AI's Facial Expressions: A Mixed Bag of Emotions with Flux-pro
- 9 minutes read - 1863 wordsTable of Contents
Facial expressions are a powerful tool for conveying emotions in storytelling and art. They can add depth and realism to characters, making them more relatable and engaging. But how well can AI capture these nuances? This blog post explores the capabilities of a generative AI model in creating images with specific facial expressions, analyzing its performance in terms of camera position, shot analysis, and aesthetic appeal. We’ll delve into examples where the model excels and where it falls short, providing insights into the current state of AI’s emotional intelligence.
Created with: flux-pro
Silhouetted in the Night: A Lonely Figure on a Deserted Street
A solitary figure stands bathed in the glow of streetlights, their silhouette stark against the darkness of a wet, deserted street. The scene evokes a sense of isolation, mystery, and melancholic longing, with the dramatic contrast between light and shadow adding to the intrigue.
Prompt
facial-expressions Guilt: Desolate, regretful ; A lone figure; eye-level; Single Person; Empty street at night, rain falling; cinematic
Characteristic
Shot : A lone figure stands silhouetted against a blurry background of a rainy city street at night.
Aesthetic Score : 0.6
Mood : melancholy, lonely, atmospheric
Quality
Entropy : 6.56
Noise : 79
Prompt Clip Score : 0.25
AI Evaluation
Likelihood of AI : 0.30
Image errors : The image appears slightly blurry, particularly in the background.
Superman at Sunset: A Symbol of Hope
A powerful image captures Superman standing tall against a breathtaking sunset, his cape billowing in the wind. The scene evokes a sense of heroism, determination, and hope, as the setting sun casts a dramatic glow, making the image feel epic and inspiring.
Prompt
facial-expressions Guilt: Heavy, burdened, conflicted ; A superhero, cape billowing in the wind; medium shot; Hero; City skyline, destroyed buildings in the background; cinematic
Characteristic
Shot : A superhero, Superman, stands in front of a tall building with a cloudy sunset in the background. He is wearing the iconic red and blue suit, with the yellow ‘S’ shield prominently displayed.
Aesthetic Score : 0.7
Mood : powerful, heroic, determined
Quality
Entropy : 6.72
Noise : 94
Prompt Clip Score : 0.27
AI Evaluation
Likelihood of AI : 0.50
Image errors : There are no noticeable artifacts or errors in the image.
A Moment of Reflection: A Daughter’s Pensive Gaze
A young woman contemplates a framed photograph of an older woman, her expression mirroring the melancholic mood of the image. The soft, warm lighting enhances the intimate and thoughtful atmosphere, creating a sense of depth and connection between the two figures.
Prompt
facial-expressions Guilt: Nostalgic, melancholic ; A woman holding a photo of a loved one; close-up; Normal Person; A cluttered kitchen, dishes piled in the sink; cinematic
Characteristic
Shot : A young woman is looking at a framed picture of an older woman. The picture is being held in the young woman’s hands.
Aesthetic Score : 0.6
Mood : pensive, melancholic, thoughtful
Quality
Entropy : 6.84
Noise : 80
Prompt Clip Score : 0.29
AI Evaluation
Likelihood of AI : 0.10
Image errors : The image is slightly blurry.
Lost in the Code: A Moment of Intense Focus
A young man sits hunched over his keyboard, bathed in the red glow of his computer screen. The dim lighting and his focused expression create a sense of intensity and mystery, hinting at a world of code and digital exploration.
Prompt
facial-expressions Guilt: Isolated, self-loathing ; A gamer, hunched over a computer screen; close-up; Gamer; Neon lights reflecting in their eyes, empty pizza boxes scattered around; cinematic
Characteristic
Shot : A young person is sitting at a desk in a dimly lit room, using a computer. The room is lit by red and blue lights. There is a large monitor in front of them with a blue-toned screen.
Aesthetic Score : 0.6
Mood : intense, focused, moody
Quality
Entropy : 6.53
Noise : 73
Prompt Clip Score : 0.25
AI Evaluation
Likelihood of AI : 0.10
Image errors : The image has some noise and grain, but it is not overly distracting.
Lost in the Crowd, Found in a Moment
A young man with long hair stands amidst a bustling crowd, his gaze fixed directly on the viewer. The image, cropped to focus on his upper body and head, creates a sense of mystery and intrigue. A lone red balloon floats behind him, adding a touch of whimsy to the scene. The lighting and composition draw the viewer’s attention to his thoughtful expression, leaving them to ponder his story.
Prompt
facial-expressions Guilt: Alienated, invisible ; A man standing in a crowded room, looking lost; wide shot; Single Person; A party, people laughing and dancing, oblivious to him; cinematic
Characteristic
Shot : A man with long hair and a beard is standing in the middle of a crowd, looking at the camera. The scene is lit with warm light, and there are some people in the background.
Aesthetic Score : 0.6
Mood : intrigued, mysterious, pensive
Quality
Entropy : 6.39
Noise : 57
Prompt Clip Score : 0.22
AI Evaluation
Likelihood of AI : 0.20
Image errors : No visible errors. The image is slightly grainy, but this is likely due to the lighting.
A Shadow Falls on a Dusty Battlefield
A lone figure in a long robe stands over a fallen comrade in a desolate, fire-ravaged landscape. The smoke and dust create a somber atmosphere, highlighting the dramatic tension and suspense of the scene.
Prompt
facial-expressions Guilt: Torn, conflicted, remorseful ; A hero, standing over a fallen villain; medium shot; Hero; A battlefield, smoke and debris everywhere; cinematic
Characteristic
Shot : A man stands over a fallen man in a battle field. The man is in the middle of the frame and the fallen man is in the bottom of the frame. The scene is dark and has smoke in the background.
Aesthetic Score : 0.6
Mood : dark, dramatic, intense
Quality
Entropy : 6.39
Noise : 66
Prompt Clip Score : 0.20
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image has some noise and artifacts. The man’s face is a bit blurry.
Intimate Gathering Under Dim Lights
A group of four individuals share a quiet moment around a dinner table, bathed in soft, mysterious lighting. The close-up composition captures the intimacy and contemplation of the scene, hinting at a melancholic undercurrent.
Prompt
facial-expressions Guilt: Awkward, strained, unspoken ; A family gathered around a table, but the atmosphere is tense; medium shot; Normal People; A dimly lit dining room, empty chairs at the table; cinematic
Characteristic
Shot : Four people are gathered around a table, seemingly at a dinner party, or in a dining room setting. The lighting is soft and warm, with a focus on the characters’ faces. It is a quiet, intimate scene, emphasizing conversation and connection over food.
Aesthetic Score : 0.6
Mood : intimate, somber, thoughtful
Quality
Entropy : 6.38
Noise : 68
Prompt Clip Score : 0.28
AI Evaluation
Likelihood of AI : 0.10
Image errors : There are no significant image errors visible. The lighting and focus are good, and the image is sharp.
Lost in the Game: A Moment of Quiet Reflection
A young man finds solace in the glow of the television screen, surrounded by empty soda cans. His relaxed posture and the soft lighting suggest a moment of quiet contemplation, a break from the hustle and bustle of everyday life.
Prompt
facial-expressions Guilt: Disillusioned, defeated, empty ; A gamer, staring at a blank screen, controller in hand; close-up; Gamer; A dimly lit room, empty energy drink cans scattered around; cinematic
Characteristic
Shot : A person is sitting in front of a TV, playing video games. There are a few cans of soda on the floor in front of the person.
Aesthetic Score : 0.4
Mood : relaxed, casual, solitary
Quality
Entropy : 6.25
Noise : 51
Prompt Clip Score : 0.28
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image is slightly blurry and has some noise. There are also some artifacts in the shadows.
A Moment of Contemplation in the City
A woman, dressed in a suit jacket and jeans, walks down a bustling city street, her briefcase in hand. The blurred background and soft light create a sense of mystery and intrigue, hinting at a story waiting to unfold. The scene evokes a calm, urban, and contemplative mood.
Prompt
facial-expressions Guilt: Lonely, isolated, rejected ; A woman walking away from a group of friends; long shot; Single Person; A bustling city street, people rushing by; cinematic
Characteristic
Shot : A woman walks down a city street, carrying a suitcase, with other people walking in the background. The city is illuminated by the soft light of the setting sun.
Aesthetic Score : 0.6
Mood : tranquil, urban, serene
Quality
Entropy : 6.76
Noise : 67
Prompt Clip Score : 0.20
AI Evaluation
Likelihood of AI : 0.10
Image errors : There is some noise in the image, particularly in the shadows.
Silhouetted Against the City’s Embrace
A solitary figure stands in stark contrast against the moonlit cityscape, evoking a sense of melancholy and contemplation. The dramatic silhouette creates an air of mystery, while the grandeur of the city lights adds a touch of scale and wonder to the scene.
Prompt
facial-expressions Guilt: Reflective, contemplative, seeking redemption ; A hero, standing on a rooftop, looking out at the city; wide shot; Hero; A cityscape bathed in moonlight, a sense of peace; cinematic
Characteristic
Shot : A lone figure stands on a rooftop overlooking a cityscape at night. The moon is visible in the sky.
Aesthetic Score : 0.7
Mood : melancholy, contemplative, urban
Quality
Entropy : 6.63
Noise : 63
Prompt Clip Score : 0.21
AI Evaluation
Likelihood of AI : 0.80
Image errors : The image has a slight graininess, and the cityscape appears slightly blurry. There is some aliasing around the edges of the figure.
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 0.45, which is slightly below the “good” range of 0.5 to 0.75. This suggests that the model’s ability to accurately interpret and reproduce camera positions in the prompt is decent, but could be improved.
- Shot Analysis: The model scored 0.62, falling within the “good” range. This indicates that the model is generally able to understand the scene described in the prompt and create a shot that reflects it.
- Aesthetic Analysis: The model scored 0.20, which is significantly below the “very good” range of -0.2 to 0.1. This suggests that the generated image’s aesthetic deviated considerably from the expected aesthetic based on the prompt.
Overall, the model demonstrates a good understanding of camera positions and shot composition, but needs improvement in capturing the desired 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-pro/api