AI's Facial Expressions: A Work in Progress with Midjourney
- 9 minutes read - 1811 wordsTable of Contents
Facial expressions are a powerful tool for conveying emotions and intentions. In the realm of artificial intelligence, generating realistic facial expressions is a challenging task. This blog post examines the performance of a generative AI model in capturing facial expressions, analyzing its strengths and weaknesses in understanding camera positions, shot composition, and aesthetic elements. We’ll explore how the model’s ability to generate dramatic facial expressions can be used in various applications, from creating engaging characters in video games to enhancing the realism of virtual assistants.
Created with: midjourney
Contemplating the Cityscape
A solitary figure sits on a park bench, lost in thought as they gaze upon the distant cityscape. The overcast sky and muted colors create a melancholic atmosphere, highlighting the sense of solitude and contemplation in this urban scene.
Prompt
Thoughtfulness Thoughtful, lost in thought: 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 solitary figure sits on a park bench with a cityscape in the background. The scene is painted in a realistic style with a muted color palette, giving the image a melancholic feel.
Aesthetic Score : 0.8
Mood : melancholy, contemplative, urban
Quality
Entropy : 6.86
Noise : 106
Prompt Clip Score : 0.24
AI Evaluation
Likelihood of AI : 0.10
Image errors : The image appears to have some minor artifacts, such as slight blurring around the edges of objects.
Silhouetted Hero, City Lights, and a Starry Sky
A dramatic image of a lone figure in a red cape, standing on a rooftop overlooking a sprawling cityscape at night. The silhouette against the twinkling lights and starry sky evokes a sense of power, hope, and heroism.
Prompt
Thoughtfulness Serious, concerned: 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 lone superhero stands on a rooftop overlooking a city at night. The hero is silhouetted against the city lights, giving an impression of grandeur and isolation.
Aesthetic Score : 0.7
Mood : dark, mysterious, powerful
Quality
Entropy : 6.06
Noise : 85
Prompt Clip Score : 0.22
AI Evaluation
Likelihood of AI : 0.80
Image errors : The image appears to be slightly blurry, particularly in the city lights and the superhero’s cape. The image could be sharper and more detailed.
Lost in the Pages, Carried Away by the Scenery
A young woman finds solace in a book as the world rushes by outside her train window. The blurred landscape evokes a sense of calm and nostalgia, mirroring the peaceful contemplation in her eyes.
Prompt
Thoughtfulness Focused, relaxed: 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 sitting by a train window, reading a book, while the train speeds through a green landscape.
Aesthetic Score : 0.7
Mood : tranquil, contemplative, serene
Quality
Entropy : 6.07
Noise : 90
Prompt Clip Score : 0.32
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image has some minor noise, particularly in the darker areas, and the focus on the book is slightly soft.
Lost in the Game: A Moment of Intense Focus
A young man sits in a dimly lit room, his gaze fixed on the screen. The low-key lighting and his intense focus create a sense of mystery and intrigue, suggesting a crucial moment in a game. The room, decorated with computer equipment and gaming posters, adds to the atmosphere of immersion and dedication.
Prompt
Thoughtfulness Concentrated, determined: 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 is sitting in front of his computer, illuminated by blue light, looking directly at the camera. The scene has a gaming theme.
Aesthetic Score : 0.7
Mood : focused, intense, dark
Quality
Entropy : 5.50
Noise : 73
Prompt Clip Score : 0.25
AI Evaluation
Likelihood of AI : 0.10
Image errors : Some noise is visible in the darker areas of the image.
Solitude on the Shore: A Moment of Tranquility
A lone figure walks towards the horizon on a deserted beach, the vastness of the sky and sand creating a sense of isolation and contemplation. The minimalist composition evokes a feeling of peace and quiet reflection.
Prompt
Thoughtfulness Thoughtful, pensive: 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 deserted beach towards the horizon. The sky is a soft blue, and the sand is white.
Aesthetic Score : 0.7
Mood : tranquil, contemplative, minimalist
Quality
Entropy : 5.51
Noise : 96
Prompt Clip Score : 0.25
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image is slightly overexposed, and the colors are a bit washed out. There is also a slight blurriness in the background.
Amidst the Ashes: A Firefighter Contemplates the Devastation
A solitary firefighter stands amidst the rubble of a destroyed building, smoke billowing in the background. The somber scene, dominated by shades of gray and brown, evokes a sense of isolation and contemplation, highlighting the aftermath of a destructive event.
Prompt
Thoughtfulness Sad, weary: Somber, reflective ; A firefighter standing amidst the ruins of a fire; eye-level; Hero; smoke and debris filling the air; cinematic
Characteristic
Shot : A firefighter stands in front of a burning building, smoke and debris in the background. The image is likely a photo of a real event, emphasizing the seriousness and danger of the situation.
Aesthetic Score : 0.7
Mood : serious, somber, heroic
Quality
Entropy : 6.40
Noise : 107
Prompt Clip Score : 0.25
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image appears slightly overexposed, with some areas of the smoke and debris being too bright.
Family Laughter Fills a Cozy Dining Room
A heartwarming scene of a family of four sharing a meal and laughter under warm lighting. The focus on their joyful interaction creates an intimate and cozy atmosphere.
Prompt
Thoughtfulness Smiling, engaged: Intimate, connected ; A family gathered around a dinner table; eye-level; Normal People; a warm, inviting kitchen setting; cinematic
Characteristic
Shot : A family is sitting around a table, having dinner together. It’s dark outside, but the room is warm and well-lit. They are all smiling and laughing, and the table is filled with delicious food.
Aesthetic Score : 0.7
Mood : happy, cozy, warm
Quality
Entropy : 6.63
Noise : 95
Prompt Clip Score : 0.29
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image has minor color banding in the background and some areas of the table. There are also some minor artifacts around the edges.
The Glow of Competition: A Gamer’s Focus Under the Neon Lights
A close-up shot captures the intensity of a young man engrossed in a video game. Red and blue lighting dramatically illuminate his face and hands, highlighting the focus and competitive spirit of the moment.
Prompt
Thoughtfulness Focused, exhilarated: 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 : Close-up portrait of a young man playing a video game, illuminated with red and blue lights.
Aesthetic Score : 0.7
Mood : intense, focused, futuristic
Quality
Entropy : 6.35
Noise : 59
Prompt Clip Score : 0.28
AI Evaluation
Likelihood of AI : 0.10
Image errors : The image is slightly overexposed, particularly in the highlights.
Finding Peace in the Park
A young woman finds tranquility amidst the lush greenery, her focused expression and the soft, gentle atmosphere creating a sense of calm and serenity. The image captures a moment of peaceful contemplation in a beautiful natural setting.
Prompt
Thoughtfulness Calm, focused: 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 sits on a park bench, writing in a notebook, with a blurred background of green trees and yellow flowers
Aesthetic Score : 0.6
Mood : peaceful, calm, contemplative
Quality
Entropy : 6.84
Noise : 91
Prompt Clip Score : 0.29
AI Evaluation
Likelihood of AI : 0.10
Image errors : No noticeable errors in the image
Superman Faces the Storm, Hope in His Eyes
A powerful image of Superman, clad in his iconic suit, gazes upwards at a sky filled with ominous clouds and a single ray of light. The scene evokes a sense of drama and hope, suggesting that the Man of Steel is ready to face whatever challenges lie ahead.
Prompt
Thoughtfulness Serious, focused: 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 in a Superman costume looks up at the cloudy sky with a hopeful expression.
Aesthetic Score : 0.6
Mood : hopeful, dramatic, powerful
Quality
Entropy : 6.71
Noise : 95
Prompt Clip Score : 0.25
AI Evaluation
Likelihood of AI : 0.70
Image errors : The clouds look a bit too uniform and artificial. The lighting is a bit harsh and flat, and the edges of the man’s costume are somewhat pixelated.
Conclusion
The results show that the generative AI model performed okay in terms of understanding camera positions and scene composition, but needs improvement in capturing the desired aesthetic. Here’s a breakdown:
- Camera Position: The model scored 0.05, indicating it struggled to accurately translate the camera position from the prompt to the generated image. This suggests the model may not be very sensitive to camera angles and perspectives.
- Shot Analysis: The model scored 0.42, which is slightly below average. This means the generated image’s shot composition wasn’t perfectly aligned with the prompt’s description. The model might have difficulty understanding and implementing specific shot types like close-ups or wide shots.
- Aesthetic Analysis: The model scored 0.05, which is significantly below average. This indicates a considerable difference between the expected aesthetic and the actual aesthetic of the generated image. The model might be struggling to capture the desired mood, style, or visual elements.
Overall: The model needs further training to improve its ability to understand and implement camera positions, shot composition, and aesthetic elements.
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://midjourney.com