AI's Facial Expressions: A Mixed Bag with Leonardo-ai
- 9 minutes read - 1890 wordsTable of Contents
Facial expressions are a powerful tool in storytelling, conveying emotions and intentions without words. In the realm of generative AI, the ability to accurately depict these expressions is crucial for creating compelling and realistic images. This blog post delves into the performance of a generative AI model in capturing facial expressions, analyzing its strengths and weaknesses in translating textual prompts into visual representations.
Created with: leonardo-ai
Lost in the Neon Glow: A Solitary Figure Walks Through a Mysterious Asian City
A lone figure navigates a wet, neon-lit street in a bustling Asian city. The reflections of the vibrant signs in the puddles create an atmosphere of mystery and intrigue, leaving you wondering about the story unfolding in this urban landscape.
Prompt
facial-expressions Realization: Melancholy, introspective ; A lone figure; eye-level; Single Person; a bustling city street at night, with neon signs and rain reflecting on the wet pavement; cinematic
Characteristic
Shot : A lonely figure walks down a rainy street in a city at night, illuminated by neon signs reflecting on the wet pavement.
Aesthetic Score : 0.8
Mood : melancholy, urban, nostalgic
Quality
Entropy : 6.46
Noise : 109
Prompt Clip Score : 0.30
AI Evaluation
Likelihood of AI : 0.20
Image errors : No noticeable artifacts or errors.
Heroic Silhouette: A Guardian Watches Over the City
A powerful image captures the essence of heroism as a superhero, bathed in the golden light of sunset, stands on the edge of a skyscraper overlooking a sprawling cityscape. The scene evokes a sense of drama, hope, and the immense power of the hero to protect the city below.
Prompt
facial-expressions Realization: Triumphant, awe-inspiring ; A superhero, standing atop a skyscraper; wide shot; Hero; a sprawling cityscape bathed in the golden light of sunset; cinematic
Characteristic
Shot : A man in a superhero costume is standing on the edge of a rooftop overlooking a city skyline at sunset. The Empire State Building is visible in the distance.
Aesthetic Score : 0.7
Mood : heroic, powerful, dramatic
Quality
Entropy : 6.87
Noise : 101
Prompt Clip Score : 0.33
AI Evaluation
Likelihood of AI : 0.20
Image errors : There are some minor artifacts in the image, such as the edges of the buildings being slightly jagged.
Lost in Thought: A Moment of Melancholy in a Cluttered Kitchen
A woman sits alone in a dimly lit kitchen, her head resting on her hand, lost in contemplation. The cluttered surroundings and her pensive posture evoke a sense of isolation and loneliness, highlighting the introspective nature of the moment.
Prompt
facial-expressions Realization: Disillusioned, resigned ; A young woman, sitting at a kitchen table; close-up; Normal People; a cluttered kitchen, with dishes piled in the sink and a half-eaten meal on the table; cinematic
Characteristic
Shot : A woman sitting at a kitchen counter, looking out a window. She is dressed in casual clothes and appears to be in a thoughtful or melancholic mood.
Aesthetic Score : 0.6
Mood : melancholy, pensive, subdued
Quality
Entropy : 6.84
Noise : 98
Prompt Clip Score : 0.31
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image appears to be slightly underexposed, with some noise in the shadows.
The Gamer’s Focus: A Moment of Intensity
A young man, headphones on, is completely immersed in his gaming world. The dimly lit room, multiple monitors displaying gaming content, and a half-eaten pizza box create a scene of intense focus and dedication. This image captures the thrill and commitment of a true gamer.
Prompt
facial-expressions Realization: Intense, focused ; A gamer, hunched over a computer screen; close-up; Gamer; a dimly lit room, with flashing lights from the monitor and empty pizza boxes scattered around; cinematic
Characteristic
Shot : A young man is sitting in a dimly lit room, wearing headphones and focused on a computer screen. There are three monitors set up, each displaying a different game. A half-eaten pizza box sits on the desk, suggesting a late-night gaming session.
Aesthetic Score : 0.6
Mood : focused, intense, slightly dark
Quality
Entropy : 6.14
Noise : 90
Prompt Clip Score : 0.26
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image has some slight noise and grain, particularly in the darker areas. The focus appears sharp, but there might be a bit of blurring around the edges of the monitors.
Lost in the Crowd: A Man’s Anxious Gaze in a Tense Subway Station
A man, his face etched with worry, stands amidst the throngs of commuters in a bustling subway station. His intense gaze, locked directly on the viewer, creates a palpable sense of suspense and unease. The crowded background amplifies the feeling of anticipation, leaving you wondering what secrets lie beneath the surface of this tense scene.
Prompt
facial-expressions Realization: Lost, alienated ; A man, walking through a crowded train station; eye-level; Single Person; a sea of faces, all rushing in different directions; cinematic
Characteristic
Shot : A man with a worried expression looks directly at the camera in a crowded subway station.
Aesthetic Score : 0.7
Mood : tense, suspenseful, anxious
Quality
Entropy : 6.50
Noise : 100
Prompt Clip Score : 0.28
AI Evaluation
Likelihood of AI : 0.10
Image errors : No noticeable artifacts or errors.
Superman Stands Tall Amidst Devastation
A lone Superman, unyielding and resolute, stands amidst a cityscape ravaged by explosions and smoke. The image captures the epic scale of the destruction while highlighting Superman’s heroic power and unwavering determination.
Prompt
facial-expressions Realization: Determined, resolute ; A superhero, standing in the middle of a battle; wide shot; Hero; a chaotic scene of destruction and explosions, with enemies closing in; cinematic
Characteristic
Shot : Superman stands confidently in a destroyed city, a background of fire and smoke. His pose suggests a heroic stance, ready to face whatever danger is coming.
Aesthetic Score : 0.7
Mood : intense, heroic, epic
Quality
Entropy : 6.74
Noise : 103
Prompt Clip Score : 0.28
AI Evaluation
Likelihood of AI : 0.70
Image errors : Some blurring in the background and a slightly unnatural look to the smoke and explosions.
Warmth and Laughter Fill the Room
A cozy scene unfolds as three friends gather around a table, bathed in the golden glow of natural light. Their smiles and shared laughter speak of a comfortable and happy moment, captured in this intimate setting.
Prompt
facial-expressions Realization: Nostalgic, heartwarming ; A family, gathered around a dinner table; medium shot; Normal People; a warm and inviting kitchen, with the aroma of home-cooked food filling the air; cinematic
Characteristic
Shot : A family is sitting at a table in a kitchen, eating dinner. They are smiling and laughing, enjoying each other’s company. The table is set with plates of food, and there is a pot of food on the stove. The kitchen is warm and inviting, with natural light streaming in from the window.
Aesthetic Score : 0.7
Mood : happy, cozy, family
Quality
Entropy : 6.81
Noise : 100
Prompt Clip Score : 0.25
AI Evaluation
Likelihood of AI : 0.20
Image errors : No significant image errors, although the lighting may be slightly uneven.
Lost in the Code: A Moment of Intense Focus
A young man, bathed in the blue glow of his computer screen, is completely absorbed in his work. The dimly lit room and his focused gaze create a sense of tension and isolation, highlighting the intensity of his concentration.
Prompt
facial-expressions Realization: Defeated, frustrated ; A gamer, staring at a blank screen; close-up; Gamer; a dimly lit room, with the only light coming from the monitor, which is now displaying a game over message; cinematic
Characteristic
Shot : A young man is sitting at his desk, wearing headphones and looking intently at a computer screen. The scene is dimly lit, with only the glow of the monitor screen illuminating his face.
Aesthetic Score : 0.6
Mood : focused, intense, serious
Quality
Entropy : 6.15
Noise : 92
Prompt Clip Score : 0.26
AI Evaluation
Likelihood of AI : 0.20
Image errors : There is some slight noise in the image, particularly in the darker areas. The colors are a bit muted, and the overall image feels a bit flat.
Silhouetted Against the Sunset: A Moment of Contemplation
A woman stands on a pier, bathed in the golden light of the setting sun. The vast ocean stretches before her, mirroring the quiet melancholy in her gaze. This evocative scene captures a moment of peaceful contemplation, with the dramatic lighting highlighting the woman’s solitude and the beauty of the natural world.
Prompt
facial-expressions Realization: Reflective, contemplative ; A woman, standing on a cliff overlooking the ocean; eye-level; Single Person; a vast expanse of blue water stretching out to the horizon, with the sun setting in the distance; cinematic
Characteristic
Shot : A woman stands by a railing, looking out over the ocean at sunset. The sun is setting behind her, and its light is illuminating her hair and face.
Aesthetic Score : 0.75
Mood : melancholy, contemplative, calm
Quality
Entropy : 6.85
Noise : 97
Prompt Clip Score : 0.30
AI Evaluation
Likelihood of AI : 0.10
Image errors : No noticeable artifacts or errors.
A Lone Hero in the Golden Ruins
A solitary superhero stands tall amidst the crumbling cityscape, bathed in the warm glow of the setting sun. This evocative image captures a sense of both melancholy and hope, as the hero emerges as a beacon of strength in a world ravaged by destruction.
Prompt
facial-expressions Realization: Hopeful, determined ; A superhero, standing in the ruins of a city; wide shot; Hero; a desolate landscape, with smoke rising from the rubble and the sun breaking through the clouds; cinematic
Characteristic
Shot : A lone superhero stands in a post-apocalyptic cityscape, amidst rubble and debris, looking towards a setting sun.
Aesthetic Score : 0.7
Mood : gloomy, hopeful, contemplative
Quality
Entropy : 6.70
Noise : 102
Prompt Clip Score : 0.29
AI Evaluation
Likelihood of AI : 0.10
Image errors : No major image errors are visible.
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 0.25, which is below the “good” range of 0.5 to 0.75. This suggests that the model didn’t accurately capture the intended camera positions described in the prompt.
- Shot Analysis: The model scored 0.43, also below the “good” range. This indicates that the model didn’t fully understand the scene described in the prompt and didn’t create the expected shot composition.
- Aesthetic Analysis: The model scored 0.12, which is within the “very good” range of -0.2 to 0.1. This means the generated image’s aesthetic closely matched the expected aesthetic described in the prompt.
Overall, the model seems to be better at understanding the desired aesthetic than the camera positions and shot composition. This suggests that the model might need further training to improve its ability to interpret and translate camera and shot instructions into visual representations.
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