AI's Facial Expressions: A Mixed Bag of Emotions with Flux-dev
- 9 minutes read - 1916 wordsTable of Contents
Facial expressions are a powerful tool for conveying emotions and intentions. In the realm of AI, generating realistic and expressive faces is a challenging task. This blog post explores the capabilities of a generative AI model in creating facial expressions, analyzing its performance in understanding scene context and aesthetic. We’ll examine how the model interprets prompts, its strengths in capturing the essence of a scene, and areas where it needs improvement, particularly in accurately capturing camera position and aesthetic.
Created with: flux-dev
A Solitary Figure, A Crowd Awaits
A lone man, shrouded in mystery, stands with his back to the camera, microphone in hand, facing a sea of expectant faces. The silhouette and blurred background create a sense of isolation and anticipation, leaving the viewer wondering what secrets lie ahead.
Prompt
facial-expressions Skepticism: Uncertain, hesitant ; A hero, standing in front of a crowd, holding a weapon, but looking conflicted; eye-level; Hero; cheering crowd, bright lights, stage; cinematic
Characteristic
Shot : A man standing in front of a crowd at a concert, holding a microphone stand
Aesthetic Score : 0.3
Mood : dark, mysterious, lonely
Quality
Entropy : 6.14
Noise : 55
Prompt Clip Score : 0.23
AI Evaluation
Likelihood of AI : 0.30
Image errors : The image is a bit noisy and grainy. There are also some artifacts in the background.
Silhouetted Against the City: A Moment of Contemplation
A lone figure stands on a rooftop, their back to the viewer, gazing out over a cityscape bathed in the soft light of dusk. The scene evokes a sense of melancholy and contemplation, with the man’s silhouette against the twinkling city lights highlighting his isolation and introspective mood.
Prompt
facial-expressions Skepticism: Isolated, disillusioned ; A hero, standing on a rooftop, looking out at a city skyline, but with a sense of loneliness; eye-level; Hero; City lights, distant sounds of the city; cinematic
Characteristic
Shot : A man in silhouette stands on a rooftop overlooking a city skyline at dusk. The cityscape is bathed in soft, warm light, creating a sense of mystery and intrigue.
Aesthetic Score : 0.7
Mood : melancholy, contemplative, urban
Quality
Entropy : 6.51
Noise : 57
Prompt Clip Score : 0.26
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image is slightly blurry, which could be due to low light conditions. The colors are also a bit muted, which could be a stylistic choice or a result of post-processing.
Lost in the Neon Maze
A solitary figure, shrouded in darkness, walks towards the viewer through a city awash in vibrant neon lights. The blurred background and shadowy figure create an atmosphere of mystery and isolation, leaving the viewer to wonder about their story and destination.
Prompt
facial-expressions Skepticism: Melancholy, disillusioned ; A lone figure, back turned, walking away from a brightly lit city skyline; eye-level; Single Person; Urban, neon signs, bustling crowds; cinematic
Characteristic
Shot : A lone person standing in a city with neon lights in the background.
Aesthetic Score : 0.5
Mood : lonely, urban, contemplative
Quality
Entropy : 6.21
Noise : 57
Prompt Clip Score : 0.25
AI Evaluation
Likelihood of AI : 0.10
Image errors : The image is a bit grainy and there is some noise in the background.
Lost in the Neon Glow: A Moment of Intense Focus
A young man, bathed in the ethereal glow of pink and blue neon lights, stares intently at his computer screen. Headphones on, a can of soda within reach, he’s completely absorbed in the digital world. The dramatic lighting creates an atmosphere of mystery and intrigue, hinting at a story waiting to unfold.
Prompt
facial-expressions Skepticism: Suspicious, wary ; A gamer, hunched over a computer screen, surrounded by empty pizza boxes and energy drink cans; close-up; Gamer; Dark room, flashing lights, gaming peripherals; cinematic
Characteristic
Shot : A young man is sitting at a desk in a dimly lit room with his headphones on. He is looking at a computer screen and his hands are holding the headphones. There is a can of soda on the desk in front of him, and there are pizza slices on the table near him.
Aesthetic Score : 0.5
Mood : focused, contemplative, techy
Quality
Entropy : 6.56
Noise : 58
Prompt Clip Score : 0.28
AI Evaluation
Likelihood of AI : 0.10
Image errors : The image appears to be somewhat overexposed, especially in the background. Some slight blur appears on the man’s face.
Lost in the City: A Woman’s Mysterious Journey
A captivating image of a confident young woman navigating the urban landscape. Her leather jacket and long brown hair exude an air of mystery, while the blurred background and shallow depth of field heighten the sense of intrigue. This photograph captures a fleeting moment of urban life, leaving the viewer to wonder about her destination and the secrets she holds.
Prompt
facial-expressions Skepticism: Paranoid, distrustful ; A woman, walking through a crowded street, looking around with suspicion; eye-level; Single Person; Busy city street, people rushing by, street vendors; cinematic
Characteristic
Shot : A young woman with long dark hair is walking in a city street. She is wearing a leather jacket and a floral patterned shirt. The background is blurred, and there are other people walking in the distance. The lighting is soft and natural.
Aesthetic Score : 0.7
Mood : mysterious, urban, confident
Quality
Entropy : 6.75
Noise : 66
Prompt Clip Score : 0.23
AI Evaluation
Likelihood of AI : 0.10
Image errors : There are no obvious artifacts or errors in the image.
Lost in the Neon Glow: A Man’s Melancholy at the Bar
A solitary figure sits at a dimly lit bar, his silhouette shrouded in the red and blue neon glow. The atmosphere is heavy with melancholy, hinting at a story of introspection and loneliness. The dramatic lighting creates a sense of mystery, leaving the viewer to ponder the man’s thoughts and the secrets hidden within the shadows.
Prompt
facial-expressions Skepticism: Doubtful, introspective ; A man, sitting alone in a dimly lit bar, staring into his drink; eye-level; Single Person; Empty bar, flickering neon lights, rain outside; cinematic
Characteristic
Shot : A man sits at a bar, lost in thought, with a drink in his hand. The scene is dimly lit, with neon signs casting a red glow on the bar.
Aesthetic Score : 0.5
Mood : melancholy, introspective, somber
Quality
Entropy : 5.88
Noise : 49
Prompt Clip Score : 0.29
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image is slightly blurry, and there is some noise in the shadows.
Intimate Gathering Under Warm Lights
A group of friends or family share a casual and thoughtful moment over dinner, bathed in warm, inviting light. The composition draws you into their conversation, leaving the background softly blurred.
Prompt
facial-expressions Skepticism: Disbelieving, amused ; A group of friends, gathered around a table, listening to a story with skeptical expressions; eye-level; Normal People; Cozy living room, warm lighting, snacks; cinematic
Characteristic
Shot : A group of three people are sitting at a table, eating and talking. The image is taken from a slightly elevated angle and is lit by soft artificial light.
Aesthetic Score : 0.6
Mood : casual, intimate, conversational
Quality
Entropy : 6.67
Noise : 73
Prompt Clip Score : 0.19
AI Evaluation
Likelihood of AI : 0.10
Image errors : The image is slightly grainy and the colors are a bit muted. The image is slightly underexposed.
Silhouetted Against the Setting Sun, a Hero Emerges
A lone figure, possibly a superhero, stands defiant against a backdrop of smoke and a setting sun. The city skyline stretches out behind them, bathed in a warm glow. The image evokes a sense of mystery, epic scale, and hope, leaving viewers wondering what challenges lie ahead.
Prompt
facial-expressions Skepticism: Doubtful, conflicted ; A superhero, cape billowing, standing on a rooftop, looking down at a city in chaos; eye-level; Hero; Smoke, fire, destruction; cinematic
Characteristic
Shot : A lone figure in a red cape stands with their back to the viewer, looking at a city skyline with smoke in the background. The figure is silhouetted against the setting sun, creating a dramatic effect.
Aesthetic Score : 0.7
Mood : epic, hopeful, dramatic
Quality
Entropy : 6.52
Noise : 52
Prompt Clip Score : 0.27
AI Evaluation
Likelihood of AI : 0.40
Image errors : The image is slightly blurry, particularly in the background, and the smoke in the background seems a bit artificial.
In the Zone: A Gamer’s Intense Focus
A young man is completely immersed in his game, his face illuminated by the screen’s glow. The low-key lighting and close-up shot create a sense of suspense and focus, capturing the intensity of his concentration.
Prompt
facial-expressions Skepticism: Frustrated, doubtful ; A gamer, staring intently at a screen, but with a look of frustration; close-up; Gamer; Brightly lit room, gaming setup, controller in hand; cinematic
Characteristic
Shot : A young man is sitting in front of a computer monitor, wearing headphones and holding a video game controller. The scene is illuminated by blue and pink light, creating a futuristic atmosphere.
Aesthetic Score : 0.6
Mood : focused, intense, futuristic
Quality
Entropy : 6.55
Noise : 62
Prompt Clip Score : 0.27
AI Evaluation
Likelihood of AI : 0.30
Image errors : The image seems to have some minor color banding and compression artifacts, especially in the darker areas, possibly caused by image resizing.
Lost in the Pages: A Moment of Contemplation
A young woman, absorbed in the news, sits alone in a cafe. The blurred background isolates her, creating a sense of intimacy and privacy. Her thoughtful expression hints at a world of stories unfolding within the pages of her newspaper.
Prompt
facial-expressions Skepticism: Cynical, disbelieving ; A woman, dressed in everyday clothes, holding a newspaper with a sensational headline; eye-level; Normal People; Coffee shop, people going about their day; cinematic
Characteristic
Shot : A woman is reading a newspaper in a cafe. The setting is a casual cafe, and the woman is dressed in a black jacket.
Aesthetic Score : 0.6
Mood : focused, pensive, casual
Quality
Entropy : 6.87
Noise : 74
Prompt Clip Score : 0.24
AI Evaluation
Likelihood of AI : 0.10
Image errors : The image has a slight amount of blurriness, especially in the background.
Conclusion
The analysis shows that the generative AI model performed well in understanding the scene and camera position, but struggled with the aesthetic aspect. Here’s a breakdown:
- Camera Position: The model scored 0.3, 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 0.65, 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 0.15, 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 shows promise in understanding the scene and shot composition, but needs improvement in accurately 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/dev/api