AI's Facial Expressions: A Mixed Bag with Stability-ai-ultra
- 9 minutes read - 1809 wordsTable of Contents
Facial expressions are a powerful tool in storytelling, conveying emotions and intentions without words. 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 creating images with dramatic facial expressions, analyzing its strengths and weaknesses in capturing camera position, shot analysis, and aesthetic style. We’ll explore examples of where this technology excels and where it still needs improvement, providing insights into the future of AI-generated imagery.
Created with: stability-ai-ultra
Autumn Solitude: A Moment of Contemplation
A solitary figure finds peace amidst the fallen leaves of autumn. The blurred background and muted colors create a sense of tranquility and melancholy, inviting viewers to contemplate the beauty of solitude.
Prompt
facial-expressions Sadness: Melancholy, loneliness ; A lone figure; eye-level; Single Person; Empty park bench with fallen leaves; cinematic
Characteristic
Shot : A lone figure sits on a park bench in a foggy autumn scene, surrounded by fallen leaves. The background features trees with a soft, blueish hue.
Aesthetic Score : 0.7
Mood : melancholy, contemplative, peaceful
Quality
Entropy : 6.89
Noise : 85
Prompt Clip Score : 0.30
AI Evaluation
Likelihood of AI : 0.10
Image errors : No noticeable errors.
The City Awaits: A Superhero Stands Watch in the Rain
A brooding superhero, clad in blue and red, stands alone in the rain-soaked city. The neon lights of the cityscape illuminate the scene, while the hero’s cape billows in the wind. This image captures a sense of drama and suspense, hinting at the hero’s solitary vigil and the challenges that lie ahead.
Prompt
facial-expressions Sadness: Despair, disillusionment ; A superhero in their costume; eye-level; Hero; City skyline at night, rain falling; cinematic
Characteristic
Shot : A superhero, likely Superman, stands in a rain-soaked city at night, facing away from the viewer. The cityscape behind him is illuminated by bright, neon lights.
Aesthetic Score : 0.6
Mood : heroic, dramatic, melancholic
Quality
Entropy : 6.90
Noise : 93
Prompt Clip Score : 0.30
AI Evaluation
Likelihood of AI : 0.80
Image errors : There are some minor artifacts in the image, such as the rain streaks and the cityscape. The texture of the superhero’s costume is also a bit artificial.
A Moment of Solitude: A Woman’s Contemplative Gaze
A woman sits alone at a kitchen table, her gaze fixed directly on the viewer. The lighting and composition evoke a sense of melancholy and isolation, highlighting the introspective nature of the moment. The plate and two cups of coffee suggest a shared meal, now left untouched, adding to the feeling of loneliness.
Prompt
facial-expressions Sadness: Hopelessness, grief ; A woman sitting at a kitchen table; eye-level; Normal People; Empty coffee cup, unwashed dishes; cinematic
Characteristic
Shot : A woman is sitting at a kitchen table, with her elbows on the table, resting her chin on her hands. She looks contemplative. A cup of coffee is in front of her. The kitchen is in the background and looks somewhat cluttered.
Aesthetic Score : 0.6
Mood : melancholy, introspective, contemplative
Quality
Entropy : 6.89
Noise : 83
Prompt Clip Score : 0.27
AI Evaluation
Likelihood of AI : 0.30
Image errors : No noticeable artifacts or errors.
The Gamer’s Glow: Intensity and Focus in a Dimly Lit Room
A young man is completely immersed in his video game, the blue and orange hues of the lighting highlighting his intense focus. The cluttered room, filled with gaming equipment and empty energy drinks, speaks to the dedication and passion of a true gamer.
Prompt
facial-expressions Sadness: Isolation, withdrawal ; A gamer hunched over their computer; close-up; Gamer; Empty pizza boxes, energy drink cans; cinematic
Characteristic
Shot : A young man is playing video games in a dimly lit room. He is wearing a headset and focusing intently on the screen. The room is cluttered with gaming equipment and other items.
Aesthetic Score : 0.6
Mood : intense, focused, gamer
Quality
Entropy : 6.78
Noise : 75
Prompt Clip Score : 0.28
AI Evaluation
Likelihood of AI : 0.20
Image errors : There are some minor artifacts in the image, particularly in the shadows. The image is also slightly over-sharpened, which makes some of the details look artificial.
Silhouetted in Mystery: A Boy’s Lonely Journey
A young boy stands alone in a dimly lit hallway, his figure a stark silhouette against the light at the end. The long, narrow space and the play of light and shadow create a mood of mystery and suspense, leaving you wondering what secrets lie ahead.
Prompt
facial-expressions Sadness: Loneliness, abandonment ; A child standing in a doorway; eye-level; Single Person; Empty hallway, dim lighting; cinematic
Characteristic
Shot : A young boy standing in a dimly lit hallway, facing a doorway with a bright light coming from the other side
Aesthetic Score : 0.5
Mood : mysterious, eerie, suspenseful
Quality
Entropy : 6.39
Noise : 95
Prompt Clip Score : 0.22
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image suffers from slight overexposure in the doorway and a slight graininess in the shadows
A Soldier’s Burden: The Weight of War in a Single Image
This powerful image captures the somber reality of war. A lone soldier, clad in full gear, crouches amidst a ravaged landscape, his gaze fixed on the ground. The towering flames and billowing smoke in the background create a sense of impending danger and the chaos of battle. The soldier’s posture and the overall mood evoke a feeling of vulnerability and the heavy weight of conflict.
Prompt
facial-expressions Sadness: Loss, regret ; A soldier kneeling on a battlefield; eye-level; Hero; Explosions in the distance, smoke filling the air; cinematic
Characteristic
Shot : A soldier in camouflage uniform sits on the ground in front of a large explosion and smoke plume. The ground is littered with debris, suggesting a battlefield.
Aesthetic Score : 0.6
Mood : serious, somber, intense
Quality
Entropy : 6.89
Noise : 86
Prompt Clip Score : 0.28
AI Evaluation
Likelihood of AI : 0.10
Image errors : No major image artifacts or errors are visible.
Intimate Moments on the Couch
A couple cuddles on the couch, lost in the glow of the television. Scattered popcorn and a bowl on the floor tell a story of shared laughter and cozy intimacy. The soft lighting and composition create a sense of connection and warmth, capturing the essence of a quiet, relaxed evening.
Prompt
facial-expressions Sadness: Silence, unspoken tension ; A couple sitting on a couch; eye-level; Normal People; Empty popcorn bowl, remote control on the floor; cinematic
Characteristic
Shot : A couple is sitting on a couch, watching TV. There are popcorn kernels scattered on the floor and two remote controls.
Aesthetic Score : 0.7
Mood : calm, quiet, intimate
Quality
Entropy : 4.27
Noise : 52
Prompt Clip Score : 0.28
AI Evaluation
Likelihood of AI : 0.90
Image errors : The image is slightly pixelated, and the edges of the objects are not as sharp as they could be.
The Game is Over, But the Nostalgia Remains
A player sits defeated, staring at the ‘Game Over’ screen. The blue glow of the monitor and the soft lighting create a nostalgic atmosphere, even as the player prepares to start anew. This image captures the bittersweet feeling of defeat and the enduring power of gaming.
Prompt
facial-expressions Sadness: Frustration, defeat ; A gamer’s hands on a keyboard; close-up; Gamer; Screen displaying a game over message; cinematic
Characteristic
Shot : A person is sitting at a computer desk, the screen of the computer displays ‘GAME OVER’ in pixelated text. The person’s hands are on the keyboard.
Aesthetic Score : 0.5
Mood : defeated, frustrated, somber
Quality
Entropy : 6.76
Noise : 68
Prompt Clip Score : 0.24
AI Evaluation
Likelihood of AI : 0.00
Image errors : No noticeable errors
Lost in the City’s Symphony
A solitary figure, shrouded in green, stands amidst the bustling chaos of a city street. The blurred background creates a sense of mystery, drawing the eye to the woman’s contemplative gaze. This image captures a moment of quiet introspection in the heart of urban life.
Prompt
facial-expressions Sadness: Alienation, loneliness ; A woman walking down a crowded street; eye-level; Single Person; People passing by, oblivious to her; cinematic
Characteristic
Shot : A woman stands in a city street with blurred out people behind her. She is looking directly at the camera, with a serious and somewhat melancholic expression.
Aesthetic Score : 0.7
Mood : melancholic, serious, urban
Quality
Entropy : 6.75
Noise : 91
Prompt Clip Score : 0.22
AI Evaluation
Likelihood of AI : 0.20
Image errors : No visible errors.
Silhouetted in the City’s Embrace
A solitary figure stands on a rooftop, their silhouette stark against the backdrop of a city awash in dusk. The blurred lights create a bokeh effect, adding to the sense of melancholy and contemplation. This image captures the essence of urban solitude, a moment of quiet reflection amidst the bustling city.
Prompt
facial-expressions Sadness: Reflection, introspection ; A hero standing on a rooftop; eye-level; Hero; City lights twinkling in the distance; cinematic
Characteristic
Shot : A silhouette of a man standing on the edge of a rooftop overlooking a city at night, with the lights of the city blurred in the background and a colorful sunset sky above.
Aesthetic Score : 0.7
Mood : melancholy, contemplative, urban
Quality
Entropy : 6.61
Noise : 76
Prompt Clip Score : 0.27
AI Evaluation
Likelihood of AI : 0.60
Image errors : The image has some slight blurring and noise, especially in the background. The city lights appear slightly artificial and lack natural variation.
Conclusion
The analysis shows 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 0.35, 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 0.515, 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 0.15, which is considered very good. This means that the generated image closely matched the expected aesthetic style.
Overall, the model demonstrates a good understanding of the scene and shot composition, but needs improvement in accurately capturing the intended camera position.
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