AI's Facial Expressions: A Mixed Bag with Stability-ai-ultra
- 9 minutes read - 1851 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 explores the capabilities of a generative AI model in creating images with dramatic facial expressions, analyzing its performance in capturing camera positions, shot types, and aesthetics. We’ll examine examples of where this technology is being used and discuss its potential for the future.
Created with: stability-ai-ultra
Lost in the Neon Glow: A Solitary Figure Walks the City Streets
A hooded figure blends into the vibrant cityscape, their silhouette shrouded in mystery as they navigate the brightly lit streets. The bokeh effect adds a touch of isolation, leaving the viewer to wonder about their journey and their secrets.
Prompt
facial-expressions Anxiety: Overwhelmed, isolated ; A lone figure; eye-level; Single Person; bustling city street at night; cinematic
Characteristic
Shot : A lone person in a hooded jacket walks down a city street at night, with the streetlights and neon signs creating a blurred background of colorful lights.
Aesthetic Score : 0.6
Mood : lonely, urban, nighttime
Quality
Entropy : 6.85
Noise : 75
Prompt Clip Score : 0.25
AI Evaluation
Likelihood of AI : 0.50
Image errors : The image appears to be slightly overexposed in the background, leading to some blown-out highlights in the neon signs. The bokeh is also slightly artificial looking, with some circular lights appearing overly smooth and lacking in detail.
Superman, Guardian of the Night
A dramatic shot of Superman standing on a rooftop, bathed in the warm glow of city lights. His determined gaze and powerful pose evoke a sense of heroism and contemplation. The bokeh effect adds a touch of magic to the scene, highlighting the extraordinary nature of the moment.
Prompt
facial-expressions Anxiety: Pressure, responsibility ; A superhero standing on a rooftop; high angle; Hero; cityscape with flashing lights; cinematic
Characteristic
Shot : A man dressed as Superman stands on a rooftop overlooking a city at night. The city lights are blurred in the background, creating a sense of depth and distance.
Aesthetic Score : 0.7
Mood : heroic, dramatic, powerful
Quality
Entropy : 6.88
Noise : 77
Prompt Clip Score : 0.26
AI Evaluation
Likelihood of AI : 0.10
Image errors : There are some slight artifacts in the image, such as around the edges of Superman’s costume.
The Weight of Work: A Man Crumbles Under a Mountain of Paperwork
A stark image of a man in a suit, hands on his head, surrounded by a towering pile of paperwork. The scene captures the overwhelming feeling of stress and frustration that comes with being buried under deadlines and responsibilities.
Prompt
facial-expressions Anxiety: Overwhelmed, stressed ; A person sitting at a desk, surrounded by paperwork; close-up; Normal Person; cluttered office; cinematic
Characteristic
Shot : A man in a suit is sitting at a desk, surrounded by a large amount of paperwork. He looks stressed and overwhelmed.
Aesthetic Score : 0.4
Mood : stressed, overwhelmed, frustrated
Quality
Entropy : 6.55
Noise : 80
Prompt Clip Score : 0.27
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image has some minor artifacts, such as noise and grain. The lighting is also a bit uneven, creating harsh shadows.
Lost in the Game: A Gamer’s Intense Focus Under Neon Lights
A young man, bathed in the glow of blue and red lights, sits transfixed at his computer, headphones on, his expression a testament to the intensity of his gaming session. The dramatic lighting and his focused gaze capture the essence of a gamer fully immersed in their virtual world.
Prompt
facial-expressions Anxiety: Focused, intense ; A gamer hunched over a computer screen; close-up; Gamer; dimly lit room with flashing lights; cinematic
Characteristic
Shot : A young man is intently focused on a computer screen, wearing headphones and illuminated by colorful neon lights. The scene is set in a dimly lit room, suggesting a gaming setup or a late-night work session.
Aesthetic Score : 0.7
Mood : intense, focused, technological
Quality
Entropy : 6.26
Noise : 66
Prompt Clip Score : 0.27
AI Evaluation
Likelihood of AI : 0.20
Image errors : No major errors, but the image could benefit from slightly better color balance.
Lost in the City: A Moment of Mystery
A woman walks through a bustling urban landscape, her gaze locked on the camera. The shallow depth of field blurs the city around her, drawing you into her enigmatic world. A sense of contemplation and mystery hangs in the air, inviting you to wonder about her story.
Prompt
facial-expressions Anxiety: Anxious, uncomfortable ; A woman walking down a crowded street; eye-level; Single Person; blurred background of people; cinematic
Characteristic
Shot : A woman is walking through a busy city street. She is looking directly at the camera with a serious expression. The background is blurred, creating a sense of depth and anonymity.
Aesthetic Score : 0.7
Mood : mysterious, contemplative, urban
Quality
Entropy : 6.68
Noise : 74
Prompt Clip Score : 0.26
AI Evaluation
Likelihood of AI : 0.10
Image errors : No noticeable errors.
Intense Gaze: A Portrait of Mystery
A close-up portrait captures a bearded man’s intense gaze, his expression shrouded in mystery. The dimly lit setting and blurred background heighten the dramatic effect, leaving the viewer questioning what lies ahead.
Prompt
facial-expressions Anxiety: Fear, anticipation ; A hero facing a menacing villain; medium shot; Hero; dark and ominous setting; cinematic
Characteristic
Shot : A close-up of a man’s face, looking off-camera. The scene is dark, and the man appears to be in a state of tension.
Aesthetic Score : 0.7
Mood : intense, serious, dramatic
Quality
Entropy : 6.22
Noise : 84
Prompt Clip Score : 0.20
AI Evaluation
Likelihood of AI : 0.40
Image errors : The image appears to be slightly over-sharpened, resulting in a slightly artificial look, particularly around the hair. There are also some slight artifacts around the edges of the subject’s face.
Silhouettes of Anticipation: Waiting in the Airport
A quiet scene of people waiting in an airport terminal, their silhouettes framed against a large window overlooking the city. The mood is one of anticipation, tinged with a sense of anonymity and mystery, as the dramatic use of silhouettes emphasizes the waiting aspect.
Prompt
facial-expressions Anxiety: Impatient, restless ; A person waiting in a long line; eye-level; Normal Person; crowded waiting room; cinematic
Characteristic
Shot : A group of people sitting on a bench in an airport waiting area, facing a large window, with their backs to the camera.
Aesthetic Score : 0.4
Mood : waiting, anticipation, travel
Quality
Entropy : 6.74
Noise : 83
Prompt Clip Score : 0.19
AI Evaluation
Likelihood of AI : 0.10
Image errors : The image appears to be slightly underexposed, resulting in a muted color palette and darker shadows.
Immersed in the Game: A Young Man’s Focused Intensity
A young man, bathed in vibrant pink and blue lighting, sits captivated at his computer, his hands flying across the keyboard. His concentrated expression and the presence of a microphone reveal his deep immersion in the game, creating a scene of intense focus and energetic engagement.
Prompt
facial-expressions Anxiety: Adrenaline, pressure ; A gamer’s hands frantically moving across a keyboard; close-up; Gamer; glowing computer screen; cinematic
Characteristic
Shot : A young man in a dark room, wearing a headset, is intensely focused on a video game. The room is lit with neon blue and pink lighting, creating a dramatic and vibrant atmosphere. The gamer’s hands are positioned over a keyboard, and his facial expression is one of intense concentration.
Aesthetic Score : 0.6
Mood : intense, focused, energized
Quality
Entropy : 6.74
Noise : 75
Prompt Clip Score : 0.24
AI Evaluation
Likelihood of AI : 0.30
Image errors : The image appears to have some slight blurriness, particularly around the edges, suggesting possible over-sharpening or post-processing artifacts.
A Solitary Figure Awaits the Storm
A lone man stands amidst a field of tall grass, his gaze fixed on a stormy sky. The ominous clouds suggest an impending downpour, creating a sense of solitude, contemplation, and foreboding. The dramatic contrast between the lone figure and the stormy sky evokes a feeling of isolation and anticipation.
Prompt
facial-expressions Anxiety: Loneliness, despair ; A man standing alone in a vast field; wide shot; Single Person; open sky with dark clouds; cinematic
Characteristic
Shot : A lone figure stands in a field of tall grass, looking towards a stormy sky. The sky is dark and ominous, with heavy clouds looming overhead. There is a sense of foreboding and isolation in the image.
Aesthetic Score : 0.7
Mood : dramatic, contemplative, ominous
Quality
Entropy : 6.83
Noise : 89
Prompt Clip Score : 0.25
AI Evaluation
Likelihood of AI : 0.20
Image errors : No visible artifacts or errors.
Solitude Amidst the Ashes
A lone figure stands on a rooftop, silhouetted against a sky choked with smoke and fire. The city below lies in ruins, a stark testament to the destructive power of the flames. This dramatic image captures the somber mood of an apocalyptic world, leaving the viewer to ponder the man’s fate and the future of the city.
Prompt
facial-expressions Anxiety: Guilt, responsibility ; A hero looking out over a devastated city; high angle; Hero; destroyed buildings and smoke; cinematic
Characteristic
Shot : A man stands on a rooftop overlooking a city engulfed in fire and smoke. The buildings are destroyed and there is debris everywhere. The man is wearing a green jacket and jeans and is looking out at the scene. The sky is overcast and the air is thick with smoke.
Aesthetic Score : 0.6
Mood : dramatic, somber, apocalyptic
Quality
Entropy : 6.85
Noise : 90
Prompt Clip Score : 0.26
AI Evaluation
Likelihood of AI : 0.70
Image errors : The smoke and flames in the image look a bit artificial and overly dramatic.
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 0.51, 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 0.18, which is considered very good. This means that the generated image closely matched the expected aesthetic described in the prompt.
Overall, the model seems to be better at understanding the aesthetic and shot composition of the prompt than the 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