Facial expressions are a powerful tool for conveying emotions and intentions in visual storytelling. Generative AI models are increasingly being used to create images with specific facial expressions, but how well do they capture the nuances of human emotion? This blog post delves into the performance of a generative AI model in understanding and generating facial expressions across a range of scenes, exploring its strengths and weaknesses in capturing camera position, scene context, and aesthetic style. We’ll examine examples of successful and less successful outputs, providing insights into the current capabilities and limitations of AI in this domain.
Created with: scenario
Lost in Thought: A Moment of Contemplation in the City
A young woman, cloaked in a beige trench coat, sits alone on a park bench, her gaze fixed on the distant cityscape. The vibrant fall foliage and the bustling city backdrop create a poignant contrast to her pensive mood, inviting viewers to contemplate her inner world.
Prompt
facial-expressions Thoughtfulness: Melancholy, contemplative ; A lone figure sitting on a park bench; eye-level; Single Person; a bustling city park in the background; cinematic
Characteristic
Shot : A woman is sitting on a bench in a park, wearing a trench coat, looking away from the camera. The background is blurred and shows trees and a city skyline.
Aesthetic Score : 0.7
Mood : pensive, contemplative, wistful
Quality
Entropy : 6.77
Noise : 82
Prompt Clip Score : 0.30
AI Evaluation
Likelihood of AI : 0.20
Image errors : No notable errors
Silhouettes of Hope: A Moment of Reflection at Sunset
A young woman sits on the edge of a rooftop, her silhouette outlined against the vibrant hues of a setting sun. The vast cityscape stretches out before her, mirroring the vastness of her thoughts. This image captures a moment of quiet contemplation, tinged with both melancholy and a glimmer of hope.
Prompt
facial-expressions Thoughtfulness: Reflective, introspective ; A superhero standing on a rooftop, looking out at the city; eye-level; Hero; a sprawling cityscape with twinkling lights; cinematic
Characteristic
Shot : A woman sitting on a rooftop overlooking a city skyline at sunset, with a starry sky in the background. The woman is dressed in a blue and white tank top and denim pants, and she is looking up at the sky.
Aesthetic Score : 0.8
Mood : serene, contemplative, hopeful
Quality
Entropy : 6.72
Noise : 97
Prompt Clip Score : 0.28
AI Evaluation
Likelihood of AI : 0.90
Image errors : The image contains a few minor artifacts, such as some blurry areas in the background. The woman’s hair looks a bit too perfect and smooth, lacking natural texture.
Tranquility in Motion: A Moment of Peace on a Scenic Train Ride
A young woman finds solace in a book as she gazes out the window of a train, taking in the breathtaking views of rolling green fields and majestic mountains. The sun bathes the scene in a warm glow, creating a sense of calm and peace. This image captures the essence of a contemplative moment, where the world outside fades away and the focus shifts inward.
Prompt
facial-expressions Thoughtfulness: Peaceful, absorbed ; A woman reading a book on a train; eye-level; Normal Person; a blurry view of passing scenery outside the window; cinematic
Characteristic
Shot : A young woman is reading a book in a train carriage, with the window open and a view of a countryside scene.
Aesthetic Score : 0.7
Mood : peaceful, serene, contemplative
Quality
Entropy : 6.82
Noise : 89
Prompt Clip Score : 0.31
AI Evaluation
Likelihood of AI : 0.10
Image errors : The image appears to be well-composed and without any visible errors.
Focused and Calm: A Woman at Work
A young woman, headphones on, sits at her desk, her fingers flying across the keyboard. The scene is calm and professional, with framed maps and drawings adding a touch of personality to the background. The focus is on her concentration, creating a sense of quiet determination.
Prompt
facial-expressions Thoughtfulness: Intense, focused ; A gamer sitting in a dimly lit room, staring intently at a computer screen; eye-level; Gamer; a cluttered desk with gaming peripherals; cinematic
Characteristic
Shot : A woman sits at a desk with a computer, she is wearing headphones and a hoodie, her hair is tied up, she is looking towards the left and appears to be typing on the keyboard, the room she is in has many framed drawings on the wall.
Aesthetic Score : 0.7
Mood : focused, calm, contemplative
Quality
Entropy : 6.40
Noise : 89
Prompt Clip Score : 0.25
AI Evaluation
Likelihood of AI : 0.90
Image errors : The image looks like it is from a video game or anime-style, the image style makes it look less realistic, the image has slight blur effect, it could be due to compression, there is a small artifact of a line on the woman’s shoulder, there is a small line on the desk, and the images on the wall seem to be blurry
Solitude at Sunset
A young man stands on a beach, his silhouette framed against a breathtaking sunset. The vast ocean and the man’s contemplative pose evoke a sense of calm melancholy and introspection.
Prompt
facial-expressions Thoughtfulness: Solitary, introspective ; A man walking alone on a deserted beach; eye-level; Single Person; the vast ocean stretching out before him; cinematic
Characteristic
Shot : A young man stands on a beach, looking out at the ocean. The sun is setting, casting a warm glow over the scene.
Aesthetic Score : 0.7
Mood : melancholy, contemplative, peaceful
Quality
Entropy : 6.53
Noise : 85
Prompt Clip Score : 0.23
AI Evaluation
Likelihood of AI : 0.80
Image errors : The image is slightly blurry and the colors are a bit oversaturated. The background also appears slightly out of focus.
Firefighter Stands Tall Amidst the Ashes
A female firefighter, clad in full gear, stands in front of a fire-damaged building, her gaze fixed on the horizon. The scene, with its billowing smoke and partially collapsed structure, evokes a sense of both destruction and resilience. The image captures the heroic spirit of firefighters, highlighting their dedication and the challenges they face in the aftermath of a fire.
Prompt
facial-expressions Thoughtfulness: Somber, reflective ; A firefighter standing amidst the ruins of a fire; eye-level; Hero; smoke and debris filling the air; cinematic
Characteristic
Shot : A firefighter in full gear is standing in front of a burning building, looking away from the camera
Aesthetic Score : 0.7
Mood : serious, determined, heroic
Quality
Entropy : 6.87
Noise : 89
Prompt Clip Score : 0.30
AI Evaluation
Likelihood of AI : 0.20
Image errors : No visible errors.
Warmth and Connection: A Cozy Kitchen Gathering
Three friends share laughter and conversation around a beautifully set table, bathed in the warm glow of a kitchen window. The scene captures the essence of intimacy and connection, creating a feeling of cozy comfort.
Prompt
facial-expressions Thoughtfulness: Intimate, connected ; A family gathered around a dinner table; eye-level; Normal People; a warm, inviting kitchen setting; cinematic
Characteristic
Shot : Three people are sitting around a table in a kitchen. The light is coming from the window behind them. The table is set with plates and glasses. The man in the blue shirt is looking at the woman in the yellow shirt. The other woman in the blue dress is looking at the man.
Aesthetic Score : 0.8
Mood : warm, cozy, happy
Quality
Entropy : 6.64
Noise : 98
Prompt Clip Score : 0.29
AI Evaluation
Likelihood of AI : 0.90
Image errors : The image seems to be slightly over-sharpened, and some details, such as the hair and skin, appear a bit artificial.
Pink Hoodie, Big Smile, and Beats: This Photo Is Pure Joy
A close-up portrait bursting with color and energy! This woman’s bright pink hoodie and playful expression, captured against a vibrant backdrop, radiate happiness and excitement. Get ready to feel the good vibes!
Prompt
facial-expressions Thoughtfulness: Excited, immersed ; A gamer holding a controller, eyes glued to the screen; close-up; Gamer; a vibrant, colorful gaming world displayed on the monitor; cinematic
Characteristic
Shot : A young woman wearing headphones, smiling brightly, against a colorful abstract background.
Aesthetic Score : 0.8
Mood : happy, vibrant, energetic
Quality
Entropy : 6.74
Noise : 96
Prompt Clip Score : 0.23
AI Evaluation
Likelihood of AI : 0.90
Image errors : The woman’s hair looks slightly unnatural, and the background appears a bit messy and could benefit from more cohesive color palette.
Lost in a World of Cherry Blossoms
A young woman finds solace amidst a breathtaking display of cherry blossoms, her peaceful expression and the soft, dreamlike atmosphere creating a sense of tranquility and wonder.
Prompt
facial-expressions Thoughtfulness: Peaceful, creative ; A woman sitting on a park bench, sketching in a notebook; eye-level; Single Person; a serene park setting with blooming flowers; cinematic
Characteristic
Shot : A young woman with long brown hair sits on a park bench under a blossoming cherry tree, reading a book.
Aesthetic Score : 0.7
Mood : serene, peaceful, contemplative
Quality
Entropy : 6.71
Noise : 92
Prompt Clip Score : 0.31
AI Evaluation
Likelihood of AI : 0.80
Image errors : The image is slightly blurry in some areas, particularly around the edges of the woman’s hair. The trees in the background look somewhat artificial.
Hope Amidst the Storm: A Superhero’s Determined Gaze
A powerful image of a woman in a superhero costume, her gaze fixed on a dramatic, stormy sky. The scene evokes a sense of determination and hope, suggesting a battle against overwhelming odds.
Prompt
facial-expressions Thoughtfulness: Determined, resolute ; A superhero looking up at the sky, a determined expression on their face; eye-level; Hero; a dramatic sky with dark clouds gathering; cinematic
Characteristic
Shot : A woman in a superhero costume stands against a stormy sky, looking up with a determined expression.
Aesthetic Score : 0.7
Mood : determined, hopeful, powerful
Quality
Entropy : 6.89
Noise : 79
Prompt Clip Score : 0.29
AI Evaluation
Likelihood of AI : 0.20
Image errors : There are no visible errors or artifacts in the image.
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 0.15, 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 0.57, which is considered good. This indicates that the model was able to understand the scene described in the prompt and create a shot that aligns with it.
- Aesthetic Analysis: The model scored 0.02, which is considered very good. This means that the generated image closely matched the expected aesthetic style.
Overall, the model demonstrated a good understanding of the scene and its aesthetic, but struggled with accurately capturing the intended camera position.