AI Captures Emotions, But Struggles with Camera Angles with Stable-diffusion
- 9 minutes read - 1886 wordsTable of Contents
In the realm of artificial intelligence, the ability to generate realistic and expressive images is a rapidly evolving field. One area of particular interest is the creation of facial expressions, which play a crucial role in conveying emotions and storytelling. This blog post examines the performance of a generative AI model in capturing facial expressions across various scenes and camera positions. We’ll explore the model’s strengths and weaknesses, highlighting its impressive ability to capture emotions while revealing its challenges in accurately replicating camera angles. Through this analysis, we gain insights into the current state of AI image generation and its potential for future advancements.
Created with: stability-ai-core
City Lights, City Smiles: Capturing Joy in the Urban Jungle
A young woman radiates happiness as she strolls through a bustling city street. The shallow depth of field draws our attention to her infectious smile, highlighting the joy she finds amidst the urban landscape. The bright sky and vibrant surroundings create a cheerful atmosphere, capturing the essence of a happy moment in the city.
Prompt
facial-expressions Happiness: Joyful, carefree ; Single person; eye-level; Single Persons; A bustling city street with vibrant colors and people going about their day.; cinematic
Characteristic
Shot : A young woman is walking down a busy city street, smiling happily. The city is full of life and color.
Aesthetic Score : 0.7
Mood : joyful, vibrant, energetic
Quality
Entropy : 6.82
Noise : 66
Prompt Clip Score : 0.24
AI Evaluation
Likelihood of AI : 0.10
Image errors : No significant errors. The subject has a slightly blurred background and the focus is a little off, but it is not significant. There are also some minor artifacts in the background of the image, which could be improved.
Heroic Silhouette Against the Setting Sun
A lone superhero, cloaked in a flowing cape and wielding a staff, stands triumphantly atop a mountain peak as the sun dips below the horizon. The dramatic lighting and epic landscape create a powerful image of hope and authority.
Prompt
facial-expressions Happiness: Triumphant, proud, relieved ; Hero; eye-level; Heroes; A hero standing triumphantly on a mountain peak, with a breathtaking sunset behind them.; cinematic
Characteristic
Shot : A lone superhero stands on a mountain top, looking out over a landscape of mountains and a sunset sky.
Aesthetic Score : 0.7
Mood : epic, dramatic, powerful
Quality
Entropy : 6.89
Noise : 65
Prompt Clip Score : 0.26
AI Evaluation
Likelihood of AI : 0.80
Image errors : There are some visible signs of digital manipulation, particularly in the clouds and the cape, giving the image a slightly artificial look. The shadows on the hero’s face are a little unnatural.
Sunny Day Picnics and Laughter: Friends Enjoying the Good Times
Capture the joy of a perfect summer day with this heartwarming image. A group of friends gather for a picnic, their laughter and smiles radiating warmth and happiness. The bright colors and casual atmosphere create a sense of carefree enjoyment, making this a picture that evokes feelings of pure bliss.
Prompt
facial-expressions Happiness: Warm, intimate, joyful ; Normal people; eye-level; Normal People; A group of friends laughing and sharing a meal at a picnic table in a park.; cinematic
Characteristic
Shot : A group of friends are enjoying a meal together outdoors in a park. They are all laughing and smiling, and the atmosphere is relaxed and happy.
Aesthetic Score : 0.75
Mood : joyful, friendly, relaxed
Quality
Entropy : 6.89
Noise : 80
Prompt Clip Score : 0.27
AI Evaluation
Likelihood of AI : 0.10
Image errors : No visible errors
Laughter Contagious: Sharing the Joy of a Funny Moment
A man bursts into laughter, his joy radiating as he watches a screen with friends. The well-lit image captures the pure excitement and happiness of the moment, making it relatable and heartwarming.
Prompt
facial-expressions Happiness: Excited, exhilarated, triumphant ; Gamer; close-up; Gamer; A gamer’s face lit by the screen, eyes wide with excitement as they celebrate a victory.; cinematic
Characteristic
Shot : A young man with a beard is laughing, wearing a headset and a grey t-shirt, sitting in a dimly lit room with a TV screen in the background, other people are blurred in the background.
Aesthetic Score : 0.7
Mood : joyful, vibrant, excited
Quality
Entropy : 6.43
Noise : 69
Prompt Clip Score : 0.31
AI Evaluation
Likelihood of AI : 0.20
Image errors : Some minor blurriness on the subject’s face and around the edges of the image.
Golden Hour Joy: A Woman Finds Happiness in a Field of Flowers
Capture the essence of summer with this heartwarming image. A young woman with long brown hair radiates joy as she walks through a field of yellow flowers, bathed in the warm glow of the setting sun. The scene evokes a sense of carefree happiness and the beauty of nature’s golden hour.
Prompt
facial-expressions Happiness: Free, joyful, carefree ; Single person; eye-level; Single Persons; A woman dancing freely in a field of wildflowers, bathed in golden sunlight.; cinematic
Characteristic
Shot : A young woman in a floral dress is standing in a field of yellow flowers. The sun is setting in the background, casting a warm glow on the scene.
Aesthetic Score : 0.8
Mood : joyful, carefree, summery
Quality
Entropy : 6.80
Noise : 70
Prompt Clip Score : 0.25
AI Evaluation
Likelihood of AI : 0.10
Image errors : No noticeable artifacts or errors
Superhero Squad: A Whimsical Celebration of Childhood
This playful collage captures the youthful energy and innocence of eight children dressed as Superman. The repetition of the portraits creates a sense of unity, while the subtle variations in their expressions add a touch of individuality. The overall mood is whimsical and hopeful, reminding us of the power and potential within each child.
Prompt
facial-expressions Happiness: Brave, heroic, selfless ; Hero; wide shot; Heroes; A hero saving a child from danger, with a sense of urgency and determination.; cinematic
Characteristic
Shot : A collage of 8 images, each featuring a young child dressed as Superman or Supergirl, with various hairstyles, looking at the camera. The background is a generic, blurred city scene.
Aesthetic Score : 0.7
Mood : optimistic, playful, innocent
Quality
Entropy : 6.90
Noise : 80
Prompt Clip Score : 0.26
AI Evaluation
Likelihood of AI : 0.80
Image errors : There is some pixelation in the images, particularly in the hair and skin.
Cozy Holiday Gathering by the Fireplace
A heartwarming scene of three friends enjoying a festive evening by a crackling fireplace. The warm glow and holiday decorations create a cozy and inviting atmosphere, capturing the joy of the season.
Prompt
facial-expressions Happiness: Warm, cozy, loving ; Normal people; eye-level; Normal People; A family gathered around a fireplace, sharing stories and laughter.; cinematic
Characteristic
Shot : A family of three, two women and a boy, are sitting in front of a fireplace. They are all smiling and appear to be enjoying their time together.
Aesthetic Score : 0.8
Mood : warm, cozy, happy
Quality
Entropy : 6.62
Noise : 75
Prompt Clip Score : 0.24
AI Evaluation
Likelihood of AI : 0.10
Image errors : No obvious image errors.
The Focus Is On Him: A Gamer’s Intensity
A young man sits at a table, his eyes locked on the camera, a video game controller gripped tightly in his hand. The background blurs, highlighting his intense focus and determination. This image captures the raw emotion and dedication of a gamer in the heat of the moment.
Prompt
facial-expressions Happiness: Focused, determined, absorbed ; Gamer; close-up; Gamer; A gamer’s hands deftly navigating a game controller, with a look of intense focus and concentration.; cinematic
Characteristic
Shot : A young man is sitting at a table, looking directly at the camera while holding a video game controller in his hands. He appears to be engrossed in a game, and his facial expression is intense.
Aesthetic Score : 0.6
Mood : intense, focused, serious
Quality
Entropy : 6.40
Noise : 66
Prompt Clip Score : 0.26
AI Evaluation
Likelihood of AI : 0.10
Image errors : The image has a slight blur in the background and there is some noise in the shadows.
Autumn Bliss: A Man Finds Peace in the Golden Leaves
A heartwarming scene of a man basking in the beauty of autumn. His contented smile and the vibrant yellow leaves create a sense of warmth and tranquility. This image captures the essence of peaceful happiness found in nature’s embrace.
Prompt
facial-expressions Happiness: Peaceful, content, nostalgic ; Single person; eye-level; Single Persons; A man sitting on a bench in a park, watching children play, with a gentle smile on his face.; cinematic
Characteristic
Shot : A man sitting on a park bench in autumn, with golden leaves on the ground and trees in the background
Aesthetic Score : 0.7
Mood : happy, relaxed, peaceful
Quality
Entropy : 6.93
Noise : 75
Prompt Clip Score : 0.19
AI Evaluation
Likelihood of AI : 0.20
Image errors : No significant artifacts or errors.
Heroic Victory: A Champion Rises Amidst the Cheers
A powerful image captures the moment of triumph as a superhero, clad in blue and gold, stands tall before a cheering crowd. The scene, set against a backdrop of city buildings and waving flags, exudes a sense of drama, heroism, and excitement. The superhero’s raised fist and the energy of the crowd create a powerful visual that embodies the spirit of victory.
Prompt
facial-expressions Happiness: Triumphant, victorious, celebrated ; Hero; wide shot; Heroes; A hero standing tall, surrounded by cheering crowds, after achieving a great victory.; cinematic
Characteristic
Shot : A man in a superhero costume is standing in front of a crowd of people. He is raising his fist in the air and appears to be giving a speech. The crowd is cheering and raising their arms in the air. The background is a city street with buildings on both sides.
Aesthetic Score : 0.7
Mood : dramatic, powerful, hopeful
Quality
Entropy : 6.65
Noise : 81
Prompt Clip Score : 0.23
AI Evaluation
Likelihood of AI : 0.20
Image errors : Slight compression artifacts are visible on the costume.
Conclusion
The results show 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 0.25, 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 0.58, 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 0.11, which is considered very good. This means that the generated image closely matched the expected aesthetic style.
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://stability.ai