AI's Facial Expressions: A Mixed Bag with Flux-pro
- 9 minutes read - 1803 wordsTable of Contents
Facial expressions are a powerful tool in storytelling, conveying emotions and intentions with a single glance. In the realm of AI-generated imagery, capturing these nuances presents a unique challenge. This blog post explores the results of a generative AI model tasked with creating images featuring specific facial expressions. We’ll delve into the model’s performance, analyzing its strengths and weaknesses in capturing the desired emotional range. From the subtle expressions of a lone coffee shop patron to the dramatic intensity of a superhero facing danger, we’ll examine how the model interprets and translates these prompts into visual form. Join us as we explore the fascinating world of AI-generated facial expressions and their potential for future development.
Created with: flux-pro
Lost in Thought: A Moment of Melancholy in a Rainy City
A young woman sits alone at a cafe table, her face illuminated by soft light, lost in contemplation. The rain-soaked city outside the window adds to the pensive mood, creating a scene of quiet introspection and melancholic beauty.
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 at a cafe, looking distressed, her hands on her face. She sits next to a window and a table with a cup of coffee and a book on it.
Aesthetic Score : 0.7
Mood : melancholy, contemplative, introspective
Quality
Entropy : 6.45
Noise : 74
Prompt Clip Score : 0.22
AI Evaluation
Likelihood of AI : 0.10
Image errors : The image is slightly grainy and there are some artifacts in the background.
Superman’s Gaze: A Moment of Intensity
A close-up shot captures Superman’s unwavering gaze, his serious expression hinting at a moment of intense focus. The blurred urban backdrop and warm lighting create a sense of drama and anticipation, leaving the viewer wondering what challenge lies ahead.
Prompt
facial-expressions Worry: intense, burdened ; Man in a superhero costume; medium shot; Heroes; cityscape at night with flashing sirens; cinematic
Characteristic
Shot : A close-up portrait of a man in a Superman costume, with out-of-focus city lights in the background.
Aesthetic Score : 0.6
Mood : intense, dramatic, serious
Quality
Entropy : 6.72
Noise : 72
Prompt Clip Score : 0.26
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image has some minor artifacts and noise, particularly in the background.
Lost in the City’s Pulse: A Moment of Pensive Isolation
A young woman stands amidst the bustling chaos of a subway car, her gaze fixed directly on the viewer. Her stoic expression and the blurred background evoke a sense of melancholic introspection, leaving the viewer to ponder her thoughts and the story behind her solitary presence.
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 with long brown hair is standing on a train. She is looking at the camera with a serious expression.
Aesthetic Score : 0.7
Mood : mysterious, pensive, melancholic
Quality
Entropy : 6.69
Noise : 61
Prompt Clip Score : 0.31
AI Evaluation
Likelihood of AI : 0.10
Image errors : No noticeable artifacts or errors.
The Gamer’s Focus: A Portrait in Blue and Red
A close-up portrait captures the intensity of a young gamer, bathed in dramatic blue and red lighting. His focused expression and the vibrant colors create a powerful and moody atmosphere, highlighting his determination to conquer the virtual 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, lit by blue and red lights, likely in a gaming or computer setup.
Aesthetic Score : 0.7
Mood : intense, focused, mysterious
Quality
Entropy : 6.70
Noise : 70
Prompt Clip Score : 0.33
AI Evaluation
Likelihood of AI : 0.20
Image errors : Some slight noise and compression artifacts are noticeable, but overall the image quality is good.
Autumn Solitude: A Man Finds Peace Amidst Falling Leaves
A poignant image of a man lost in thought on a park bench, surrounded by the vibrant hues of autumn. The scene evokes a sense of melancholy and contemplation, highlighting the beauty and introspection found in solitude.
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 man in a dark jacket is sitting on a bench in a park. The trees are bare and the leaves are on the ground. The man is looking off to the side, seeming introspective.
Aesthetic Score : 0.6
Mood : melancholy, contemplative, autumnal
Quality
Entropy : 6.74
Noise : 79
Prompt Clip Score : 0.31
AI Evaluation
Likelihood of AI : 0.20
Image errors : No significant image errors, but some slight blurring in the background.
Silhouette of Despair: A Woman Stands Against a Burning City
A lone woman stands in silhouette against a backdrop of a city engulfed in flames. The hazy sunset casts a melancholic glow, creating a dramatic and contemplative scene. The image evokes a powerful sense of isolation and despair, with the burning city serving as a stark reminder of loss and destruction.
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 stands on a rooftop with a city skyline in the background, smoke or fire is visible in the distance, creating an apocalyptic mood.
Aesthetic Score : 0.7
Mood : melancholy, hopeful, dramatic
Quality
Entropy : 6.68
Noise : 75
Prompt Clip Score : 0.30
AI Evaluation
Likelihood of AI : 0.20
Image errors : Slight blurriness and a lack of sharpness in the image, particularly in the background.
Silent Tension in the Kitchen
A man and a woman stand locked in a tense confrontation, their expressions unreadable in the low light. The atmosphere crackles with unspoken words, hinting at a brewing argument or a simmering disagreement. The dramatic framing emphasizes the weight of the moment, leaving the viewer to wonder what secrets lie beneath the surface.
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 having a tense conversation in a kitchen. They are standing close to each other, and the man is looking at the woman with a serious expression. The woman is looking away, and her face is expressionless.
Aesthetic Score : 0.6
Mood : tense, serious, confrontational
Quality
Entropy : 6.52
Noise : 74
Prompt Clip Score : 0.30
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image has some minor artifacts, such as noise in the shadows, but no major errors.
Lost in the Code: A Man’s Intense Focus Under Warm Lighting
A close-up shot captures a man deeply engrossed in his work, headphones on, fingers flying across the keyboard. The soft, warm lighting creates an intimate atmosphere, highlighting his determination and the mystery surrounding his task.
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 man is shown wearing a headset, focusing intensely on a keyboard while gaming in a dimly lit room.
Aesthetic Score : 0.6
Mood : intense, focused, determined
Quality
Entropy : 6.71
Noise : 74
Prompt Clip Score : 0.24
AI Evaluation
Likelihood of AI : 0.30
Image errors : Some minor noise and graininess in the image due to low light conditions.
Lost in the Mist: A Silhouette of Solitude
A lone figure walks through a misty night, their silhouette stark against the blurry background. The scene evokes a sense of loneliness, melancholy, and mystery, leaving the viewer to wonder about the figure’s story.
Prompt
facial-expressions Worry: lonely, vulnerable ; Woman walking alone at night; long shot; Single Persons; deserted street with streetlights; cinematic
Characteristic
Shot : A lone figure walking down a street at night. The street is wet and the atmosphere is foggy and mysterious.
Aesthetic Score : 0.6
Mood : lonely, mysterious, melancholic
Quality
Entropy : 6.72
Noise : 74
Prompt Clip Score : 0.29
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image has some noise and grain. The figure is not perfectly in focus. The light source on the left is blurry.
A Soldier’s Burden: A Desolate Landscape and a Heavy Gaze
A lone soldier, clad in military gear, stands amidst a war-torn landscape, his intense gaze fixed on a map. The desolate backdrop and his serious expression create a palpable sense of urgency and suspense, hinting at the weight of his mission and the harsh realities of war.
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 standing in a barren, dusty landscape. He is holding a map in his hand and looking off into the distance.
Aesthetic Score : 0.6
Mood : serious, tense, contemplative
Quality
Entropy : 6.83
Noise : 74
Prompt Clip Score : 0.29
AI Evaluation
Likelihood of AI : 0.10
Image errors : The image is a little blurry and the colors are somewhat muted. The lighting is slightly flat.
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 0.4, which is considered okay. This means the camera position in the generated image was somewhat different from what was expected based on the prompt.
- Shot Analysis: The model scored 0.53, which is considered good. This indicates that the model was able to understand the scene in the prompt and create a shot that was fairly close to what was expected.
- Aesthetic Analysis: The model scored 0.16, which is considered okay. This suggests that the generated image’s aesthetic was somewhat different from what was expected based on the prompt.
Overall, the model seems to be better at understanding the scene and shot composition than it is at 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