AI Captures Emotions, But Struggles with Camera Angles with Leonardo-ai
- 9 minutes read - 1851 wordsTable of Contents
In the realm of artificial intelligence, the ability to generate realistic and emotionally evocative images is a rapidly evolving field. This study focuses on a generative AI model’s capacity to capture facial expressions, a key element in conveying human emotion. We explore the model’s performance across various scenarios, analyzing its strengths and weaknesses in understanding camera angles, shot composition, and aesthetic appeal. Through this analysis, we gain valuable insights into the current state of AI image generation and its potential for creating compelling and emotionally resonant visuals.
Created with: leonardo-ai
Finding Peace in the Everyday
A woman finds solace in a quiet moment, her soft smile reflecting a sense of calm and contemplation as she gazes out the window of a cozy cafe. The gentle lighting and her thoughtful expression create an intimate and serene atmosphere.
Prompt
facial-expressions Gratitude: Contentment and appreciation for solitude ; Single woman; eye-level; Single Persons; cozy cafe with warm lighting; cinematic
Characteristic
Shot : A woman sitting at a table in a cafe, looking out the window. The lighting is soft and warm, creating a cozy atmosphere.
Aesthetic Score : 0.8
Mood : calm, contemplative, warm
Quality
Entropy : 6.50
Noise : 97
Prompt Clip Score : 0.20
AI Evaluation
Likelihood of AI : 0.10
Image errors : The image appears to be slightly overexposed, which is noticeable in the highlights. The sharpness could also be slightly improved.
Firefighter Stands Tall Amidst Blazing Inferno
A dramatic scene unfolds as a firefighter, silhouetted against a raging fire, confronts a burning building. Smoke billows from the windows, creating a chaotic and somber atmosphere. The composition highlights the firefighter’s heroic stance, capturing the intensity and danger of the situation.
Prompt
facial-expressions Gratitude: Relief, gratitude for the hero’s bravery ; Firefighter rescuing a child from a burning building; wide shot; Heroes; smoke and flames in the background; cinematic
Characteristic
Shot : A firefighter in full gear, with his back to the camera, is standing in front of a building that is on fire. The fire is burning fiercely, and there is a lot of smoke in the air. The firefighter is looking at the fire, and his expression is serious.
Aesthetic Score : 0.6
Mood : serious, intense, dangerous
Quality
Entropy : 6.91
Noise : 96
Prompt Clip Score : 0.25
AI Evaluation
Likelihood of AI : 0.10
Image errors : The image is well-exposed, but the smoke in the background is a bit hazy and the fire is not as intense as it could be. The composition is a little bit static, and the firefighter’s pose is a bit awkward.
Family Togetherness: A Moment of Joy and Connection
This heartwarming image captures a family of three sharing a meal, radiating happiness and connection. The warm lighting and balanced composition create a sense of intimacy and joy, making it perfect for representing family, togetherness, and the simple pleasures of life.
Prompt
facial-expressions Gratitude: Warmth, appreciation for family and connection ; Family having dinner together; eye-level; Normal People; warm, inviting kitchen; cinematic
Characteristic
Shot : Three people are sitting at a table and eating, smiling at each other. The table is set for a meal and there is food on the table.
Aesthetic Score : 0.7
Mood : happy, joyful, friendly
Quality
Entropy : 6.90
Noise : 97
Prompt Clip Score : 0.22
AI Evaluation
Likelihood of AI : 0.10
Image errors : There are no visible image errors
Laughter and Camaraderie: Friends Enjoy a Night of Gaming
Two friends share a moment of pure joy and excitement as they play video games in a dimly lit room. The man in the foreground’s infectious laughter captures the energy and camaraderie of the scene, while the soft lighting adds a touch of intimacy.
Prompt
facial-expressions Gratitude: Excitement, gratitude for the shared experience ; Gamer celebrating a victory with friends; close-up; Gamer; brightly lit gaming room with screens and controllers; cinematic
Characteristic
Shot : A man is laughing while playing a video game in a dimly lit room. The room appears to be a gaming setup, with multiple monitors and a gaming controller in the foreground.
Aesthetic Score : 0.7
Mood : joyful, intense, focused
Quality
Entropy : 6.61
Noise : 92
Prompt Clip Score : 0.27
AI Evaluation
Likelihood of AI : 0.10
Image errors : The image is slightly overexposed, making the subject’s face too bright. The lighting is uneven, creating a dark background and a bright foreground. The image also has a slight amount of noise in the dark areas.
Golden Hour Reflections: A Moment of Tranquility in a Field of Flowers
An elderly man stands amidst a vibrant field of flowers, bathed in the warm glow of the setting sun. His contemplative gaze and the serene atmosphere evoke a sense of peace and nostalgia, capturing the beauty of a golden hour moment.
Prompt
facial-expressions Gratitude: Awe, gratitude for the beauty of nature ; Man looking out at a beautiful sunset; eye-level; Single Persons; vast, open field with golden light; cinematic
Characteristic
Shot : A man stands in a field of flowers at sunset, looking off into the distance. The light is soft and warm, creating a peaceful atmosphere.
Aesthetic Score : 0.75
Mood : peaceful, contemplative, serene
Quality
Entropy : 6.64
Noise : 94
Prompt Clip Score : 0.22
AI Evaluation
Likelihood of AI : 0.20
Image errors : No visible image errors or artifacts
Doctor’s Concerned Expression Reflects the Gravity of the Situation
A doctor, clad in a blue surgical gown and face mask, leans over a male patient lying in a hospital bed. The doctor’s serious expression and the patient’s vulnerable position create a palpable sense of tension and empathy, highlighting the gravity of the medical situation.
Prompt
facial-expressions Gratitude: Hope, gratitude for the doctor’s care ; Doctor comforting a patient; medium shot; Heroes; sterile hospital room with medical equipment; cinematic
Characteristic
Shot : A doctor is talking to a patient in a hospital bed. The patient is lying in the bed and the doctor is standing beside him.
Aesthetic Score : 0.5
Mood : serious, concerned, somber
Quality
Entropy : 6.91
Noise : 99
Prompt Clip Score : 0.22
AI Evaluation
Likelihood of AI : 0.10
Image errors : The image appears to be slightly grainy. The lighting is a little flat.
Friends, Laughter, and a Perfect Picnic
Capture the joy of friendship with this heartwarming image of three friends enjoying a sunny picnic. The warm colors, soft focus, and genuine smiles create a sense of carefree happiness and a perfect moment to cherish.
Prompt
facial-expressions Gratitude: Joy, gratitude for friendship and good times ; Group of friends laughing together at a picnic; eye-level; Normal People; sunny park with green grass and trees; cinematic
Characteristic
Shot : Three friends are sitting outdoors, laughing, in a field with a basket of fruit in the foreground.
Aesthetic Score : 0.7
Mood : joyful, happy, carefree
Quality
Entropy : 6.95
Noise : 102
Prompt Clip Score : 0.23
AI Evaluation
Likelihood of AI : 0.20
Image errors : No significant errors. The image is well-lit and there are no obvious artifacts or distortions.
Champions in the Spotlight: Two Gamers Face the Crowd
The energy is palpable as two young men, bathed in blue light, take center stage before a roaring crowd. Their focus is unwavering, their controllers gripped tight, as they prepare for the ultimate gaming showdown. The blur of the cheering fans in the background only amplifies the intensity of the moment.
Prompt
facial-expressions Gratitude: Pride, gratitude for recognition and hard work ; Gamer receiving an award for their achievements; close-up; Gamer; stage with a crowd and flashing lights; cinematic
Characteristic
Shot : Two young men are seated in front of a large crowd, holding a gaming controller. They are participating in an esports event. The background is dark with spotlights shining on the stage.
Aesthetic Score : 0.6
Mood : intense, excited, competitive
Quality
Entropy : 6.53
Noise : 97
Prompt Clip Score : 0.25
AI Evaluation
Likelihood of AI : 0.10
Image errors : Some slight noise in the background and slight banding in the blue light effect.
Lost in the Pages: A Moment of Tranquility in the Library
A young woman finds solace in a book, bathed in the warm glow of natural light streaming through a window. The peaceful atmosphere of the library, filled with towering bookshelves, creates a serene and contemplative mood. The soft lighting highlights her focused expression, capturing a moment of quiet reflection.
Prompt
facial-expressions Gratitude: Peace, gratitude for knowledge and escape ; Woman reading a book in a quiet library; eye-level; Single Persons; peaceful library with bookshelves and natural light; cinematic
Characteristic
Shot : A woman is reading a book in a library, standing in front of a bookshelf.
Aesthetic Score : 0.7
Mood : calm, focused, thoughtful
Quality
Entropy : 6.82
Noise : 101
Prompt Clip Score : 0.21
AI Evaluation
Likelihood of AI : 0.30
Image errors : The image has slight noise and graininess, possibly due to compression or low-light conditions.
Beach Cleanup Brings Smiles and a Sense of Community
A woman finds joy in picking up trash on a beautiful beach, inspiring others to join in the effort. This heartwarming scene highlights the positive impact of environmental responsibility and the power of community action.
Prompt
facial-expressions Gratitude: Satisfaction, gratitude for making a difference ; Volunteer helping to clean up a beach; wide shot; Heroes; beautiful beach with clear water and blue sky; cinematic
Characteristic
Shot : A woman is crouching on a beach, picking up trash with yellow gloves. There is a yellow and red basket in front of her. Behind her are palm trees and the ocean.
Aesthetic Score : 0.6
Mood : positive, happy, active
Quality
Entropy : 6.82
Noise : 100
Prompt Clip Score : 0.21
AI Evaluation
Likelihood of AI : 0.10
Image errors : No noticeable artifacts or errors in the image.
Conclusion
The results show that the generative AI model performed well in understanding the camera position and shot composition, 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 generated image didn’t accurately reflect the camera position described in the prompt.
- Shot Analysis: The model scored 0.53, which is considered good. This indicates that the model was able to understand the scene and create a shot that was relatively close to what was described in the prompt.
- Aesthetic Analysis: The model scored 0.12, which is considered very good. This means that the generated image’s aesthetic was very close to the expected aesthetic, despite the issues with camera position and shot composition.
Overall, the model seems to be better at understanding the scene and creating a visually appealing image than accurately capturing the intended camera position.
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://leonardo.ai