AI's Facial Expressions: A Mixed Bag of Success with Flux-schnell
- 9 minutes read - 1765 wordsTable of Contents
The ability to generate realistic facial expressions is a crucial aspect of creating compelling and engaging AI-generated content. This blog post examines the results of a recent experiment where a generative AI model was tasked with creating images featuring specific facial expressions and scenes. The results reveal a mixed bag of success, highlighting the model’s strengths and weaknesses in capturing the nuances of human emotion. We’ll explore the model’s performance in terms of camera position, scene analysis, and aesthetic, providing insights into the challenges and opportunities in the field of AI-generated facial expressions.
Created with: flux-schnell
Lost in Thought: A Moment of Contemplation in the City
A solitary figure sits on a park bench, his gaze fixed on the bustling cityscape. His posture and expression convey a sense of pensive melancholy, as if lost in deep thought. The scene evokes a feeling of reflection and loneliness, capturing the quiet moments of introspection amidst the urban chaos.
Prompt
facial-expressions Thoughtfulness: Melancholy, contemplative ; A lone figure sitting on a park bench; eye-level; Single Person; a bustling city park in the background; cinematic
Characteristic
Shot : A young man is sitting on a bench in a city park. The image is taken from a slightly elevated perspective, and the subject is in focus. The background is blurry, and there are trees and buildings in the background.
Aesthetic Score : 0.6
Mood : melancholy, contemplative, lonely
Quality
Entropy : 6.89
Noise : 96
Prompt Clip Score : 0.27
AI Evaluation
Likelihood of AI : 0.20
Image errors : No visible errors
Silhouetted Hero, City Lights, and a Hopeful Future
A lone figure in a superhero costume stands against the backdrop of a glittering cityscape, their silhouette casting a mysterious and powerful presence. The scene evokes a sense of hope and contemplation, leaving viewers to wonder about the hero’s mission and the future that lies ahead.
Prompt
facial-expressions Thoughtfulness: Reflective, introspective ; A superhero standing on a rooftop, looking out at the city; eye-level; Hero; a sprawling cityscape with twinkling lights; cinematic
Characteristic
Shot : A man in a superhero costume stands in a city skyline, looking out at the cityscape.
Aesthetic Score : 0.6
Mood : heroic, contemplative, futuristic
Quality
Entropy : 6.72
Noise : 78
Prompt Clip Score : 0.28
AI Evaluation
Likelihood of AI : 0.70
Image errors : No significant errors
Lost in the Pages, Found in the Moment
A young woman finds solace in a book as the train glides through a tranquil landscape. The intimate framing draws you into her peaceful world, capturing a moment of calm contemplation.
Prompt
facial-expressions Thoughtfulness: Peaceful, absorbed ; A woman reading a book on a train; eye-level; Normal Person; a blurry view of passing scenery outside the window; cinematic
Characteristic
Shot : A young woman is reading a book on a train, looking down at the book
Aesthetic Score : 0.6
Mood : pensive, quiet, contemplative
Quality
Entropy : 6.54
Noise : 67
Prompt Clip Score : 0.31
AI Evaluation
Likelihood of AI : 0.20
Image errors : There are no visible artifacts or errors in the image.
Lost in the Digital World: A Moment of Focus and Intrigue
A young man sits bathed in the blue glow of his computer screen, his expression focused and contemplative. The dramatic lighting creates a sense of mystery, drawing the viewer into his digital world.
Prompt
facial-expressions Thoughtfulness: Intense, focused ; A gamer sitting in a dimly lit room, staring intently at a computer screen; eye-level; Gamer; a cluttered desk with gaming peripherals; cinematic
Characteristic
Shot : A young man sits at a desk in front of a computer, his face illuminated by the screen, in a dimly lit room.
Aesthetic Score : 0.6
Mood : focused, contemplative, serious
Quality
Entropy : 5.90
Noise : 52
Prompt Clip Score : 0.25
AI Evaluation
Likelihood of AI : 0.10
Image errors : The image is slightly blurry, particularly in the background. Some noise is visible, especially in the darker areas.
Solitude by the Sea: A Moment of Tranquility
A lone figure strolls along a sandy beach, the vast ocean stretching out behind them. The cloudy sky adds a sense of contemplation, while the overall mood is one of peaceful solitude. The image evokes a feeling of isolation and introspection, highlighting the beauty and power of being alone with one’s thoughts.
Prompt
facial-expressions Thoughtfulness: Solitary, introspective ; A man walking alone on a deserted beach; eye-level; Single Person; the vast ocean stretching out before him; cinematic
Characteristic
Shot : A lone figure walks along a beach with a vast grey sky overhead.
Aesthetic Score : 0.6
Mood : lonely, contemplative, somber
Quality
Entropy : 5.54
Noise : 36
Prompt Clip Score : 0.26
AI Evaluation
Likelihood of AI : 0.10
Image errors : The image is slightly overexposed, leading to a washed-out look.
Firefighter Bravely Faces Blazing Inferno
A dramatic image captures a firefighter in full gear standing defiantly against a backdrop of raging flames and billowing smoke. The scene evokes a sense of danger, heroism, and somber reflection.
Prompt
facial-expressions Thoughtfulness: Somber, reflective ; A firefighter standing amidst the ruins of a fire; eye-level; Hero; smoke and debris filling the air; cinematic
Characteristic
Shot : A fireman in full gear, standing in front of a burning building, with smoke in the background.
Aesthetic Score : 0.7
Mood : serious, dramatic, heroic
Quality
Entropy : 6.65
Noise : 83
Prompt Clip Score : 0.35
AI Evaluation
Likelihood of AI : 0.20
Image errors : No major errors, some noise and slight blur due to the low light conditions.
Intimate Moments: A Conversation Under Dim Lights
Four figures gather around a table in a dimly lit kitchen, their faces illuminated by the soft glow of the room. The composition draws the viewer into the heart of their conversation, creating a sense of intimacy and shared secrets. The subdued lighting and focus on their expressions hint at a story waiting to unfold.
Prompt
facial-expressions Thoughtfulness: Intimate, connected ; A family gathered around a dinner table; eye-level; Normal People; a warm, inviting kitchen setting; cinematic
Characteristic
Shot : Three people are sitting around a kitchen table, eating and talking. The kitchen has a warm, inviting feel, with wooden cabinets and warm lighting.
Aesthetic Score : 0.6
Mood : casual, intimate, friendly
Quality
Entropy : 6.86
Noise : 87
Prompt Clip Score : 0.30
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image has some noise and artifacts, particularly in the shadows.
Lost in the Game: A Moment of Focused Intensity
A young gamer, bathed in the soft glow of their monitor, is completely absorbed in their game. The dimly lit room adds an air of mystery, drawing attention to their focused expression and the intensity of their play.
Prompt
facial-expressions Thoughtfulness: Excited, immersed ; A gamer holding a controller, eyes glued to the screen; close-up; Gamer; a vibrant, colorful gaming world displayed on the monitor; cinematic
Characteristic
Shot : A young person is playing video games at home. They are holding a controller in their hand and are focused on the screen. The room is dimly lit and there is a lot of colorful light coming from the screens.
Aesthetic Score : 0.6
Mood : focused, intense, playful
Quality
Entropy : 6.62
Noise : 57
Prompt Clip Score : 0.26
AI Evaluation
Likelihood of AI : 0.30
Image errors : The image has some minor artifacts, such as noise and blurriness, particularly in the background.
Finding Peace in the Park
A young woman finds solace in the quiet beauty of a park, her pen gliding across the pages of her notebook. The soft light and blurred background create a sense of calm and contemplation, capturing a moment of quiet reflection.
Prompt
facial-expressions Thoughtfulness: Peaceful, creative ; A woman sitting on a park bench, sketching in a notebook; eye-level; Single Person; a serene park setting with blooming flowers; cinematic
Characteristic
Shot : A young woman is sitting on a bench in a park, writing in a notebook.
Aesthetic Score : 0.7
Mood : calm, contemplative, thoughtful
Quality
Entropy : 6.90
Noise : 98
Prompt Clip Score : 0.31
AI Evaluation
Likelihood of AI : 0.20
Image errors : No notable errors.
Facing the Storm: A Man’s Hopeful Gaze
A solitary figure, cloaked in vibrant red and yellow, stands against a backdrop of brooding clouds. His gaze, directed upwards, speaks of a pensive spirit, a flicker of hope amidst the uncertainty. The dramatic composition hints at a challenging journey ahead, leaving the viewer to ponder the man’s destiny.
Prompt
facial-expressions Thoughtfulness: Determined, resolute ; A superhero looking up at the sky, a determined expression on their face; eye-level; Hero; a dramatic sky with dark clouds gathering; cinematic
Characteristic
Shot : A man is looking up towards the sky, his face partially obscured by a red and yellow costume. The background is a hazy blue sky with clouds.
Aesthetic Score : 0.7
Mood : hopeful, determined, melancholic
Quality
Entropy : 6.09
Noise : 50
Prompt Clip Score : 0.27
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image is slightly over-processed, and the colors are a bit too saturated.
Conclusion
The results show that the generative AI model performed well in understanding the camera position and scene, but struggled with the aesthetic aspect. Here’s a breakdown:
- Camera Position: The model scored 0.1, indicating it did not perform well in capturing the intended camera position. A score between 0.5 and 0.75 would be considered good, and above 0.75 very good.
- Shot Analysis: The model scored 0.44, which is slightly below average. A score between 0.5 and 0.75 would be considered good, and above 0.75 very good. This suggests the model had some difficulty understanding the scene described in the prompt.
- Aesthetic Analysis: The model scored 0.12, which is very good. A score between -0.2 and 0.1 indicates a close match between the expected and actual aesthetic of the image. This suggests the model was able to create an image that visually aligned with the desired aesthetic.
Overall, the model demonstrated a strong ability to capture the desired aesthetic but struggled with accurately representing the camera position and scene.
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