AI's Facial Expressions: A Mixed Bag of Success with Flux-dev
- 10 minutes read - 1945 wordsTable of Contents
Facial expressions are a powerful tool for conveying emotions and intentions in visual storytelling. Generative AI models are increasingly being used to create images with realistic facial expressions, but how well do they capture the nuances of human emotion? This blog post delves into the performance of a generative AI model in creating images with facial expressions, analyzing its ability to understand camera position, shot composition, and aesthetic quality. We’ll explore examples where the model excels and where it needs improvement, providing insights into the current state of AI’s ability to capture the complexities of human expression.
Created with: flux-dev
Lost in the Code: A Man’s Focus in the Dark
A solitary figure hunches over a glowing screen, bathed in the soft light of a few strategically placed lamps. The darkness surrounding him adds an air of mystery, hinting at the intensity of his concentration. Is he working on a groundbreaking project, or is he lost in a world of his own making? The mood is one of focused determination, tinged with a hint of melancholy.
Prompt
facial-expressions Realization: Intense, focused ; A gamer, hunched over a computer screen; close-up; Gamer; a dimly lit room, with flashing lights from the monitor and empty pizza boxes scattered around; cinematic
Characteristic
Shot : A young man is sitting in front of a computer in a dimly lit room. He is typing on the keyboard and appears to be focused on his work.
Aesthetic Score : 0.6
Mood : intense, focused, melancholic
Quality
Entropy : 6.16
Noise : 66
Prompt Clip Score : 0.17
AI Evaluation
Likelihood of AI : 0.20
Image errors : There is a slight blur in the background and some minor noise in the image.
Warm Glow, Intimate Conversation: A Dinner Party Captured
A group of friends gather around a table, bathed in warm, inviting light. The casual atmosphere and lively conversation create a sense of intimacy and connection, captured in this slightly dramatic image.
Prompt
facial-expressions Realization: Nostalgic, heartwarming ; A family, gathered around a dinner table; medium shot; Normal People; a warm and inviting kitchen, with the aroma of home-cooked food filling the air; cinematic
Characteristic
Shot : A group of people are sitting around a table eating dinner. The room is dimly lit and there is a warm, inviting atmosphere.
Aesthetic Score : 0.5
Mood : cozy, warm, intimate
Quality
Entropy : 6.62
Noise : 71
Prompt Clip Score : 0.26
AI Evaluation
Likelihood of AI : 0.10
Image errors : No visible artifacts or errors.
Solitude and Serenity on the Cliffside
A woman finds peace amidst the breathtaking beauty of a sunset over the ocean. The vastness of the sea and the soft glow of the setting sun create a serene and contemplative atmosphere, highlighting the feeling of solitude and reflection.
Prompt
facial-expressions Realization: Reflective, contemplative ; A woman, standing on a cliff overlooking the ocean; eye-level; Single Person; a vast expanse of blue water stretching out to the horizon, with the sun setting in the distance; cinematic
Characteristic
Shot : A woman standing on a cliff overlooking a beautiful ocean sunset. The sun is setting behind the woman, and the ocean is a deep blue.
Aesthetic Score : 0.7
Mood : tranquil, serene, romantic
Quality
Entropy : 6.66
Noise : 56
Prompt Clip Score : 0.27
AI Evaluation
Likelihood of AI : 0.20
Image errors : No noticeable errors
Superman Faces the Flames
A dramatic image of Superman, clad in his iconic suit, standing amidst a fiery inferno. The smoke and flames create a sense of danger and intensity, while the close-up shot of Superman’s face highlights his unwavering determination.
Prompt
facial-expressions Realization: Determined, resolute ; A superhero, standing in the middle of a battle; wide shot; Hero; a chaotic scene of destruction and explosions, with enemies closing in; cinematic
Characteristic
Shot : A man dressed as Superman is standing in front of a fiery background
Aesthetic Score : 0.8
Mood : serious, powerful, heroic
Quality
Entropy : 6.51
Noise : 65
Prompt Clip Score : 0.27
AI Evaluation
Likelihood of AI : 0.50
Image errors : No significant errors. The lighting is slightly uneven, which could be fixed with minor retouching.
Lost in the Shadows: A Man’s Solitude in the Subway
A solitary figure stands amidst the blurred chaos of a dimly lit subway station. The shallow depth of field isolates him, emphasizing his sense of loneliness and the mystery surrounding his presence. The mood is dark and evocative, leaving the viewer to ponder his story.
Prompt
facial-expressions Realization: Lost, alienated ; A man, walking through a crowded train station; eye-level; Single Person; a sea of faces, all rushing in different directions; cinematic
Characteristic
Shot : A man in a black jacket stands in a crowded train station, looking serious and introspective. The background is blurry, creating a sense of depth and isolation.
Aesthetic Score : 0.6
Mood : dark, mysterious, introspective
Quality
Entropy : 6.46
Noise : 50
Prompt Clip Score : 0.25
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image is slightly blurry, but this could be intentional to create a sense of mystery and distance.
The Weight of Defeat: A Moment of Solitude in the Digital Age
A young person sits alone in a dimly lit room, staring at a computer screen displaying the stark message ‘game over’. The scene evokes a sense of melancholy and loneliness, capturing the feeling of defeat that can accompany digital experiences.
Prompt
facial-expressions Realization: Defeated, frustrated ; A gamer, staring at a blank screen; close-up; Gamer; a dimly lit room, with the only light coming from the monitor, which is now displaying a game over message; cinematic
Characteristic
Shot : A person, likely a teenager, is sitting in front of a computer screen with the words ‘game over’ displayed on it. The lighting is dim and blue, creating a somewhat melancholic atmosphere. It is suggested that this person is experiencing feelings of disappointment, frustration, or even sadness related to the game.
Aesthetic Score : 0.3
Mood : melancholic, somber, defeated
Quality
Entropy : 4.57
Noise : 26
Prompt Clip Score : 0.31
AI Evaluation
Likelihood of AI : 0.10
Image errors : The image is underexposed and the silhouette is too dark to make out any facial expressions or details.
Silhouette of Hope: A Lone Figure Contemplates the City at Sunset
A solitary figure, cloaked in mystery, stands on a rooftop overlooking a breathtaking cityscape bathed in the golden hues of sunset. The dramatic silhouette against the vibrant sky evokes a sense of epic hope and grandeur, leaving the viewer to ponder the figure’s story and the city’s future.
Prompt
facial-expressions Realization: Triumphant, awe-inspiring ; A superhero, standing atop a skyscraper; wide shot; Hero; a sprawling cityscape bathed in the golden light of sunset; cinematic
Characteristic
Shot : A silhouetted superhero stands on a rooftop in a city at sunset, looking out over the cityscape.
Aesthetic Score : 0.6
Mood : epic, hopeful, dramatic
Quality
Entropy : 6.80
Noise : 55
Prompt Clip Score : 0.30
AI Evaluation
Likelihood of AI : 0.80
Image errors : The image quality is a bit soft. The skyline is blurry and lacking detail. The hero’s cape has an unrealistic texture.
Hope Amidst the Ruins: Superman Stands Tall in a Post-Apocalyptic World
A solitary figure of hope emerges from the ashes. Superman, bathed in the warm glow of the setting sun, stands defiant against a backdrop of a shattered cityscape. The dramatic composition highlights his heroic presence, while the blurred background evokes a sense of isolation and grandeur, hinting at the weight of his responsibility in a world on the brink.
Prompt
facial-expressions Realization: Hopeful, determined ; A superhero, standing in the ruins of a city; wide shot; Hero; a desolate landscape, with smoke rising from the rubble and the sun breaking through the clouds; cinematic
Characteristic
Shot : A man dressed as Superman stands in front of a hazy cityscape at sunset.
Aesthetic Score : 0.6
Mood : epic, heroic, dramatic
Quality
Entropy : 6.73
Noise : 72
Prompt Clip Score : 0.28
AI Evaluation
Likelihood of AI : 0.10
Image errors : The image is slightly overexposed and the lighting is uneven.
Lost in the Neon Glow: A Mysterious Figure Walks the Night
A hooded figure blends into the shadows of a rain-slicked city street, their silhouette stark against the vibrant neon lights. The scene evokes a sense of mystery and loneliness, leaving you wondering who they are and where they’re going.
Prompt
facial-expressions Realization: Melancholy, introspective ; A lone figure; eye-level; Single Person; a bustling city street at night, with neon signs and rain reflecting on the wet pavement; cinematic
Characteristic
Shot : A lone figure, shrouded in a black hoodie, walks through a city street at night. The city is brightly lit with neon signs and streetlights reflecting off the wet pavement.
Aesthetic Score : 0.6
Mood : mysterious, urban, lonely
Quality
Entropy : 6.45
Noise : 64
Prompt Clip Score : 0.27
AI Evaluation
Likelihood of AI : 0.30
Image errors : Some noise and digital artifacts are noticeable in the image, especially in the darker areas. The figure’s silhouette is not very well defined.
A Moment of Reflection: A Young Woman Contemplates Over a Bowl of Salad
This image captures a young woman in a moment of quiet contemplation, seated at a kitchen table with a bowl of salad before her. The soft, natural lighting highlights her thoughtful expression and the vibrant colors of the salad, creating a sense of casual intimacy and inviting viewers to share in her quiet reflection.
Prompt
facial-expressions Realization: Disillusioned, resigned ; A young woman, sitting at a kitchen table; close-up; Normal People; a cluttered kitchen, with dishes piled in the sink and a half-eaten meal on the table; cinematic
Characteristic
Shot : A young woman is sitting at a kitchen table, looking directly at the camera, with a bowl of salad in front of her.
Aesthetic Score : 0.6
Mood : serious, contemplative, calm
Quality
Entropy : 6.80
Noise : 74
Prompt Clip Score : 0.32
AI Evaluation
Likelihood of AI : 0.20
Image errors : There are no visible errors in the image.
Conclusion
The analysis shows 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 0.3, 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 0.51, 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 0.21, which is considered very good. This means that the generated image’s aesthetic closely matched the expected aesthetic described in the prompt.
Overall, the model demonstrates a good understanding of the scene and shot composition, but needs improvement in accurately capturing the intended camera position. The aesthetic quality of the generated image is very good.
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