AI's Facial Expressions: A Mixed Bag of Success with Scenario
- 9 minutes read - 1722 wordsTable of Contents
Facial expressions are a powerful tool in storytelling, conveying emotions and adding depth to characters. Generative AI models are increasingly being used to create images with specific facial expressions, but how well do they perform? This blog post explores the capabilities of a generative AI model in capturing facial expressions across diverse scenes, analyzing its performance in terms of camera position, shot analysis, and aesthetic style. We’ll examine examples where the model excels and where it falls short, providing insights into the current state of AI-generated facial expressions.
Created with: scenario
Dreamy Moments: A Soft-Featured Woman in Focus
In this captivating image, a young woman with brown hair and freckles steals the spotlight as she gazes upwards on a bustling city street. The dreamy, romantic mood is accentuated by the shallow depth of field, which blurs the background and emphasizes her soft features, creating a truly enchanting scene.
Prompt
facial-expressions Interest: Intrigued, observant ; A lone figure; eye-level; Single Person; bustling city street; cinematic
Characteristic
Shot : A young woman with freckles looking up in a city setting with a blurred out background
Aesthetic Score : 0.8
Mood : pensive, hopeful, dreamy
Quality
Entropy : 6.86
Noise : 100
Prompt Clip Score : 0.19
AI Evaluation
Likelihood of AI : 0.80
Image errors : The image appears to be generated by AI and has some unnatural features, including the skin texture and the eyes.
Fiery Determination: A Woman Faces the Flames
A woman, clad in a black leather jacket, stands defiantly before a roaring fire. Her gaze is intense, her expression determined. The flames behind her create a sense of danger and excitement, hinting at a story of power and resilience.
Prompt
facial-expressions Interest: Focused, determined ; A superhero in a dramatic pose; medium shot; Hero; cityscape with a burning building in the background; cinematic
Characteristic
Shot : A woman in a black leather jacket stands in front of a fiery explosion with a determined look on her face.
Aesthetic Score : 0.6
Mood : intense, dramatic, powerful
Quality
Entropy : 6.87
Noise : 102
Prompt Clip Score : 0.25
AI Evaluation
Likelihood of AI : 0.80
Image errors : The image appears to have some minor artifacts, particularly in the fire. The lighting and colors also appear slightly unrealistic.
Finding Peace in the Pages: A Moment of Tranquility at the Cafe
A woman, bathed in warm sunlight, finds solace in a good book at a cozy cafe. The scene exudes a sense of calm and focus, capturing the beauty of quiet contemplation.
Prompt
facial-expressions Interest: Engrossed, absorbed ; A woman reading a book in a coffee shop; eye-level; Normal People; warm, inviting cafe interior; cinematic
Characteristic
Shot : A young woman in a white shirt and glasses sits at a table in a cafe, reading a book.
Aesthetic Score : 0.7
Mood : calm, relaxed, contemplative
Quality
Entropy : 6.81
Noise : 82
Prompt Clip Score : 0.29
AI Evaluation
Likelihood of AI : 0.20
Image errors : Some minor noise in the background and slight overexposure in the woman’s face.
Lost in Thought: A Moment of Contemplation
A woman, enveloped in a cozy knitted sweater, gazes upwards, headphones on, lost in a world of her own. The soft lighting and her pensive expression create an intimate and mysterious atmosphere, hinting at a moment of deep reflection.
Prompt
facial-expressions Interest: Excited, concentrated ; A gamer intensely focused on a screen; close-up; Gamer; dimly lit room with glowing monitor; cinematic
Characteristic
Shot : A woman wearing headphones is looking off to the side, likely at a computer screen.
Aesthetic Score : 0.7
Mood : thoughtful, contemplative, focused
Quality
Entropy : 6.89
Noise : 85
Prompt Clip Score : 0.26
AI Evaluation
Likelihood of AI : 0.10
Image errors : No visible image artifacts or errors.
Lost in the Storm: A Moment of Contemplation
A young man gazes out a window at a stormy sea, the dramatic lighting casting long shadows and highlighting his pensive expression. The scene evokes a sense of introspection and foreboding, leaving the viewer to wonder what thoughts are swirling in his mind.
Prompt
facial-expressions Interest: Contemplative, thoughtful ; A man gazing out a window at a stormy sky; eye-level; Single Person; dark, moody interior; cinematic
Characteristic
Shot : A young man, possibly in his late teens or early twenties, gazes out of a window. The window frame is white, and the background features a dramatic stormy sky with a hint of orange sunlight peeking through.
Aesthetic Score : 0.75
Mood : melancholy, contemplative, pensive
Quality
Entropy : 6.60
Noise : 91
Prompt Clip Score : 0.27
AI Evaluation
Likelihood of AI : 0.80
Image errors : The image has some minor artifacts and smoothing around the hair and skin, particularly visible in the hair and edges. Some edges of the subject look a little soft. This suggests it might have been created or heavily edited in an AI program.
Golden Hour Confidence
A woman in a white blazer and black pants stands confidently on a rooftop, bathed in the warm glow of the setting sun. The cityscape stretches out before her, inspiring a sense of calm and contemplation.
Prompt
facial-expressions Interest: Confident, determined ; A hero standing on a rooftop overlooking a city; wide shot; Hero; panoramic cityscape with dramatic lighting; cinematic
Characteristic
Shot : A woman in a beige blazer stands on a rooftop overlooking a city skyline at sunset.
Aesthetic Score : 0.7
Mood : calm, contemplative, urban
Quality
Entropy : 6.81
Noise : 77
Prompt Clip Score : 0.26
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image appears slightly blurry, particularly in the background.
Laughter and Love Fill the Air
A heartwarming scene of friends gathered around a table, sharing a meal and laughter. The focus on the woman’s joyful expression creates a sense of intimacy and celebration, capturing the warmth and happiness of the moment.
Prompt
facial-expressions Interest: Happy, engaged ; A group of friends laughing together at a dinner table; eye-level; Normal People; cozy, homey dining room; cinematic
Characteristic
Shot : A group of friends are gathered around a table, laughing and enjoying a meal. The table is set with wine glasses, plates, and a centerpiece of flowers.
Aesthetic Score : 0.8
Mood : joyful, friendly, celebratory
Quality
Entropy : 6.70
Noise : 105
Prompt Clip Score : 0.28
AI Evaluation
Likelihood of AI : 0.80
Image errors : The image has some minor artifacts, such as slight blurring around the edges of some of the objects. The lighting is also a bit uneven in places, and the shadows are not entirely realistic. The image appears to be heavily processed, especially the skin.
Neon Glow, Focused Flow: A Tech-Fueled Moment
A young woman, bathed in vibrant pink and blue neon light, sits intently at her computer, headphones on, fingers flying across the keyboard. The scene captures the energy and focus of a tech-driven world, where passion meets productivity.
Prompt
facial-expressions Interest: Thrilled, focused ; A gamer’s hands rapidly moving across a keyboard and mouse; close-up; Gamer; brightly lit gaming setup with flashing lights; cinematic
Characteristic
Shot : A young woman wearing headphones is sitting in front of a computer keyboard, lit by pink and blue light. She is looking off to the side, engrossed in something.
Aesthetic Score : 0.6
Mood : focused, intense, concentrated
Quality
Entropy : 6.81
Noise : 85
Prompt Clip Score : 0.26
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image is slightly grainy, especially in the darker areas. The colors are a little over-saturated, making the image feel a bit artificial.
Lost in Art: A Moment of Contemplation
A woman in a striking leopard print dress stands captivated before a golden-framed masterpiece in an art gallery. The scene exudes calm and elegance, with a hint of mystery as her gaze draws the viewer’s attention to the hidden story within the painting.
Prompt
facial-expressions Interest: Appreciative, curious ; A woman looking at a painting in a museum; eye-level; Single Person; grand museum hall with intricate artwork; cinematic
Characteristic
Shot : A woman in a leopard print dress stands in an art gallery, admiring a painting on the wall.
Aesthetic Score : 0.7
Mood : contemplative, elegant, calm
Quality
Entropy : 6.83
Noise : 87
Prompt Clip Score : 0.29
AI Evaluation
Likelihood of AI : 0.10
Image errors : No visible errors.
Facing the Blast: A Woman’s Moment of Courage
A woman, backpack in tow, stands defiant in the face of a powerful explosion. Her worried expression and the intense, dramatic scene create a sense of adventure and danger, leaving the viewer on the edge of their seat.
Prompt
facial-expressions Interest: Intense, focused ; A hero facing off against a villain; medium shot; Hero; dramatic, action-packed scene with explosions and smoke; cinematic
Characteristic
Shot : A woman in a white shirt and black backpack standing in front of an explosion. She is looking away from the camera with a serious expression on her face.
Aesthetic Score : 0.7
Mood : intense, action, dramatic
Quality
Entropy : 6.76
Noise : 98
Prompt Clip Score : 0.24
AI Evaluation
Likelihood of AI : 0.20
Image errors : No significant errors.
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 0.25, 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 0.55, which is considered average. This indicates that the model was able to understand the scene in the prompt to a reasonable degree, but not exceptionally well.
- Aesthetic Analysis: The model scored 0.09, which is considered very good. This means that the generated image closely matched the expected aesthetic style described in the prompt.
Overall, the model seems to be better at understanding the aesthetic style than the camera position and scene 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://www.scenario.com