AI's Facial Expressions: A Step Forward, But Still Room for Growth with Leonardo-ai
- 9 minutes read - 1841 wordsTable of Contents
Facial expressions are a powerful tool for conveying emotions and intentions in storytelling. In the realm of AI-generated imagery, capturing these nuances accurately is crucial for creating compelling and engaging visuals. This blog post examines the capabilities of a generative AI model in producing images with specific facial expressions, exploring its strengths and weaknesses in capturing the desired aesthetic.
Created with: leonardo-ai
Lost in the Neon Glow: A Man’s Mysterious Gaze
A brooding figure, clad in leather, stands bathed in the vibrant hues of a city night. His intense stare, locked directly on the viewer, evokes a sense of mystery and intrigue. The dramatic lighting and the man’s enigmatic presence create an atmosphere of suspense and tension, leaving you questioning what secrets lie hidden in the shadows.
Prompt
facial-expressions Disappointment: Melancholy, isolation ; A lone figure; eye-level; Single Person; a bustling city street at night, with neon signs and blurred lights; cinematic
Characteristic
Shot : A man in a leather jacket stands on a city street at night, with neon lights in the background. It is likely raining.
Aesthetic Score : 0.7
Mood : mysterious, urban, moody
Quality
Entropy : 6.63
Noise : 94
Prompt Clip Score : 0.22
AI Evaluation
Likelihood of AI : 0.10
Image errors : The image has some minor artifacts, particularly in the background. The edges of the subject’s hair also appear slightly blurred.
Superman Stands Tall Against the Setting Sun
A powerful image captures Superman, clad in his iconic costume, silhouetted against a breathtaking sunset. The city skyline stretches out before him, reflecting the dramatic mood and heroic spirit of the moment. This image evokes a sense of hope and the unwavering strength of a true hero.
Prompt
facial-expressions Disappointment: Defeated, disillusioned ; A superhero standing on a rooftop; eye-level; Hero; a cityscape bathed in the orange glow of a setting sun, with the hero’s cape billowing in the wind; cinematic
Characteristic
Shot : A man dressed as Superman stands on a rooftop, looking out at a city skyline at sunset. The sky is a dramatic orange and purple, and the cityscape is silhouetted in the distance.
Aesthetic Score : 0.7
Mood : heroic, dramatic, contemplative
Quality
Entropy : 6.58
Noise : 96
Prompt Clip Score : 0.30
AI Evaluation
Likelihood of AI : 0.30
Image errors : The image is slightly overexposed, particularly in the sky, and there are some minor artifacts on the subject’s costume.
A Moment of Quiet Reflection
A woman sits alone at a kitchen table, her head resting in her hand, lost in thought. The soft lighting and intimate composition evoke a sense of sadness and contemplation, highlighting the loneliness of the moment.
Prompt
facial-expressions Disappointment: Hopelessness, resignation ; A woman sitting at a kitchen table; eye-level; Normal Person; a cluttered kitchen with dirty dishes and a half-eaten meal; cinematic
Characteristic
Shot : A woman is sitting at a kitchen table, looking forlorn, with a plate of food in front of her.
Aesthetic Score : 0.6
Mood : sad, lonely, contemplative
Quality
Entropy : 6.80
Noise : 95
Prompt Clip Score : 0.29
AI Evaluation
Likelihood of AI : 0.20
Image errors : No visible artifacts or errors
Intense Focus: A Man Lost in the Digital World
A man sits hunched over his computer, his face illuminated by a single, dramatic light source. His intense gaze is fixed on something in the distance, creating a sense of mystery and suspense. The scene evokes a mood of focused determination and seriousness, leaving the viewer wondering what captivating him so deeply.
Prompt
facial-expressions Disappointment: Frustration, anger ; A gamer sitting in front of a computer screen; eye-level; Gamer; a dimly lit room with flashing lights and the glow of the monitor reflecting in their eyes; cinematic
Characteristic
Shot : A young man sits at a computer in a dimly lit room. The background is blurred, and the man is looking intensely at the camera.
Aesthetic Score : 0.6
Mood : intense, focused, serious
Quality
Entropy : 6.55
Noise : 89
Prompt Clip Score : 0.24
AI Evaluation
Likelihood of AI : 0.20
Image errors : There is a slight overexposure in the subject’s face.
Lost in the Gloom: A Solitary Walk Through a Wet City
A man walks alone down a narrow, rain-soaked street, his silhouette a stark contrast against the overcast sky. The buildings on either side seem to close in, amplifying the sense of loneliness and introspection that permeates the scene.
Prompt
facial-expressions Disappointment: Loneliness, despair ; A man walking down a deserted street; eye-level; Single Person; a street lined with closed shops and flickering streetlights; cinematic
Characteristic
Shot : A man in a dark coat walks down a deserted street in the city. The street is wet from rain, and the buildings on either side of the street are tall and gray.
Aesthetic Score : 0.6
Mood : gloomy, solitary, melancholic
Quality
Entropy : 6.84
Noise : 101
Prompt Clip Score : 0.25
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image has a slight amount of noise, and the colors are a bit muted. The image also has a slight bit of blur, but it is not overly noticeable.
Solitude Amidst the Ashes
A solitary figure sits amidst the ruins of a ravaged city, smoke and fire painting a backdrop of destruction. His posture speaks of despair and shock, capturing the raw emotion of a world lost. The stark contrast between his stillness and the chaotic surroundings amplifies the tragedy of the scene.
Prompt
facial-expressions Disappointment: Disappointment, regret ; A hero standing over a fallen villain; eye-level; Hero; a battlefield littered with debris and smoke, with the villain’s defeated form at the hero’s feet; cinematic
Characteristic
Shot : A man in a suit sits on the ground in a war-torn city, surrounded by debris and fire. He appears distraught, holding his head in his hands.
Aesthetic Score : 0.7
Mood : desolate, somber, melancholic
Quality
Entropy : 6.72
Noise : 99
Prompt Clip Score : 0.26
AI Evaluation
Likelihood of AI : 0.20
Image errors : No visible artifacts or errors in the image.
Silent Tension: A Family’s Uncomfortable Gathering
A dimly lit room, a family gathered around a table, but the air is thick with unspoken tension. Their postures and expressions speak volumes, hinting at a conflict simmering beneath the surface. The subdued lighting and composition amplify the sense of unease, leaving the viewer to wonder what secrets lie hidden within this family’s gathering.
Prompt
facial-expressions Disappointment: Tension, estrangement ; A family gathered around a dinner table; eye-level; Normal People; a table set with a simple meal, but with an uncomfortable silence hanging in the air; cinematic
Characteristic
Shot : A family is sitting at a dinner table in a dimly lit room, the mother and daughter are looking at the father who is looking down at his plate, there are plates of food, wine glasses and oranges on the table.
Aesthetic Score : 0.6
Mood : tense, dramatic, uncomfortable
Quality
Entropy : 6.81
Noise : 98
Prompt Clip Score : 0.24
AI Evaluation
Likelihood of AI : 0.20
Image errors : No visible errors
In the Shadows of Focus: A Man’s Intense Concentration
A dimly lit room, a man hunched over his computer, his expression etched with focus. The low lighting and his intense gaze create a palpable sense of suspense and mystery. What is he working on? What secrets lie hidden in the digital shadows?
Prompt
facial-expressions Disappointment: Defeat, frustration ; A gamer staring at a game over screen; eye-level; Gamer; a darkened room with the glow of the monitor reflecting in their eyes, showing a game over message; cinematic
Characteristic
Shot : A man looking intently at a computer screen, the lighting is blue and there is a soft red light in the background.
Aesthetic Score : 0.7
Mood : intense, focused, mysterious
Quality
Entropy : 6.21
Noise : 88
Prompt Clip Score : 0.23
AI Evaluation
Likelihood of AI : 0.10
Image errors : No visible errors
Lost in the Rain: A Moment of Melancholy
A woman gazes out a rain-streaked window, her face etched with sadness and worry. The gloomy atmosphere and dramatic use of light and shadow create a sense of isolation and loneliness, capturing a moment of deep contemplation.
Prompt
facial-expressions Disappointment: Sadness, longing ; A woman standing at a window; eye-level; Single Person; a rainy day with the city streets blurred in the background; cinematic
Characteristic
Shot : A woman is looking out a window at a rainy day. She is standing in a room with a window and a view of a city street.
Aesthetic Score : 0.6
Mood : melancholy, pensive, contemplative
Quality
Entropy : 6.83
Noise : 98
Prompt Clip Score : 0.23
AI Evaluation
Likelihood of AI : 0.10
Image errors : The image has some artifacts, such as graininess and a slight blur. The background is also a bit blurry. The image is not perfectly sharp.
Solitude and Sunset on the Mountaintop
A lone hiker stands silhouetted against the breathtaking panorama of a snow-covered mountaintop, bathed in the warm glow of the setting sun. The scene evokes a sense of serenity, contemplation, and adventure, capturing the beauty and solitude of the natural world.
Prompt
facial-expressions Disappointment: Isolation, disillusionment ; A hero standing on a mountaintop; eye-level; Hero; a vast landscape stretching out before them, but with a sense of emptiness in the air; cinematic
Characteristic
Shot : A lone hiker stands on a snowy mountain peak, looking out at a vast mountain range in the distance. The sky is a soft orange and pink, suggesting sunset or sunrise.
Aesthetic Score : 0.7
Mood : peaceful, serene, contemplative
Quality
Entropy : 6.87
Noise : 94
Prompt Clip Score : 0.22
AI Evaluation
Likelihood of AI : 0.10
Image errors : No noticeable image errors.
Conclusion
The analysis shows 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, indicating a slight deviation from the intended camera position in the prompt. This suggests the model is somewhat capable of understanding and implementing camera positions, but could be improved.
- Shot Analysis: The model scored 0.52, indicating a good understanding of the scene described in the prompt. This suggests the model is able to translate the prompt into a visually coherent scene.
- Aesthetic Analysis: The model scored -0.09, indicating a significant difference between the expected aesthetic and the actual aesthetic of the generated image. This suggests the model struggled to capture the desired aesthetic style.
Overall, the model shows promise in understanding scene composition and camera positioning, but needs improvement in capturing the intended 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://leonardo.ai