AI's Facial Expressions: A Mixed Bag with Flux-schnell
- 8 minutes read - 1667 wordsTable of Contents
Facial expressions are a powerful tool in storytelling, conveying emotions and intentions without words. Generative AI is increasingly being used to create images with specific facial expressions, but how well does it capture the nuances of human emotion? This blog post explores the capabilities of generative AI in this area, analyzing its performance in terms of camera position, shot composition, and aesthetic. We’ll examine examples of AI-generated images and discuss the challenges and opportunities that lie ahead in this exciting field.
Created with: flux-schnell
Lost in Thought: A Man’s Melancholy Moment in the Park
A solitary figure sits on a bench amidst a sea of fallen leaves, the overcast sky mirroring his somber mood. The scene evokes a sense of isolation and contemplation, capturing the essence of melancholy.
Prompt
facial-expressions Sadness: Melancholy, loneliness ; A lone figure; eye-level; Single Person; Empty park bench with fallen leaves; cinematic
Characteristic
Shot : A man sits alone on a bench in a park, with fallen leaves scattered around him. The trees are bare, and the sky is overcast, giving a sense of melancholy.
Aesthetic Score : 0.6
Mood : melancholy, contemplative, somber
Quality
Entropy : 6.86
Noise : 117
Prompt Clip Score : 0.23
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image has a slightly grainy texture, especially in the background.
The Man of Steel Faces the Storm
A brooding Superman stands amidst a rain-soaked cityscape, the dark lighting and stormy atmosphere adding to the scene’s dramatic tension. The image evokes a sense of mystery and danger, hinting at the challenges the hero may face.
Prompt
facial-expressions Sadness: Despair, disillusionment ; A superhero in their costume; eye-level; Hero; City skyline at night, rain falling; cinematic
Characteristic
Shot : A man dressed as Superman stands in front of a city skyline, with rain falling around him.
Aesthetic Score : 0.7
Mood : dark, intense, dramatic
Quality
Entropy : 6.56
Noise : 76
Prompt Clip Score : 0.25
AI Evaluation
Likelihood of AI : 0.70
Image errors : The rain and city background look slightly artificial and lack depth. The edges of the Superman suit have some aliasing.
A Moment of Quiet Melancholy
A woman sits alone in a dimly lit kitchen, her posture and expression conveying a sense of sadness and contemplation. The composition emphasizes her isolation, creating a poignant image of quiet reflection.
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 sits at a kitchen table, looking down. There are two mugs and a bowl on the table in front of her.
Aesthetic Score : 0.5
Mood : sad, contemplative, quiet
Quality
Entropy : 6.33
Noise : 68
Prompt Clip Score : 0.27
AI Evaluation
Likelihood of AI : 0.10
Image errors : There are some slight artifacts in the image, particularly around the edges of the subject’s hair. The color is slightly muted.
Focused on the Task at Hand
A young man, headphones on, eyes glued to the computer screen. Pizza and soda fuel his intense concentration, capturing the essence of a focused, casual work session.
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, wearing headphones, is sitting in front of a computer screen, looking intently at it. There is a box of pizza and some drinks in the foreground, suggesting a late-night gaming session.
Aesthetic Score : 0.5
Mood : focused, intense, contemplative
Quality
Entropy : 6.43
Noise : 76
Prompt Clip Score : 0.25
AI Evaluation
Likelihood of AI : 0.20
Image errors : There is some noise in the image, particularly in the darker areas. The colors are a bit muted.
Lost in the Shadows: A Boy’s Lonely Journey
A young boy stands alone in a dimly lit hallway, his expression filled with melancholy. The atmosphere is heavy with suspense and mystery, leaving the viewer wondering what secrets lie hidden in the shadows.
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 stands in a dimly lit hallway, looking directly at the camera. The walls are a dark teal color, and the only light source appears to be coming from the hallway behind the boy.
Aesthetic Score : 0.6
Mood : melancholy, lonely, somber
Quality
Entropy : 5.69
Noise : 38
Prompt Clip Score : 0.21
AI Evaluation
Likelihood of AI : 0.20
Image errors : There is a slight amount of noise in the image, which is most apparent in the shadows. There is a slight vignette effect on the image.
A Soldier’s Solitude Amidst the Fury of War
A lone soldier stands amidst a ravaged landscape, his gaze fixed on the ground as explosions paint the horizon. The image captures the dramatic weight of war, highlighting the isolation and somber mood of a single figure facing overwhelming chaos.
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 lone soldier stands amidst a battlefield, with a large explosion in the background, while the sky is overcast and filled with falling debris.
Aesthetic Score : 0.6
Mood : dramatic, somber, melancholic
Quality
Entropy : 6.07
Noise : 72
Prompt Clip Score : 0.29
AI Evaluation
Likelihood of AI : 0.20
Image errors : There are some slight artifacts in the image, particularly in the areas of the explosions and the soldier’s clothing. The overall sharpness and clarity could be improved as well.
Cozy Night In: Couple Relaxing on the Couch
A couple enjoys a quiet evening together, snuggled on the couch with a bowl of popcorn. The soft lighting creates a warm and intimate atmosphere, perfect for a relaxing night in.
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 sitting on a couch with a bowl of popcorn in the foreground. The lighting is dim and the focus is on the couple’s faces.
Aesthetic Score : 0.4
Mood : relaxed, intimate, cozy
Quality
Entropy : 6.78
Noise : 78
Prompt Clip Score : 0.29
AI Evaluation
Likelihood of AI : 0.10
Image errors : The image has some noise and blurriness, which is most noticeable in the background.
Lost in the Code: A Moment of Focused Intensity
A young person, bathed in the soft glow of a computer screen, is deeply engrossed in their work. The dimly lit room and headphones create an atmosphere of focused concentration, hinting at a world of digital possibilities.
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 young man is sitting at a computer in a dimly lit room, focused on his work. He is wearing headphones and a watch.
Aesthetic Score : 0.6
Mood : focused, concentrated, serious
Quality
Entropy : 6.70
Noise : 65
Prompt Clip Score : 0.19
AI Evaluation
Likelihood of AI : 0.10
Image errors : No noticeable image artifacts or errors.
Lost in the City: A Moment of Melancholy
A young woman navigates the bustling city streets, her face etched with concern. The blurred background emphasizes her isolation and introspective mood, creating a poignant image of urban solitude.
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 young woman with long brown hair walks through a city street, looking concerned. She is the central subject of the photo and stands out from the background.
Aesthetic Score : 0.7
Mood : pensive, urban, somber
Quality
Entropy : 6.83
Noise : 82
Prompt Clip Score : 0.23
AI Evaluation
Likelihood of AI : 0.10
Image errors : No noticeable errors.
Lost in the City Lights
A young man stands alone, silhouetted against a vibrant cityscape. The soft lighting and shallow depth of field create a sense of isolation and contemplation, leaving the viewer to wonder about his thoughts and the story behind his gaze.
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 young man in a dark jacket is standing in front of a blurred out cityscape, most likely at night, he looks slightly melancholy.
Aesthetic Score : 0.7
Mood : melancholy, contemplative, urban
Quality
Entropy : 6.59
Noise : 50
Prompt Clip Score : 0.24
AI Evaluation
Likelihood of AI : 0.30
Image errors : There are no notable artifacts or errors in the image.
Conclusion
The results show 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 0.25, 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 0.515, 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 0.17, which is considered okay. This means that the generated image’s aesthetic was somewhat different from the expected aesthetic described in the prompt.
Overall, the model seems to be better at understanding the scene and shot composition than it is at capturing the intended camera position and aesthetic.
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://fal.ai/models/fal-ai/flux/schnell/api