AI Captures Emotions, But Struggles with Camera Angles with Stability-ai-ultra
- 9 minutes read - 1893 wordsTable of Contents
Dramatic facial expressions are a powerful tool in storytelling, conveying a wide range of emotions and adding depth to characters. From the intense focus of a gamer to the triumphant joy of a hero, these expressions can draw viewers in and create a lasting impact. This blog post explores the use of dramatic facial expressions in AI-generated images, examining how well a generative AI model can capture these nuances and create compelling visuals.
Created with: stability-ai-ultra
Two Friends Sharing a Moment of Joy in the City
A vibrant scene captures two women radiating happiness as they pose for a photo in a bustling city setting. The woman in focus, adorned with a colorful scarf and a bright blue jacket, beams with a contagious smile. Her friend, with shorter brown hair and a matching blue jacket, adds to the cheerful atmosphere. The image exudes positivity and warmth, showcasing the joy of friendship amidst the urban backdrop.
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 : Two women are standing in a bustling city street, one in the foreground looking directly at the camera and smiling broadly, and the other blurred behind her.
Aesthetic Score : 0.8
Mood : joyful, energetic, positive
Quality
Entropy : 6.91
Noise : 82
Prompt Clip Score : 0.22
AI Evaluation
Likelihood of AI : 0.20
Image errors : Slight chromatic aberration on the edges of the image. There’s a hint of noise in the background.
Silhouetted Serenity: A Lone Figure Contemplates the Sunset
A solitary figure stands on a mountain peak, their silhouette stark against the vibrant hues of a setting sun. The scene evokes a sense of peace and contemplation, with the vastness of the landscape emphasizing the figure’s isolation and the majesty of nature.
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 figure stands on a mountain peak at sunset, overlooking a vast mountain range. The sky is ablaze with vibrant orange and purple hues, and the silhouette of the figure is stark against the glowing horizon.
Aesthetic Score : 0.8
Mood : epic, majestic, contemplative
Quality
Entropy : 6.72
Noise : 89
Prompt Clip Score : 0.25
AI Evaluation
Likelihood of AI : 0.70
Image errors : The image has a slight oversaturation and overly smooth transitions in the gradient of the sky. The figure’s silhouette is slightly pixelated.
Laughter and Light: Friends Share a Joyful Meal Outdoors
A group of friends gather for a meal under the open sky, their laughter and conversation filling the air. The warm lighting and natural setting create a sense of warmth and happiness, capturing a moment of joy and connection.
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 : Group of friends laughing and enjoying a meal outdoors at a picnic table with a red and white checkered tablecloth.
Aesthetic Score : 0.7
Mood : happy, joyful, friendly
Quality
Entropy : 6.95
Noise : 77
Prompt Clip Score : 0.27
AI Evaluation
Likelihood of AI : 0.10
Image errors : The image quality is good with minor noise in the background, however, there are some minor artifacts around the edges of the subjects, which may be due to compression.
Caught in the Moment: Excitement and Surprise in a Flash of Blue and Orange
A close-up shot captures a man’s face, illuminated by vibrant blue and orange lighting. Headphones and glasses frame his eyes, which widen in surprise and excitement. The exaggerated expression and dynamic lighting create a powerful sense of energy and anticipation.
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 man with headphones and glasses is looking at the camera with a surprised and excited expression. The lighting is colorful with blue and orange tones.
Aesthetic Score : 0.4
Mood : excitement, surprise, joy
Quality
Entropy : 6.84
Noise : 80
Prompt Clip Score : 0.27
AI Evaluation
Likelihood of AI : 0.10
Image errors : The image has some slight noise and compression artifacts.
Golden Hour Serenity: A Moment of Joy and Freedom
Experience the enchanting scene of a woman standing in a field of daisies, her long brown hair flowing in the wind. Dressed in a white dress, she basks in the warm glow of the setting sun, exuding a carefree and romantic mood. The golden light creates a captivating atmosphere, highlighting her happiness and the beauty of the surrounding nature.
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 woman in a white dress with long brown hair is standing in a field of daisies. The sun is setting in the background, creating a warm, golden glow.
Aesthetic Score : 0.8
Mood : happy, carefree, romantic
Quality
Entropy : 6.63
Noise : 85
Prompt Clip Score : 0.26
AI Evaluation
Likelihood of AI : 0.20
Image errors : No visible artifacts or errors. However, the image appears slightly over-sharpened. Some of the colors are also slightly oversaturated, particularly in the background.
Hero’s Promise: A Moment of Hope and Protection
A close-up shot captures the intense connection between a superhero and a young child. The hero’s serious expression and protective stance convey a sense of responsibility and hope, leaving viewers with a powerful message of courage and resilience.
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 close-up shot of a superhero in a blue and red costume, looking intently at a young child. The superhero is wearing a mask that covers most of his face, and the child is looking up at him with wide eyes.
Aesthetic Score : 0.7
Mood : intense, protective, hopeful
Quality
Entropy : 6.74
Noise : 100
Prompt Clip Score : 0.28
AI Evaluation
Likelihood of AI : 0.80
Image errors : The image appears to have some slight blurriness and artifacts in the superhero’s costume.
Cozy Cabin Gathering: Friends, Fire, and Festive Cheer
A group of friends gather around a crackling fireplace in a cozy cabin, their laughter filling the air. The warm glow of the fire contrasts with the snowy landscape outside, creating a scene of warmth and joy. This image captures the essence of a festive gathering, filled with laughter and good company.
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 group of friends gathered around a fireplace, laughing and enjoying drinks. The scene is warm and inviting, suggesting a cozy winter evening.
Aesthetic Score : 0.7
Mood : joyful, cozy, celebratory
Quality
Entropy : 6.69
Noise : 82
Prompt Clip Score : 0.23
AI Evaluation
Likelihood of AI : 0.80
Image errors : Some minor artifacts are visible around the edges of the characters and the fire.
The Intensity of the Game
A close-up shot captures the focused determination on a man’s face as he plays a video game. The lighting and focus draw the viewer into the moment, highlighting the intensity of his concentration.
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 playing a video game, with his face illuminated by colorful lights, in a darkened room.
Aesthetic Score : 0.7
Mood : intense, focused, energetic
Quality
Entropy : 6.85
Noise : 79
Prompt Clip Score : 0.26
AI Evaluation
Likelihood of AI : 0.20
Image errors : No noticeable errors, but the background lights appear a bit artificial, like they are added digitally.
Sun-Kissed Happiness: A Moment of Joy in the Park
A man basks in the warm glow of the sun, his smile radiating contentment as he sits on a park bench. The blurred figures in the background add a sense of peaceful solitude, capturing a moment of pure happiness.
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 is sitting on a bench in a park, smiling and looking off into the distance. The sun is setting in the background, casting a warm glow over the scene.
Aesthetic Score : 0.8
Mood : joyful, serene, content
Quality
Entropy : 6.95
Noise : 81
Prompt Clip Score : 0.21
AI Evaluation
Likelihood of AI : 0.20
Image errors : There are no noticeable artifacts or errors in the image.
Superman Soars Amidst a Sea of Cheers
A close-up of Superman, radiating confidence in his iconic suit, stands before a jubilant crowd. The scene is ablaze with red flags and fiery flares, creating a dynamic and hopeful atmosphere. This image captures the essence of Superman’s heroism and the energy of his unwavering spirit.
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 : Superman, looking happy, walking through a crowd of cheering people, possibly after winning a battle or a sporting event. There is a lot of red and yellow in the scene.
Aesthetic Score : 0.6
Mood : excitement, heroism, victory
Quality
Entropy : 6.75
Noise : 82
Prompt Clip Score : 0.21
AI Evaluation
Likelihood of AI : 0.70
Image errors : The crowd appears somewhat unrealistic, with some faces looking odd and lacking detail. The flames are also very stylized and do not look natural. Some parts of the image, particularly the crowd, appear to be poorly rendered, with some textures and details appearing blurry or uneven.
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 0.3, 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 0.565, 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 its aesthetic, but needs improvement in 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://stability.ai