the man’s face.
Bound by Despair: A Man’s Fate Amidst Urban Ruin
A powerful image captures the raw emotion of despair. A bearded man, cloaked in red, is bound in the foreground, his pose echoing the devastation of the city behind him. The dramatic composition and somber mood evoke a sense of hopelessness and the weight of loss.
Prompt
facial-expressions Guilt: Heavy, burdened, conflicted ; A superhero, cape billowing in the wind; medium shot; Hero; City skyline, destroyed buildings in the background; cinematic
Characteristic
Shot : A man, presumably a superhero, is tied up and looking down at a destroyed city in the background.
Aesthetic Score : 0.6
Mood : despair, defeat, melancholic
Quality
Entropy : 6.12
Noise : 102
Prompt Clip Score : 0.25
AI Evaluation
Likelihood of AI : 0.80
Image errors : The image exhibits some minor blurring and artifacts, particularly in the background.
Lost in Time: A Moment of Melancholy and Nostalgia
A woman gazes at an old photograph, her expression heavy with sadness. The vintage feel of the image evokes a sense of longing and reflection, as if she’s lost in memories of a bygone era. The stack of plates in the background adds a touch of everyday life, contrasting with the poignant emotion of the moment.
Prompt
facial-expressions Guilt: Nostalgic, melancholic ; A woman holding a photo of a loved one; close-up; Normal Person; A cluttered kitchen, dishes piled in the sink; cinematic
Characteristic
Shot : A woman in a kitchen, looking at an old, faded photograph of a couple.
Aesthetic Score : 0.7
Mood : melancholy, nostalgic, somber
Quality
Entropy : 6.64
Noise : 95
Prompt Clip Score : 0.29
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image appears slightly overexposed, leading to some loss of detail in the highlights, and the woman’s skin tone appears slightly unnatural.
The Weight of Expectations: A Young Man Struggles with Pressure
A young man sits hunched over a desk, surrounded by pizza boxes, his weary expression reflecting the weight of his anxieties. The dim lighting and his tense posture amplify the sense of frustration and contemplation he carries.
Prompt
facial-expressions Guilt: Isolated, self-loathing ; A gamer, hunched over a computer screen; close-up; Gamer; Neon lights reflecting in their eyes, empty pizza boxes scattered around; cinematic
Characteristic
Shot : A young man is sitting at a computer desk, looking down with a worried expression. He is illuminated by red and blue lighting, and there is a half-eaten pizza box in front of him. The overall atmosphere is one of tension and anxiety.
Aesthetic Score : 0.6
Mood : tense, anxious, dark
Quality
Entropy : 6.71
Noise : 85
Prompt Clip Score : 0.31
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image has a few minor artifacts, particularly in the shadows. The colors are also slightly oversaturated.
Lost in the Laughter: A Man’s Solitary Struggle at a Vibrant Party
A man stands alone in the heart of a joyous celebration, his serious expression a stark contrast to the surrounding laughter and merriment. The scene, bathed in the warm glow of string lights, captures a poignant moment of isolation amidst a sea of revelry.
Prompt
facial-expressions Guilt: Alienated, invisible ; A man standing in a crowded room, looking lost; wide shot; Single Person; A party, people laughing and dancing, oblivious to him; cinematic
Characteristic
Shot : A man stands in the middle of a crowded room full of people laughing and dancing, lit with fairy lights, with the man looking somber and out of place.
Aesthetic Score : 0.6
Mood : melancholy, somber, joyous
Quality
Entropy : 6.79
Noise : 105
Prompt Clip Score : 0.28
AI Evaluation
Likelihood of AI : 0.10
Image errors : Slight color distortion on the right side of the image, and a couple of pixels in the man’s shirt are distorted, giving it a grainy look.
Amidst the Chaos, a Soldier’s Resolve
A close-up shot captures the intensity of a soldier amidst a ravaged battlefield, his determined expression reflecting the somber mood and dramatic tension of the scene. The helicopter in the background adds to the sense of urgency and chaos.
Prompt
facial-expressions Guilt: Torn, conflicted, remorseful ; A hero, standing over a fallen villain; medium shot; Hero; A battlefield, smoke and debris everywhere; cinematic
Characteristic
Shot : A soldier in a military uniform, with bloodstains on his face, stands in a battlefield amidst debris and fallen soldiers. The background is a gloomy, cloudy sky with distant fires.
Aesthetic Score : 0.7
Mood : dark, intense, dramatic
Quality
Entropy : 6.88
Noise : 108
Prompt Clip Score : 0.24
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image quality is good, but there are some subtle artifacts visible on the soldier’s face, and the lighting is a bit uneven.
Silence at the Dinner Table: A Family’s Unseen Struggle
A tense atmosphere hangs heavy in the air as a family of five sits at a dinner table, their faces etched with unspoken emotions. The scene evokes a sense of unease and anticipation, leaving the viewer wondering what transpired to create this somber mood. What secrets lie beneath the surface of this seemingly ordinary gathering?
Prompt
facial-expressions Guilt: Awkward, strained, unspoken ; A family gathered around a table, but the atmosphere is tense; medium shot; Normal People; A dimly lit dining room, empty chairs at the table; cinematic
Characteristic
Shot : A family of five sitting at a dinner table, with a moody lighting and a sense of unease.
Aesthetic Score : 0.6
Mood : tense, somber, dramatic
Quality
Entropy : 6.82
Noise : 95
Prompt Clip Score : 0.28
AI Evaluation
Likelihood of AI : 0.20
Image errors : There are no major errors in the image, but the lighting is slightly uneven, and there is a slight blur in the background.
The Man in the Screen: A Tale of Late-Night Unease
A dimly lit room, a man staring intently at a television screen, and a sense of unease hanging in the air. The man on the screen, his face etched with fear and sadness, contrasts sharply with the viewer’s dark and indifferent expression. Energy drinks litter the table, hinting at a long night of contemplation. This image captures a moment of melancholic tension, leaving the viewer to ponder the story behind the screen.
Prompt
facial-expressions Guilt: Disillusioned, defeated, empty ; A gamer, staring at a blank screen, controller in hand; close-up; Gamer; A dimly lit room, empty energy drink cans scattered around; cinematic
Characteristic
Shot : A man is staring at a TV screen, and the screen shows the reflection of himself. The man is holding a video game controller, and there are empty cans of beer around. The image depicts a theme of loneliness, obsession, and possible addiction.
Aesthetic Score : 0.6
Mood : dark, eerie, lonely
Quality
Entropy : 6.50
Noise : 100
Prompt Clip Score : 0.29
AI Evaluation
Likelihood of AI : 0.80
Image errors : The reflection on the screen seems slightly off and lacks detail. The overall image resolution and sharpness are not the best. There are some visual artifacts and noise in the image, especially around the edges of the screen.
Lost in the City’s Blur
A solitary figure navigates a bustling cityscape, the motion blur of the crowd highlighting her sense of isolation. The cobblestone street and imposing buildings create an atmosphere of urban anonymity, leaving the woman feeling lost and alone.
Prompt
facial-expressions Guilt: Lonely, isolated, rejected ; A woman walking away from a group of friends; long shot; Single Person; A bustling city street, people rushing by; cinematic
Characteristic
Shot : A woman walks down a city street, blurred figures walking past her in the background.
Aesthetic Score : 0.6
Mood : lonely, urban, introspective
Quality
Entropy : 6.81
Noise : 88
Prompt Clip Score : 0.22
AI Evaluation
Likelihood of AI : 0.20
Image errors : No noticeable errors.
Silhouetted Against the Moon: A Moment of Solitude
A man stands alone on a rooftop, his silhouette stark against the backdrop of a city skyline bathed in moonlight. His serious expression and the play of shadows evoke a sense of melancholic introspection and loneliness.
Prompt
facial-expressions Guilt: Reflective, contemplative, seeking redemption ; A hero, standing on a rooftop, looking out at the city; wide shot; Hero; A cityscape bathed in moonlight, a sense of peace; cinematic
Characteristic
Shot : A man with a beard is standing on a rooftop overlooking a city at night. The moon is visible in the sky, and the city lights are twinkling below.
Aesthetic Score : 0.6
Mood : melancholy, lonely, contemplative
Quality
Entropy : 6.66
Noise : 90
Prompt Clip Score : 0.22
AI Evaluation
Likelihood of AI : 0.90
Image errors : The image has some minor artifacts, specifically around the edges of the man’s hair and beard.
Conclusion
The results show that the generative AI model performed well in terms of camera position and shot analysis, but struggled with aesthetic analysis.
Here’s a breakdown:
- Camera Position: The model scored 0.3, 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 0.52, 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 0.12, 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.
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://openai.com/index/dall-e-3/