AI's Facial Expressions: A Mixed Bag of Emotions with Flux-pro
- 9 minutes read - 1780 wordsTable of Contents
Facial expressions are a powerful tool for conveying emotions, and AI is increasingly being used to generate realistic and expressive faces. However, the ability to capture the full range of human emotion remains a challenge. This blog post explores the capabilities of AI in generating facial expressions, examining its strengths and weaknesses in capturing emotions and aesthetics. We’ll analyze the results of a recent experiment, highlighting the model’s strengths in shot composition and its challenges in achieving a desired aesthetic. By understanding the limitations and potential of AI in this domain, we can better appreciate the complexities of human expression and the ongoing advancements in artificial intelligence.
Created with: flux-pro
Lost in Autumn’s Embrace
A solitary figure, cloaked in black, contemplates the passing season amidst a sea of fallen leaves. The blurred background amplifies the sense of isolation and melancholy, creating a poignant image of quiet reflection.
Prompt
facial-expressions Sadness: Melancholy, loneliness ; A lone figure; eye-level; Single Person; Empty park bench with fallen leaves; cinematic
Characteristic
Shot : A lone man in a black jacket and hat sits on a park bench in a slightly blurry background with fallen autumn leaves. The man seems to be in deep thought, looking down and holding his hands in his lap.
Aesthetic Score : 0.7
Mood : melancholy, contemplative, autumnal
Quality
Entropy : 6.87
Noise : 81
Prompt Clip Score : 0.26
AI Evaluation
Likelihood of AI : 0.20
Image errors : There is a slight amount of blur in the image, especially in the background. This could be due to lens distortion or movement during the shot.
The Bat in the Rain: A Portrait of Mystery
A close-up portrait of Batman, shrouded in rain and darkness, captures the brooding intensity of the iconic hero. The low lighting and close-up shot create a sense of mystery and intrigue, drawing the viewer into the depths of his masked gaze.
Prompt
facial-expressions Sadness: Despair, disillusionment ; A superhero in their costume; eye-level; Hero; City skyline at night, rain falling; cinematic
Characteristic
Shot : A close-up portrait of a man wearing a Batman costume, looking intensely at the camera in the rain. The background is blurred and out of focus.
Aesthetic Score : 0.7
Mood : dark, intense, brooding
Quality
Entropy : 6.76
Noise : 86
Prompt Clip Score : 0.27
AI Evaluation
Likelihood of AI : 0.20
Image errors : There is a minor blurring around the edges of the subject’s mask that may be due to poor lighting or oversharpening. There is also a slight chromatic aberration around the edges of the mask, which is likely a processing artifact.
Lost in Thought: A Moment of Quiet Reflection
A young woman finds solace in a warm, intimate setting, her thoughtful gaze and the soft lighting hinting at a moment of deep contemplation and perhaps a touch of melancholy.
Prompt
facial-expressions Sadness: Hopelessness, grief ; A woman sitting at a kitchen table; eye-level; Normal People; Empty coffee cup, unwashed dishes; cinematic
Characteristic
Shot : A young woman sits at a kitchen table, looking upwards with a thoughtful expression, surrounded by a slightly cluttered kitchen.
Aesthetic Score : 0.6
Mood : pensive, reflective, contemplative
Quality
Entropy : 6.71
Noise : 66
Prompt Clip Score : 0.27
AI Evaluation
Likelihood of AI : 0.10
Image errors : Slight noise and graininess in the image.
Lost in the Code: A Moment of Intense Focus
A young man, headphones on, is completely absorbed in his work. The low-key lighting and close-up shot create a sense of mystery, while the keyboard in the foreground hints at the action unfolding. Is he gaming, coding, or something else entirely? This image captures the intensity of focus in a digital age.
Prompt
facial-expressions Sadness: Isolation, withdrawal ; A gamer hunched over their computer; close-up; Gamer; Empty pizza boxes, energy drink cans; cinematic
Characteristic
Shot : A young man is sitting at a desk in a dimly lit room, wearing headphones and using a keyboard. There is a computer monitor to his left.
Aesthetic Score : 0.6
Mood : focused, concentrated, intense
Quality
Entropy : 6.59
Noise : 73
Prompt Clip Score : 0.19
AI Evaluation
Likelihood of AI : 0.10
Image errors : No visible errors in the image.
Lost in the Shadows: A Child’s Eerie Solitude
A haunting image of a child standing alone in a dimly lit hallway, their silhouette stark against the darkness. The long, narrow space evokes a sense of confinement and isolation, leaving the viewer with a feeling of mystery and suspense.
Prompt
facial-expressions Sadness: Loneliness, abandonment ; A child standing in a doorway; eye-level; Single Person; Empty hallway, dim lighting; cinematic
Characteristic
Shot : A young boy stands alone in a dark hallway, the only light source coming from the ceiling fixtures.
Aesthetic Score : 0.4
Mood : lonely, eerie, suspenseful
Quality
Entropy : 6.07
Noise : 62
Prompt Clip Score : 0.19
AI Evaluation
Likelihood of AI : 0.20
Image errors : No significant errors are apparent in the image
Soldier’s Silhouette Against a Blazing Inferno
A lone soldier, helmet shadowed, crouches in a field, the fiery glow of a distant inferno casting an ominous light. The scene evokes a sense of dramatic tension and somber reflection, highlighting the urgency and danger of the situation.
Prompt
facial-expressions Sadness: Loss, regret ; A soldier kneeling on a battlefield; eye-level; Hero; Explosions in the distance, smoke filling the air; cinematic
Characteristic
Shot : A soldier in a helmet and military uniform is crouching in a field, a large fire is burning in the background. The scene is dramatic and evocative.
Aesthetic Score : 0.6
Mood : intense, somber, dramatic
Quality
Entropy : 6.73
Noise : 77
Prompt Clip Score : 0.28
AI Evaluation
Likelihood of AI : 0.10
Image errors : The image appears slightly blurry, particularly in the background. The lighting is a little harsh and could be more balanced.
An Intimate Evening: A Glimpse into a Quiet Moment of Connection
In this subdued scene, a young couple shares an intimate moment on the couch, lost in each other’s gaze. With a bowl of popcorn between them, they enjoy a quiet evening together, their connection illuminated by the soft, warm lighting.
Prompt
facial-expressions Sadness: Silence, unspoken tension ; A couple sitting on a couch; eye-level; Normal People; Empty popcorn bowl, remote control on the floor; cinematic
Characteristic
Shot : Two people are sitting on a couch, possibly watching TV, with a bowl of popcorn in front of them.
Aesthetic Score : 0.6
Mood : intimate, pensive, quiet
Quality
Entropy : 6.64
Noise : 73
Prompt Clip Score : 0.26
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image has a slight blurriness, particularly noticeable in the background and the popcorn bowl. The lighting is also a bit uneven, creating some shadows.
The Bitter Taste of Defeat: A Moment of Disappointment Captured
A person stares at a glowing red and pink computer screen, the stark words ‘game over’ flashing before their eyes. Their expression speaks volumes of frustration and disappointment, capturing the raw emotion of defeat in a single, poignant moment.
Prompt
facial-expressions Sadness: Frustration, defeat ; A gamer’s hands on a keyboard; close-up; Gamer; Screen displaying a game over message; cinematic
Characteristic
Shot : A young man is sitting in front of a computer with the words “Game Over” displayed on the screen. He looks defeated, and his posture is slouched. The room is dimly lit, creating a sense of gloom.
Aesthetic Score : 0.6
Mood : defeated, gloomy, melancholic
Quality
Entropy : 6.63
Noise : 56
Prompt Clip Score : 0.26
AI Evaluation
Likelihood of AI : 0.20
Image errors : There are some slight artifacts present in the image, particularly around the edges of the computer screen.
Lost in the City’s Dream
A woman with long dark hair walks through a bustling city, her gaze lost in the distance. The blurred background and her pensive expression create a melancholic and dreamy atmosphere, leaving the viewer to wonder about her thoughts and destination.
Prompt
facial-expressions Sadness: Alienation, loneliness ; A woman walking down a crowded street; eye-level; Single Person; People passing by, oblivious to her; cinematic
Characteristic
Shot : A woman is walking down a city street, with a blurred background of buildings and people.
Aesthetic Score : 0.7
Mood : melancholy, thoughtful, urban
Quality
Entropy : 6.63
Noise : 76
Prompt Clip Score : 0.21
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image is slightly blurry, especially in the background.
Lost in the City Lights
A young man stands alone in the urban landscape, bathed in the soft glow of distant city lights. His posture and the low lighting evoke a sense of melancholy and introspection, capturing the feeling of loneliness amidst the bustling city.
Prompt
facial-expressions Sadness: Reflection, introspection ; A hero standing on a rooftop; eye-level; Hero; City lights twinkling in the distance; cinematic
Characteristic
Shot : A young man in a black hoodie is standing in an urban setting. He is looking down and appears to be lost in thought. The background is blurry and out of focus, suggesting the city lights are behind him.
Aesthetic Score : 0.6
Mood : melancholy, contemplative, urban
Quality
Entropy : 6.72
Noise : 67
Prompt Clip Score : 0.24
AI Evaluation
Likelihood of AI : 0.30
Image errors : The image has some slight artifacts around the edges of the man’s head and the buildings in the background.
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 0.32, which is below the “good” range of 0.5 to 0.75. This suggests that the model didn’t perfectly capture the intended camera position described in the prompt.
- Shot Analysis: The model scored 0.55, which falls within the “good” range. This indicates that the model was able to understand and translate the scene description from the prompt into a visually coherent shot.
- Aesthetic Analysis: The model scored 0.20, which is significantly below the “very good” range of -0.2 to 0.1. This suggests that the generated image didn’t quite match the expected aesthetic style described in the prompt.
Overall, the model demonstrates a decent understanding of camera position and shot composition, but needs improvement in capturing 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