AI's Facial Expressions: A Mixed Bag of Success with Stability-ai-ultra
- 9 minutes read - 1896 wordsTable of Contents
Facial expressions are a powerful tool in storytelling, conveying emotions and intentions without words. In the realm of generative AI, accurately capturing these expressions is crucial for creating realistic and engaging visuals. This blog post examines the performance of a generative AI model in depicting facial expressions across a range of scenes, analyzing its strengths and weaknesses. We’ll explore how the model interprets camera position, shot composition, and aesthetic, providing insights into the current state of AI’s ability to understand and generate nuanced facial expressions.
Created with: stability-ai-ultra
Lost in the Neon Maze
A solitary figure, shrouded in darkness, navigates a vibrant cityscape bathed in neon light. The blurred background and silhouetted form evoke a sense of loneliness and mystery, leaving the viewer to wonder about the man’s journey and the secrets he carries.
Prompt
facial-expressions Skepticism: Melancholy, disillusioned ; A lone figure, back turned, walking away from a brightly lit city skyline; eye-level; Single Person; Urban, neon signs, bustling crowds; cinematic
Characteristic
Shot : A person walks away from the camera in a city with bright neon lights. The person is in the foreground and the lights are in the background, creating a sense of depth. The person is silhouetted against the lights, which makes the image feel mysterious.
Aesthetic Score : 0.6
Mood : lonely, urban, nocturnal
Quality
Entropy : 6.42
Noise : 71
Prompt Clip Score : 0.27
AI Evaluation
Likelihood of AI : 0.20
Image errors : No visible errors, the lighting could be slightly overexposed.
Hero Stands Tall Amidst the Flames
A dramatic scene unfolds as a superhero, silhouetted against a fiery backdrop, surveys a burning city. The contrast between the dark figure and the bright flames creates a powerful image of heroism and intensity.
Prompt
facial-expressions Skepticism: Doubtful, conflicted ; A superhero, cape billowing, standing on a rooftop, looking down at a city in chaos; eye-level; Hero; Smoke, fire, destruction; cinematic
Characteristic
Shot : A superhero stands on a rooftop overlooking a burning city skyline with a large plume of smoke in the background.
Aesthetic Score : 0.6
Mood : dramatic, somber, heroic
Quality
Entropy : 6.87
Noise : 86
Prompt Clip Score : 0.29
AI Evaluation
Likelihood of AI : 0.90
Image errors : The flames appear slightly unrealistic, and the textures on the superhero’s suit are a bit too smooth.
A Moment of Reflection: Mystery in the Cafe
A young woman, her gaze fixed on the viewer, sits in a bustling cafe, a newspaper obscuring her features. The blurred background and casual setting create an intimate atmosphere, leaving the viewer to wonder about her thoughts and the story behind her enigmatic expression.
Prompt
facial-expressions Skepticism: Cynical, disbelieving ; A woman, dressed in everyday clothes, holding a newspaper with a sensational headline; eye-level; Normal People; Coffee shop, people going about their day; cinematic
Characteristic
Shot : A woman in a yellow sweater is sitting in a cafe, holding a newspaper in front of her. The newspaper is titled “Skepstinalic” with some text in a foreign language, and an image of a group of people. The scene is set in a cafe with other people blurred in the background.
Aesthetic Score : 0.6
Mood : curious, contemplative, mysterious
Quality
Entropy : 6.88
Noise : 88
Prompt Clip Score : 0.33
AI Evaluation
Likelihood of AI : 0.20
Image errors : There are no visible artifacts or errors in the image.
Lost in the Glow: A Gamer’s Intense Focus
A young man is completely absorbed in his video game, the blue light of the screen reflecting off his face. The dimly lit room is bathed in a red glow, creating a sense of mystery and intensity. This image captures the immersive experience of gaming, highlighting the player’s focused expression and the dramatic lighting.
Prompt
facial-expressions Skepticism: Suspicious, wary ; A gamer, hunched over a computer screen, surrounded by empty pizza boxes and energy drink cans; close-up; Gamer; Dark room, flashing lights, gaming peripherals; cinematic
Characteristic
Shot : A young man is playing a video game in a dark room with red and blue lighting. He is sitting in a gaming chair in front of a computer monitor with a game running.
Aesthetic Score : 0.6
Mood : intense, focused, futuristic
Quality
Entropy : 6.55
Noise : 70
Prompt Clip Score : 0.22
AI Evaluation
Likelihood of AI : 0.10
Image errors : There is a slight blurriness to the image, particularly around the edges.
Lost in the Neon Rain
A solitary figure sits at a dimly lit bar, lost in thought as the rain pours outside. Neon lights cast a moody glow, highlighting the man’s pensive expression and creating an atmosphere of melancholy and isolation.
Prompt
facial-expressions Skepticism: Doubtful, introspective ; A man, sitting alone in a dimly lit bar, staring into his drink; eye-level; Single Person; Empty bar, flickering neon lights, rain outside; cinematic
Characteristic
Shot : A man sitting at a bar counter in the rain, looking thoughtful with a drink in front of him. The bar is lit up with neon lights, creating a moody atmosphere.
Aesthetic Score : 0.7
Mood : melancholy, moody, urban
Quality
Entropy : 6.44
Noise : 75
Prompt Clip Score : 0.31
AI Evaluation
Likelihood of AI : 0.30
Image errors : The image has some minor noise and blurriness, especially in the background. The rain drops are somewhat pixelated, giving a slightly artificial feel.
Lost in the Spotlight: A Man’s Intense Gaze Amidst the Blurred Lights
A solitary figure stands at the heart of a vibrant concert venue, his piercing gaze locked on the camera. The blurred lights and the surrounding crowd create an atmosphere of mystery and suspense, leaving the viewer questioning the man’s story and the secrets he holds.
Prompt
facial-expressions Skepticism: Uncertain, hesitant ; A hero, standing in front of a crowd, holding a weapon, but looking conflicted; eye-level; Hero; cheering crowd, bright lights, stage; cinematic
Characteristic
Shot : A man standing in front of a crowd at a concert or event, the background is blurred, the lights are colorful and there is a lot of energy in the scene.
Aesthetic Score : 0.7
Mood : intense, dramatic, mysterious
Quality
Entropy : 6.84
Noise : 81
Prompt Clip Score : 0.19
AI Evaluation
Likelihood of AI : 0.10
Image errors : The image is slightly overexposed, and the background is a bit noisy.
A Family Dinner Gone Wrong
A tense atmosphere hangs over a family gathering, as concerned expressions and a muted background suggest a serious conversation or a difficult situation. The food on the table, seemingly untouched, adds to the sense of unease.
Prompt
facial-expressions Skepticism: Disbelieving, amused ; A group of friends, gathered around a table, listening to a story with skeptical expressions; eye-level; Normal People; Cozy living room, warm lighting, snacks; cinematic
Characteristic
Shot : A group of people, possibly a family, are sitting around a table, seemingly in a tense conversation. The scene is set in a casual dining setting, with food like burgers and fries on the table. There is a plant visible in the background.
Aesthetic Score : 0.7
Mood : tense, worried, awkward
Quality
Entropy : 6.79
Noise : 74
Prompt Clip Score : 0.22
AI Evaluation
Likelihood of AI : 0.90
Image errors : No major image errors, but some of the characters have slightly distorted proportions, particularly the eyes and mouths.
Neon Glow of Focus: A Young Man’s Intense Concentration
A young man sits at his computer, bathed in vibrant pink and blue neon light. His focused gaze and the dramatic lighting create a sense of intensity and intrigue, drawing you into his world of concentration.
Prompt
facial-expressions Skepticism: Frustrated, doubtful ; A gamer, staring intently at a screen, but with a look of frustration; close-up; Gamer; Brightly lit room, gaming setup, controller in hand; cinematic
Characteristic
Shot : A young man is shown in close-up, looking intently at something outside the frame. His face is illuminated by a bright pink light, with blue light reflecting off his skin.
Aesthetic Score : 0.6
Mood : intense, focused, determined
Quality
Entropy : 6.55
Noise : 77
Prompt Clip Score : 0.29
AI Evaluation
Likelihood of AI : 0.20
Image errors : No visible errors.
Lost in the City: A Woman’s Mysterious Journey
A young woman with long blonde hair navigates a bustling city street, her serious expression hinting at a hidden story. The vibrant awnings and blurred pedestrians create a sense of urban intrigue, leaving you wondering what secrets she carries.
Prompt
facial-expressions Skepticism: Paranoid, distrustful ; A woman, walking through a crowded street, looking around with suspicion; eye-level; Single Person; Busy city street, people rushing by, street vendors; cinematic
Characteristic
Shot : A young woman with long blonde hair walks through a crowded street market, looking slightly annoyed. The background is slightly out of focus, but vibrant with colorful fabrics.
Aesthetic Score : 0.7
Mood : thoughtful, pensive, urban
Quality
Entropy : 6.93
Noise : 90
Prompt Clip Score : 0.25
AI Evaluation
Likelihood of AI : 0.10
Image errors : The image has no noticeable artifacts or errors.
Silhouetted Against the City’s Dreams
A solitary figure stands on a rooftop, bathed in the soft glow of twilight. The city lights twinkle below, mirroring the melancholic mood of the scene. The man’s silhouette against the urban backdrop evokes a sense of contemplation and loneliness, capturing the essence of urban solitude.
Prompt
facial-expressions Skepticism: Isolated, disillusioned ; A hero, standing on a rooftop, looking out at a city skyline, but with a sense of loneliness; eye-level; Hero; City lights, distant sounds of the city; cinematic
Characteristic
Shot : A man in silhouette stands on a rooftop overlooking a city skyline at dusk. The sky is a vibrant purple and orange, with the city lights twinkling in the distance.
Aesthetic Score : 0.7
Mood : melancholy, contemplative, urban
Quality
Entropy : 6.82
Noise : 79
Prompt Clip Score : 0.27
AI Evaluation
Likelihood of AI : 0.20
Image errors : Some of the city lights appear slightly blurry and out of focus. There is a slight noise reduction artifact in the sky.
Conclusion
The results show that the generative AI model performed well in terms of understanding the scene and camera position, but struggled with the aesthetic aspect. Here’s a breakdown:
- Camera Position: The model scored 0.1, indicating a very poor understanding of the camera position specified in the prompt. This suggests the generated image significantly deviates from the intended camera angle.
- Shot Analysis: The model scored 0.485, which is considered good. This means the generated image captured the scene elements and composition reasonably well, but there might be some discrepancies compared to the prompt’s description.
- Aesthetic Analysis: The model scored 0.09, which is considered very good. This indicates that the generated image’s aesthetic closely matches the expected aesthetic, suggesting the model successfully captured the desired visual style.
Overall, the model demonstrates a good understanding of the scene and its composition, but struggles to accurately interpret the camera position. The aesthetic analysis suggests the model successfully captured the desired visual style.
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://stability.ai