AI's Facial Expressions: A Mixed Bag of Emotions with Titan-g1
- 9 minutes read - 1906 wordsTable of Contents
Facial expressions are a powerful tool for conveying emotions and telling stories. In the realm of AI, generative models are increasingly capable of creating realistic and expressive faces. However, the ability to accurately capture the nuances of human emotion remains a challenge. This blog post explores the performance of a generative AI model in generating facial expressions, analyzing its strengths and weaknesses in capturing emotions, camera angles, and aesthetic styles. We’ll delve into specific examples, highlighting the model’s successes and areas for improvement, and discuss the potential and limitations of AI in creating emotionally charged imagery.
Created with: titan-g1
Solitude on the Stormy Coast
A lone woman stands on a cliff, dwarfed by the wild, crashing waves and a gray, overcast sky. The scene evokes a sense of dramatic isolation and melancholic contemplation.
Prompt
facial-expressions Disagreement: Melancholy, isolated, conflicted ; A lone figure standing on a clifftop, looking out at a stormy sea; eye-level; Single Person; Dramatic, stormy sky with crashing waves; cinematic
Characteristic
Shot : A lone figure stands on a cliff overlooking a stormy sea.
Aesthetic Score : 0.7
Mood : solitude, dramatic, contemplative
Quality
Entropy : 6.80
Noise : 99
Prompt Clip Score : 0.26
AI Evaluation
Likelihood of AI : 0.30
Image errors : The image is slightly blurry, particularly in the background.
Silhouetted Against the Sunset, a Moment of Contemplation
A young man stands alone, his figure a dark outline against the vibrant hues of a fading sunset. The distant city lights twinkle below, a reminder of the world he’s leaving behind. This evocative image captures a moment of quiet introspection, tinged with a sense of melancholy and peace.
Prompt
facial-expressions Disagreement: Urgent, conflicted, determined ; A lone figure, silhouetted against the setting sun, stands atop a towering mountain, gazing out at a vast, sprawling city below. The wind whips their cloak around them, and the air is filled with the sound of distant laughter.; cinematic
Characteristic
Shot : A young man is silhouetted against a hazy sunset, gazing at a sprawling cityscape in the distance.
Aesthetic Score : 0.5
Mood : pensive, contemplative, melancholic
Quality
Entropy : 6.77
Noise : 92
Prompt Clip Score : 0.26
AI Evaluation
Likelihood of AI : 0.30
Image errors : No major errors, but the image is slightly blurry.
A Heated Argument in the Shadows
A woman’s frustration boils over in a dimly lit setting, her expression and gestures conveying a palpable tension. The man she argues with remains out of focus in the background, adding to the sense of drama and mystery.
Prompt
facial-expressions Disagreement: Angry, tense, frustrated ; A couple arguing in a crowded restaurant, their faces close together; close-up; Normal People; Busy restaurant interior with other diners; cinematic
Characteristic
Shot : A woman is arguing with a man in a restaurant or cafe. Only the woman’s face is visible, and the man is seen from the back.
Aesthetic Score : 0.3
Mood : intense, confrontational, heated
Quality
Entropy : 6.91
Noise : 100
Prompt Clip Score : 0.31
AI Evaluation
Likelihood of AI : 0.10
Image errors : The image is slightly blurry, particularly in the background. The lighting is also not consistent, with some areas being overexposed.
Lost in the Game: A Moment of Intense Focus
A young woman, headphones on, is completely immersed in a video game. The dim lighting and her intense expression create a palpable sense of frustration and concentration, highlighting the dramatic intensity of the moment.
Prompt
facial-expressions Disagreement: Frustrated, intense, focused ; A gamer, hunched over a computer screen, furiously clicking a mouse; close-up; Gamer; Dark room with glowing computer screen and peripherals; cinematic
Characteristic
Shot : A woman is playing a video game, she’s wearing a headset and is yelling with excitement. The scene is set in a dimly lit room with a computer monitor and keyboard in the foreground.
Aesthetic Score : 0.4
Mood : intense, excited, passionate
Quality
Entropy : 6.47
Noise : 106
Prompt Clip Score : 0.27
AI Evaluation
Likelihood of AI : 0.10
Image errors : The image is slightly blurry, particularly in the background. There is some noise in the image, especially in the darker areas. The lighting is uneven, resulting in some areas being too dark.
Lost in Thought: A Moment of Contemplation at the Cafe
A young woman finds solace in a cozy cafe, her gaze fixed on the world outside. The warm lighting, the steaming teapot, and the quiet contemplation create a sense of peace and longing.
Prompt
facial-expressions Disagreement: Disappointed, lonely, withdrawn ; A woman sitting alone in a coffee shop, staring at a phone with a blank expression; eye-level; Single Person; Cozy coffee shop interior with other patrons; cinematic
Characteristic
Shot : A young woman sits in a cafe, looking out the window, lost in thought. There is a cup of coffee on the table, along with a phone and other items. The cafe’s interior is visible in the background, suggesting a cozy and intimate atmosphere.
Aesthetic Score : 0.7
Mood : pensive, contemplative, relaxed
Quality
Entropy : 6.75
Noise : 101
Prompt Clip Score : 0.25
AI Evaluation
Likelihood of AI : 0.10
Image errors : The image is slightly blurry, particularly the subject’s eyes. There is a slight chromatic aberration around the edges of the frame.
Lost in the Shadows: A Woman’s Mysterious Gaze
A woman, shrouded in darkness, stands in a graffiti-laden alleyway. Her intense gaze pierces through the shadows, leaving a lingering sense of mystery and intrigue. The stark lighting and urban backdrop create a tense atmosphere, drawing you into her enigmatic world.
Prompt
facial-expressions Disagreement: Confident, determined, defiant ; A hero, standing in a dark alleyway, looking at a villain with a determined expression; eye-level; Hero; Dark, gritty alleyway with shadows and graffiti; cinematic
Characteristic
Shot : A woman is standing in a narrow alleyway, looking directly at the viewer. The walls are made of rough concrete and are covered in graffiti. The light is dim, casting shadows across the scene. There are some visible pipes on the wall.
Aesthetic Score : 0.6
Mood : mysterious, tense, urban
Quality
Entropy : 6.92
Noise : 98
Prompt Clip Score : 0.23
AI Evaluation
Likelihood of AI : 0.10
Image errors : The image has some artifacts in the shadows, and the woman’s face appears slightly warped. The edges of the image have some blurriness.
Caught in the Heat of the Moment: Three Friends Engage in an Animated Discussion
A snapshot of raw emotion unfolds as three young people gather around a table, their conversation escalating into a heated exchange. The person in the middle speaks with passion, their hands gesturing wildly, while the person on the left reacts with surprise and the person on the right observes with a more neutral expression. The scene captures a moment of intense emotion, leaving the viewer to wonder what sparked the argument and what the outcome will be.
Prompt
facial-expressions Disagreement: Angry, frustrated, heated ; A group of college students passionately debating a philosophical topic in a bustling outdoor cafe, their voices rising in excitement; medium shot; vibrant colors; sunny day with cafe tables and chairs; cinematic
Characteristic
Shot : Three young people sitting at an outdoor table, possibly at a cafe, one person is gesturing animatedly, while another person looks surprised.
Aesthetic Score : 0.4
Mood : intense, argumentative, casual
Quality
Entropy : 6.74
Noise : 99
Prompt Clip Score : 0.30
AI Evaluation
Likelihood of AI : 0.20
Image errors : No noticeable artifacts or errors.
Poker Face: The Thrill of the Game
A man at a casino poker table, his fist clenched, eyes wide with excitement. The tension is palpable as he stares down his opponents, the chips in front of him a testament to the high stakes. This image captures the raw emotion and adrenaline rush of a high-stakes poker game.
Prompt
facial-expressions Disagreement: Frustrated, angry, defeated ; A poker player, slamming his fist on the table, yelling at his cards; close-up; Poker player; Brightly lit casino with multiple poker tables; cinematic
Characteristic
Shot : A man in a casino setting, likely a poker game, celebrating a victory with a loud yell. He is leaning forward on a table with a stack of poker chips in front of him.
Aesthetic Score : 0.6
Mood : excited, dramatic, triumphant
Quality
Entropy : 6.68
Noise : 105
Prompt Clip Score : 0.29
AI Evaluation
Likelihood of AI : 0.20
Image errors : There are no obvious artifacts or errors in the image.
Lost in Thought: A Moment of Contemplation in the City
A man, lost in his own world, walks down a bustling city street, his downcast gaze reflecting a pensive mood. The urban backdrop adds a sense of melancholy and introspection to this contemplative moment.
Prompt
facial-expressions Disagreement: Sad, lonely, rejected ; A man walking away from a group of people, his head down; long shot; Single Person; Busy city street with people walking by; cinematic
Characteristic
Shot : A man is walking down a city street, looking down. A woman is walking behind him.
Aesthetic Score : 0.6
Mood : pensive, urban, lonely
Quality
Entropy : 6.83
Noise : 95
Prompt Clip Score : 0.26
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image has a slight amount of noise and grain, likely due to the lighting conditions.
Lost in the City Lights
A solitary figure stands on a rooftop, gazing out at the twinkling cityscape. The man’s pensive expression and the distant lights evoke a sense of loneliness and longing, capturing the essence of urban contemplation.
Prompt
facial-expressions Disagreement: Thoughtful, conflicted, determined ; A hero, standing on a rooftop, looking at a city skyline with a conflicted expression; eye-level; Hero; City skyline at night with twinkling lights; cinematic
Characteristic
Shot : A man in a dark blue shirt stands on a rooftop looking out over a city skyline at night, with many city lights visible in the background.
Aesthetic Score : 0.6
Mood : pensive, melancholic, contemplative
Quality
Entropy : 6.60
Noise : 103
Prompt Clip Score : 0.28
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image is a little blurry, and the contrast is not well balanced.
Conclusion
The results show 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 0.2, 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 0.5, which is considered average. This indicates that the model was able to understand the scene in the prompt reasonably well, but there’s room for improvement.
- Aesthetic Analysis: The model scored 0.14, which is considered very good. This means the generated image closely matched the expected aesthetic style.
Overall, the model seems to be better at understanding the aesthetic style than the camera position and scene. It might be helpful to provide more specific instructions regarding camera angles and shot composition in future prompts to improve the model’s performance in these areas.
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