AI's Facial Expressions: A Step Forward, But Still Room for Growth with Dall-e-3
- 9 minutes read - 1747 wordsTable of Contents
Facial expressions are a powerful tool in storytelling, conveying emotions and adding depth to characters. In the realm of generative AI, the ability to accurately depict facial expressions is crucial for creating realistic and engaging images. This blog post examines the performance of a generative AI model in capturing facial expressions across various scenes, highlighting its strengths and weaknesses.
Created with: dall-e-3
Finding Serenity in the Everyday
A woman finds a moment of peace and tranquility at a cafe, lost in thought with a cup of coffee and a book. The soft lighting and her relaxed posture create a sense of calm and introspection.
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 sits at a table in a cafe, with her eyes closed and a cup of coffee in front of her.
Aesthetic Score : 0.7
Mood : calm, relaxed, contemplative
Quality
Entropy : 6.64
Noise : 88
Prompt Clip Score : 0.21
AI Evaluation
Likelihood of AI : 0.20
Image errors : There are no noticeable artifacts or errors in the image.
Heroic Firefighter Rescues Child From Blazing Inferno
A dramatic scene unfolds as a brave firefighter carries a child to safety from a raging fire. The intensity of the flames and the urgency in the firefighters’ expressions capture the harrowing reality 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 carrying a child out of a burning building.
Aesthetic Score : 0.7
Mood : dramatic, tense, heroic
Quality
Entropy : 6.72
Noise : 107
Prompt Clip Score : 0.30
AI Evaluation
Likelihood of AI : 0.30
Image errors : Minor blurring on the background. Some minor artifacts around the firefighter’s helmet.
Warm Family Gathering Captured in Intimate Setting
A heartwarming scene of a family enjoying a meal together, bathed in soft, inviting light. The cozy atmosphere and smiling faces evoke a sense of comfort and togetherness.
Prompt
facial-expressions Gratitude: Warmth, appreciation for family and connection ; Family having dinner together; eye-level; Normal People; warm, inviting kitchen; cinematic
Characteristic
Shot : A family is having dinner together at a wooden table. There are five people at the table. The food is on the table and there is a candle in the center.
Aesthetic Score : 0.7
Mood : warm, cozy, togetherness
Quality
Entropy : 6.76
Noise : 100
Prompt Clip Score : 0.21
AI Evaluation
Likelihood of AI : 0.10
Image errors : None
The Joy of Victory: Friends Celebrate a Gaming Triumph
Three friends, immersed in a thrilling video game, erupt in cheers and laughter. The dynamic scene, filled with flashing screens and raised controllers, captures the raw excitement and joy of shared gaming experiences.
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 : Three people are playing a video game and they are all excited and shouting. They are surrounded by screens and colorful lighting effects. The scene is very dynamic and energetic.
Aesthetic Score : 0.6
Mood : excited, intense, joyful
Quality
Entropy : 6.83
Noise : 119
Prompt Clip Score : 0.29
AI Evaluation
Likelihood of AI : 0.80
Image errors : The image appears to have some artifacts around the edges of the objects, specifically, the character in the rightmost screen, in addition to some blur.
Finding Peace in the Golden Hour
A man finds solace and connection in prayer as the sun sets, casting a warm glow over the field. The low angle and golden light create a sense of serenity and hope, capturing the essence of a spiritual 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 in traditional Middle Eastern clothing is praying in a field at sunset. The sun is setting in the background, casting a warm glow over the scene.
Aesthetic Score : 0.7
Mood : serene, peaceful, spiritual
Quality
Entropy : 6.57
Noise : 84
Prompt Clip Score : 0.20
AI Evaluation
Likelihood of AI : 0.20
Image errors : There are no noticeable artifacts or errors in the image.
Hope in the Face of Uncertainty: A Doctor and Patient Find Comfort in a Sterile Operating Room
A poignant image captures the raw emotions of a doctor and patient holding hands in an empty operating room. The stark setting amplifies the contrasting emotions of hope and somberness, creating a powerful and moving scene.
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 and a patient are holding hands in a hospital operating room. The room is clean and sterile, with medical equipment in the background.
Aesthetic Score : 0.6
Mood : tense, hopeful, dramatic
Quality
Entropy : 6.79
Noise : 114
Prompt Clip Score : 0.21
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image has some minor artifacts, such as a slight blur in the background. The image is also slightly overexposed, making the background a bit washed out.
Laughter in the Park: Friends Share a Joyful Moment
A sunny day, a picnic in the park, and a group of friends sharing laughter and good times. The low angle shot captures the joy of the moment, making the two men in the foreground seem larger than life as they share a hearty laugh.
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 : A group of friends are having a picnic in a park. They are all laughing and enjoying themselves. The sun is shining and the grass is green.
Aesthetic Score : 0.7
Mood : joyful, celebratory, carefree
Quality
Entropy : 6.46
Noise : 111
Prompt Clip Score : 0.28
AI Evaluation
Likelihood of AI : 0.20
Image errors : There are some minor artifacts in the image, such as the blurry background and the slightly out-of-focus subjects. There is also a slight color cast to the image, which may be due to the lighting.
Triumphant Smile Under the Spotlight
A woman with dark hair beams with joy as she basks in the cheers of a massive crowd. The spotlights illuminate her, creating a dramatic and hopeful atmosphere.
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 : A young woman is smiling at the camera, with a crowd cheering behind her. The scene is lit by spotlights, creating a sense of excitement and energy.
Aesthetic Score : 0.8
Mood : happy, triumphant, joyful
Quality
Entropy : 6.77
Noise : 99
Prompt Clip Score : 0.24
AI Evaluation
Likelihood of AI : 0.90
Image errors : The image appears to be digitally rendered. The woman’s skin is very smooth, and the lighting is unrealistic. There is also some slight blurring around the edges of the image.
Lost in the Glow: A Moment of Tranquility in the Library
A young woman finds solace in the pages of a book, bathed in the soft light that illuminates her face. The scene evokes a sense of serenity and contemplation, with the dramatic lighting highlighting the intimacy of her reading experience.
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 sitting in a library, reading a book. The light from the book illuminates her face and the surrounding area, creating a warm and inviting atmosphere.
Aesthetic Score : 0.75
Mood : serene, peaceful, contemplative
Quality
Entropy : 6.71
Noise : 94
Prompt Clip Score : 0.25
AI Evaluation
Likelihood of AI : 0.80
Image errors : The image has some minor artifacts, particularly in the shadows. The woman’s hand is slightly blurred.
Smiling Through the Plastic: A Powerful Message on the Beach
A young man walks on a beach littered with plastic, his smile a stark contrast to the environmental devastation. This image captures the hopefulness of tackling pollution, even amidst the stark reality of its impact.
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 man in blue gloves is cleaning up a beach, with a backdrop of a blue ocean and a sunset
Aesthetic Score : 0.6
Mood : hopeful, inspirational, uplifting
Quality
Entropy : 6.59
Noise : 102
Prompt Clip Score : 0.21
AI Evaluation
Likelihood of AI : 0.70
Image errors : The image appears to be digitally enhanced, with overly saturated colors and unnatural lighting. The textures of the sand and water are somewhat unrealistic.
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 0.38, which is below the “good” range of 0.5 to 0.75. This suggests that the model didn’t perfectly capture the intended camera position described in the prompt.
- Shot Analysis: The model scored 0.59, which falls within the “good” range. 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 0.07, which is far from the “very good” range of -0.2 to 0.1. This suggests that the generated image’s aesthetic deviated significantly from the expected aesthetic described in the prompt.
Overall, the model shows promise in understanding the scene and camera position, but needs improvement in capturing the desired 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://openai.com/index/dall-e-3/