AI's Facial Expressions: A Mixed Bag with Freepik
- 9 minutes read - 1780 wordsTable of Contents
Facial expressions are a powerful tool in storytelling, conveying emotions and intentions without words. In the realm of generative AI, the ability to create images with nuanced facial expressions is a crucial step towards realistic and engaging content. This blog post delves into the performance of a generative AI model in capturing facial expressions, analyzing its strengths and weaknesses in understanding scene context, camera position, and aesthetic style.
Created with: freepik
Lost in Thought: A Moment of Melancholy in the Rain
A young woman finds solace in a quiet cafe, her gaze lost in the falling rain. The scene evokes a sense of wistful contemplation, as she sits alone, her chin resting on her hands, a cup of coffee untouched before her. The rain outside the window amplifies the feeling of loneliness and isolation, mirroring the woman’s introspective mood.
Prompt
facial-expressions Worry: melancholy, lonely ; Single woman; eye-level; Single Persons; dimly lit coffee shop with rain outside; cinematic
Characteristic
Shot : A young woman sits alone at a table in a cafe, looking wistfully out the window at the rain. A cup of coffee sits on the table in front of her.
Aesthetic Score : 0.8
Mood : melancholy, contemplative, cozy
Quality
Entropy : 6.78
Noise : 62
Prompt Clip Score : 0.27
AI Evaluation
Likelihood of AI : 0.20
Image errors : No visible artifacts or errors
Heroic Silhouette Against the City Lights
A powerful superhero stands tall against the backdrop of a vibrant city skyline at night. The dramatic lighting and pose evoke a sense of heroism and strength, capturing the essence of a true champion.
Prompt
facial-expressions Worry: intense, burdened ; Man in a superhero costume; medium shot; Heroes; cityscape at night with flashing sirens; cinematic
Characteristic
Shot : A man dressed as Superman stands in front of a cityscape at night. The city lights are blurred in the background, creating a sense of depth.
Aesthetic Score : 0.7
Mood : dramatic, heroic, powerful
Quality
Entropy : 6.64
Noise : 51
Prompt Clip Score : 0.24
AI Evaluation
Likelihood of AI : 0.50
Image errors : The image has some noise and artifacts, particularly in the background and the subject’s costume.
Lost in the Crowd: A Moment of Anxiety on the Subway
A young woman’s worried gaze pierces through the blur of a crowded subway car, creating a palpable sense of tension and anticipation. The close-up shot and the blurred background amplify the feeling of claustrophobia and isolation, leaving the viewer wondering what she is facing.
Prompt
facial-expressions Worry: anxious, overwhelmed ; Young woman in a crowded subway; eye-level; Normal People; blurred faces of commuters; cinematic
Characteristic
Shot : A young woman is standing in a crowded subway car, looking directly at the camera with a worried expression. There are other people in the background, but they are out of focus.
Aesthetic Score : 0.6
Mood : tense, anxious, apprehensive
Quality
Entropy : 6.87
Noise : 67
Prompt Clip Score : 0.31
AI Evaluation
Likelihood of AI : 0.10
Image errors : No obvious errors
Lost in the Music: A Young Producer’s Focused Intensity
A young man, headphones on and fingers flying across a MIDI controller, is captured in a moment of intense creative focus. The dimly lit room, possibly a home studio, adds to the intimate atmosphere, drawing the viewer into the artist’s world.
Prompt
facial-expressions Worry: intense, focused ; Gamer with headphones on; close-up; Gamer; dimly lit room with glowing computer screen; cinematic
Characteristic
Shot : A young man wearing headphones is focused on a computer screen in a dimly lit room. There are other computer monitors in the background, and a keyboard is visible in the foreground.
Aesthetic Score : 0.6
Mood : focused, intense, technological
Quality
Entropy : 6.42
Noise : 48
Prompt Clip Score : 0.29
AI Evaluation
Likelihood of AI : 0.30
Image errors : There are no noticeable artifacts or errors in the image.
Autumn Melancholy: A Moment of Contemplation
A young man sits alone on a park bench, bathed in the golden hues of autumn. His posture and gaze suggest a quiet introspection, capturing a moment of melancholy and contemplation amidst the changing season.
Prompt
facial-expressions Worry: sad, reflective ; Man sitting alone on a park bench; long shot; Single Persons; empty park with falling leaves; cinematic
Characteristic
Shot : A young man is sitting on a bench in a park, with fallen leaves around him. The background is blurry and shows trees with golden leaves.
Aesthetic Score : 0.7
Mood : melancholy, contemplative, autumnal
Quality
Entropy : 6.82
Noise : 65
Prompt Clip Score : 0.33
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image is slightly blurry in the background, and the colors are a bit muted. There is some noise in the image.
A Solitary Figure Amidst the Flames
A young woman stands defiant on a rooftop, her calm gaze fixed on a burning city. The fiery chaos behind her creates a stark contrast, leaving the viewer with a sense of suspense and impending doom.
Prompt
facial-expressions Worry: determined, resolute ; Heroine standing on a rooftop; medium shot; Heroes; cityscape with smoke and fire in the distance; cinematic
Characteristic
Shot : A woman in a dark green jacket stands on a rooftop overlooking a city skyline. The city is on fire with flames and smoke rising in the background.
Aesthetic Score : 0.7
Mood : dramatic, tense, apocalyptic
Quality
Entropy : 6.82
Noise : 42
Prompt Clip Score : 0.36
AI Evaluation
Likelihood of AI : 0.10
Image errors : No obvious errors
Intense Moment at the Kitchen Table: A Tale of Tension and Conflict
A couple is seen engaged in a tense exchange at their kitchen table, their expressions filled with unease and conflict. The woman’s hands on her face and the man’s forward lean add to the intensity of the scene, creating a dramatic effect that is further enhanced by the intimate lighting.
Prompt
facial-expressions Worry: tense, frustrated ; Couple arguing in a kitchen; eye-level; Normal People; cluttered kitchen with dirty dishes; cinematic
Characteristic
Shot : A couple is arguing at a kitchen table, likely during a meal. The woman is sitting with her hands on her chin, looking surprised or shocked. The man is sitting opposite her, looking at her with a surprised or worried expression. The kitchen is dimly lit, and there are plates of food on the table.
Aesthetic Score : 0.5
Mood : tense, dramatic, uncomfortable
Quality
Entropy : 6.82
Noise : 55
Prompt Clip Score : 0.31
AI Evaluation
Likelihood of AI : 0.10
Image errors : No major image errors.
The Glow of Victory: A Gamer’s Intense Focus
A young man, lost in the digital world, his eyes reflecting the screen’s vibrant glow. This image captures the raw intensity and dedication of a gamer in the heat of the moment. The blurred background and low lighting create a dramatic atmosphere, highlighting the passion that fuels his pursuit of victory.
Prompt
facial-expressions Worry: intense, focused ; Gamer’s hands on a keyboard; close-up; Gamer; flashing lights and sounds from the game; cinematic
Characteristic
Shot : A young man is playing on his computer in a dimly lit room with colorful lights in the background.
Aesthetic Score : 0.6
Mood : focused, intense, determined
Quality
Entropy : 6.74
Noise : 59
Prompt Clip Score : 0.26
AI Evaluation
Likelihood of AI : 0.80
Image errors : The image is slightly blurry and the colors are a bit muted. The subject’s hair looks unnatural and the lighting is not very natural.
Lost in the City Lights
A solitary figure stands amidst the urban glow, her gaze piercing through the darkness. The blurred lights and empty street create a sense of isolation and mystery, leaving the viewer to ponder her thoughts and the story behind her enigmatic presence.
Prompt
facial-expressions Worry: lonely, vulnerable ; Woman walking alone at night; long shot; Single Persons; deserted street with streetlights; cinematic
Characteristic
Shot : A young woman is standing in the middle of a city street at night. The street is lit by streetlights and the woman is looking at the camera with a serious expression.
Aesthetic Score : 0.8
Mood : melancholy, introspective, urban
Quality
Entropy : 6.75
Noise : 42
Prompt Clip Score : 0.30
AI Evaluation
Likelihood of AI : 0.10
Image errors : The image appears to be slightly over-exposed.
The Weight of War: A Soldier’s Focus Amidst Chaos
A lone soldier, his face etched with determination, studies a map in a smoke-filled forest. The scene captures the intensity and urgency of wartime, leaving the viewer with a sense of impending danger and uncertainty.
Prompt
facial-expressions Worry: serious, strategic ; Hero looking at a map; medium shot; Heroes; war-torn battlefield with smoke and debris; cinematic
Characteristic
Shot : A soldier in a military uniform is crouched down in a forest, looking intently at a map, with a pen in his hand. He is in the midst of a battlefield, as there are fires and other soldiers in the background.
Aesthetic Score : 0.7
Mood : intense, serious, focused
Quality
Entropy : 6.93
Noise : 68
Prompt Clip Score : 0.26
AI Evaluation
Likelihood of AI : 0.80
Image errors : Some of the background details, particularly the other soldiers, appear somewhat blurry and unrealistic, potentially due to AI generation or post-processing. The lighting and shadowing also seem slightly artificial.
Conclusion
The results show that the generative AI model performed well in terms of understanding the scene and camera position, but struggled with the aesthetic aspect. Here’s a breakdown:
- Camera Position: The model scored 0.2, indicating it did not perform well in capturing the intended camera position. This suggests the model may not be very sensitive to camera position instructions in prompts.
- Shot Analysis: The model scored 0.435, which is below average. This means the model had some difficulty understanding the scene described in the prompt and translating it into the generated image.
- Aesthetic Analysis: The model scored 0.09, which is very good. This indicates that the generated image closely matched the expected aesthetic style, despite the other issues.
Overall, the model seems to be better at capturing the desired aesthetic than understanding the scene and camera position. This suggests that the model might need further training to improve its ability to interpret and implement these aspects of the prompt.
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://www.freepik.com