AI Captures the Nuance of Human Emotion: A Look at Facial Expressions in Generated Images with Titan-g1
- 10 minutes read - 1918 wordsTable of Contents
The ability to convey emotions through facial expressions is a hallmark of human communication. Now, AI models are beginning to master this art, generating images that capture the subtle nuances of human emotion. This blog post explores a case study where an AI model was tasked with generating images based on specific scenarios and desired facial expressions. While the model demonstrated impressive capabilities in capturing the aesthetic style of the images, it still faces challenges in accurately replicating camera position and shot composition. We delve into the model’s strengths and weaknesses, providing insights into the ongoing evolution of AI’s understanding of human emotion.
Created with: titan-g1
Laundry Day Blues: When the Washing Machine Becomes Your Enemy
This image captures the universal frustration of laundry day. A woman stands defeated before a washing machine, surrounded by a basket of clothes, her expression and posture radiating stress and overwhelm. The scene speaks to the chaotic reality of household chores and the feeling of being trapped in a never-ending cycle.
Prompt
facial-expressions Frustration: Overwhelmed and defeated ; A single person; eye-level; Single Persons; A cluttered apartment with overflowing laundry baskets and takeout containers.; cinematic
Characteristic
Shot : A woman is standing in a laundry room with a basket of laundry in front of her. She is looking up and has a distressed expression on her face, as if she has just realized that the laundry is not done.
Aesthetic Score : 0.4
Mood : frustrated, overwhelmed, chaotic
Quality
Entropy : 6.93
Noise : 101
Prompt Clip Score : 0.23
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image is slightly overexposed, and there is some noise in the background.
Lost in the City Lights
A solitary figure stands on a rooftop, bathed in the glow of a distant cityscape. Her silhouette against the night sky evokes a sense of melancholy and introspection, highlighting the themes of isolation and loneliness.
Prompt
facial-expressions Frustration: Powerless and angry ; A lone figure stands atop a towering skyscraper, the city lights twinkling below. The wind whips their hair and coat, creating a dramatic silhouette against the night sky.; cinematic
Characteristic
Shot : A woman in a coat is standing on a rooftop, looking out at a city skyline at night. The city lights are blurred in the background, and the sky is a dark blue.
Aesthetic Score : 0.6
Mood : dramatic, mysterious, urban
Quality
Entropy : 6.72
Noise : 107
Prompt Clip Score : 0.28
AI Evaluation
Likelihood of AI : 0.30
Image errors : There is some noise in the image, particularly in the background. There are also some artifacts in the city lights, which make them appear less realistic.
Man’s Furious Outburst on Train Sparks Curiosity
A man in a suit, his face contorted with emotion, yells out on a crowded train. The scene is filled with tension, leaving viewers wondering what sparked his outburst. The out-of-focus hand and another person in the background add to the mystery, hinting at a dramatic and possibly unexpected situation.
Prompt
facial-expressions Frustration: Impatient and stressed ; A businessman; eye-level; Normal People; A crowded train with people pushing and shoving, the businessman trapped in the middle.; cinematic
Characteristic
Shot : A man in a suit is sitting on a train, looking out the window and yelling. The photo is shot from an unusual angle, with the camera pointed directly at the man’s face, as if taken from another person sitting next to him.
Aesthetic Score : 0.6
Mood : intense, dramatic, frustrated
Quality
Entropy : 6.81
Noise : 96
Prompt Clip Score : 0.25
AI Evaluation
Likelihood of AI : 0.20
Image errors : There are no significant image errors.
Caught in the Moment: Gamer’s Shock and Awe
A young man, bathed in vibrant blue and purple light, sits transfixed before his computer. Headphones on, his expression is a mix of surprise and intensity, suggesting a moment of high stakes and unexpected action. The scene captures the raw emotion and focus of a gamer caught in the heat of the game.
Prompt
facial-expressions Frustration: Focused but frustrated ; A gamer; close-up; Gamer; A dimly lit room with a computer screen displaying a frustratingly difficult level, the gamer’s hands shaking on the keyboard.; cinematic
Characteristic
Shot : A young man is playing a video game in a dimly lit room. He is wearing headphones and has his hands raised in excitement.
Aesthetic Score : 0.5
Mood : intense, focused, competitive
Quality
Entropy : 6.79
Noise : 102
Prompt Clip Score : 0.26
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image appears slightly grainy. The lighting is uneven, creating harsh shadows on the subject’s face.
Lost in Thought: A Moment of Contemplation in the Park
A young woman, shrouded in a black leather jacket, sits alone on a park bench, her gaze fixed on her phone. The blurry background suggests a peaceful setting, yet her posture and expression convey a sense of melancholy and introspection. This image captures a moment of quiet contemplation, hinting at a deeper emotional state.
Prompt
facial-expressions Frustration: Lonely and isolated ; A young woman; eye-level; Single Persons; A deserted park bench, the woman staring blankly at the ground, her phone lying forgotten beside her.; cinematic
Characteristic
Shot : A young woman sits on a park bench, looking at her phone, with a thoughtful expression on her face.
Aesthetic Score : 0.6
Mood : pensive, melancholic, contemplative
Quality
Entropy : 6.91
Noise : 98
Prompt Clip Score : 0.20
AI Evaluation
Likelihood of AI : 0.20
Image errors : No visible artifacts or errors
Firefighter Braces for Danger in Blazing Building
A firefighter, clad in protective gear, faces the intense heat and smoke as he opens a door in a burning building. The close-up shot captures the urgency and danger of the situation, highlighting the bravery of those who fight fires.
Prompt
facial-expressions Frustration: Urgent and desperate ; A firefighter; close-up; Heroes; A burning building with smoke billowing out, the firefighter struggling to open a door.; cinematic
Characteristic
Shot : A firefighter in full gear, wearing a helmet with a face shield, is opening a door. There is smoke and fire behind the door. The firefighter’s expression is one of determination and fear.
Aesthetic Score : 0.6
Mood : intense, dramatic, suspenseful
Quality
Entropy : 6.82
Noise : 99
Prompt Clip Score : 0.30
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image is slightly blurry, which could be due to camera shake or a low shutter speed. There is a slight artifact in the lower right of the image.
A Moment of Surprise in the Library
A young woman, immersed in a world of books, is caught off guard by an unexpected discovery. Her surprised expression, captured in this image, hints at a moment of intrigue and anticipation. The focus on her face, framed by the stacks of books, creates a sense of drama and invites the viewer to wonder what has sparked her reaction.
Prompt
facial-expressions Frustration: Overwhelmed and anxious ; A student; eye-level; Normal People; A crowded library with students hunched over books, the student staring at a blank page, their pen hovering over the paper.; cinematic
Characteristic
Shot : A young woman sits in a library with a book open in front of her, she has a surprised expression on her face and looks as if she just came to a shocking revelation while reading. There are bookshelves full of books behind her.
Aesthetic Score : 0.6
Mood : focused, surprised, inquisitive
Quality
Entropy : 6.87
Noise : 97
Prompt Clip Score : 0.24
AI Evaluation
Likelihood of AI : 0.20
Image errors : There are no noticeable errors in the image.
Caught in the Heat of the Game: A Moment of Surprise
A young man, immersed in a video game, is caught in a moment of surprise. The dramatic lighting highlights his intense focus and the controller in his hand, capturing the thrill of the game.
Prompt
facial-expressions Frustration: Focused and intense ; A gamer; close-up; Gamer; A brightly lit gaming tournament stage, the gamer staring at the screen, their controller gripped tightly in their hands.; cinematic
Characteristic
Shot : A young man is playing a video game, wearing headphones and holding a controller. The background is blurry and dark, with a blue and red light shining.
Aesthetic Score : 0.6
Mood : intense, focused, competitive
Quality
Entropy : 6.63
Noise : 106
Prompt Clip Score : 0.26
AI Evaluation
Likelihood of AI : 0.30
Image errors : Slight blurriness around the edges, possible compression artifacts
Caught in the Chaos: A Woman’s Shocking Kitchen Reality
A messy kitchen, overflowing with dishes and bills, sets the stage for a woman’s stunned reaction. The scene captures the chaotic and stressful reality of everyday life, leaving viewers wondering what caused her surprise.
Prompt
facial-expressions Frustration: Exhausted and defeated ; A single mother; eye-level; Single Persons; A messy kitchen with dishes piled high in the sink, the single mother staring at a pile of bills, her shoulders slumped.; cinematic
Characteristic
Shot : A woman is standing in a kitchen, looking distressed with her mouth open. The scene is cluttered with dishes, money, and kitchen appliances.
Aesthetic Score : 0.2
Mood : disarray, tension, frustration
Quality
Entropy : 6.94
Noise : 105
Prompt Clip Score : 0.25
AI Evaluation
Likelihood of AI : 0.10
Image errors : The image appears slightly blurry and there is some noise, particularly in the darker areas.
Doctor’s Worried Gaze: A Close-Up Look at Medical Tension
A close-up shot captures a female doctor’s concerned expression in a hospital room, highlighting the seriousness and urgency of the medical situation.
Prompt
facial-expressions Frustration: Concerned and helpless ; A doctor; close-up; Heroes; A hospital room with a patient hooked up to machines, the doctor looking at a medical chart with a furrowed brow.; cinematic
Characteristic
Shot : A woman, likely a doctor or nurse, is in a hospital room. The scene is focused on her face and upper body.
Aesthetic Score : 0.6
Mood : serious, concerned, medical
Quality
Entropy : 6.87
Noise : 95
Prompt Clip Score : 0.27
AI Evaluation
Likelihood of AI : 0.10
Image errors : The image is slightly blurry, especially in the background, which suggests it was taken in a low-light situation.
Conclusion
The analysis shows that the generative AI model performed okay in terms of camera position and shot analysis, but very well in terms of aesthetic analysis.
Here’s a breakdown:
- Camera Position: The model scored 0.3, which is below the “good” range of 0.5 to 0.75. This suggests that the model didn’t quite capture the intended camera position as 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 the scene in the prompt reasonably well, but could be better.
- Aesthetic Analysis: The model scored 0.28, which is within the “very good” range of -0.2 to 0.1. This means the generated image closely matched the expected aesthetic style.
Overall, the model seems to be better at understanding the desired aesthetic than the specific camera position and shot composition.
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://docs.aws.amazon.com/bedrock/latest/userguide/titan-image-models.html