AI's Facial Expressions: A Mixed Bag with Stable-diffusion

Facial expressions are a powerful tool for conveying emotions and intentions. In the realm of generative AI, the ability to accurately depict these expressions is crucial for creating realistic and engaging images. This blog post delves into the performance of a generative AI model in capturing facial expressions across diverse scenes, analyzing its strengths and weaknesses in terms of camera position, shot composition, and aesthetic analysis.

Created with: stability-ai-core

Lost in the Neon Glow: A Woman’s Solitary Journey

A young woman walks through a city street at night, bathed in the vibrant hues of neon signs. The selective focus on her figure, blurred against the bustling background, evokes a sense of isolation and mystery. The evocative lighting and colors contribute to the lonely, urban, and enigmatic mood of the scene.

Prompt

facial-expressions Excitement: Thrilled, anticipation ; A lone figure; eye-level; Single Person; bustling city street at night; cinematic

Characteristic

Shot : A woman in a black coat walks down a city street at night, with blurry lights and people in the background.

Aesthetic Score : 0.7

Mood : mysterious, urban, introspective

Quality

Entropy : 6.23

Noise : 65

Prompt Clip Score : 0.23

AI Evaluation

Likelihood of AI : 0.20

Image errors : No significant errors

Heroic Flight at Sunset

Affiliate Links

Stable Diffusion XL Prompt Handbook

Create stunning AI art with this guide to Stable Diffusion XL prompts.

500+ AI Image Prompts

Over 500 Stable Diffusion and Midjourney prompts for creating AI art.

Stable Diffusion with Python

Master Stable Diffusion for AI image generation using Python. Control and customize your creations.

A superhero takes to the skies, silhouetted against a vibrant sunset over the city. The dramatic pose and lighting evoke a sense of power and action, leaving a hopeful feeling in its wake.

Prompt

facial-expressions Excitement: Triumphant, exhilarating ; A superhero in mid-air; low-angle; Hero; cityscape with a dramatic sunset; cinematic

Characteristic

Shot : A superhero in flight, against a backdrop of a city skyline at sunset.

Aesthetic Score : 0.6

Mood : dramatic, powerful, hopeful

Quality

Entropy : 6.89

Noise : 73

Prompt Clip Score : 0.28

AI Evaluation

Likelihood of AI : 0.90

Image errors : The image has some minor artifacts and blurriness, especially in the background and the cape.

Friends Run Through Park, Embracing Pure Joy

Five friends capture a moment of pure happiness as they run through a park, their laughter and smiles radiating carefree joy. The image evokes a sense of vibrancy and excitement, showcasing the beauty of shared moments with loved ones.

Prompt

facial-expressions Excitement: Joyful, carefree ; A group of friends laughing and running; eye-level; Normal People; a sunny park with a vibrant green lawn; cinematic

Characteristic

Shot : A group of young adults are running through a park, laughing and enjoying themselves. They are wearing casual clothing and appear to be having a good time.

Aesthetic Score : 0.7

Mood : joyful, carefree, friendly

Quality

Entropy : 6.84

Noise : 76

Prompt Clip Score : 0.27

AI Evaluation

Likelihood of AI : 0.10

Image errors : No visible artifacts or errors in the image.

The Focused Gaze of a Determined Mind

A young man, shrouded in shadow, sits before multiple monitors, his intense expression and low-key lighting creating a palpable sense of focus and determination. The scene evokes a feeling of intensity, hinting at a crucial moment in his pursuit of a challenging goal.

Prompt

facial-expressions Excitement: Intense, focused ; A gamer’s hands furiously tapping on a keyboard; close-up; Gamer; a dimly lit room with glowing screens; cinematic

Characteristic

Shot : A young man sits in front of a computer, focused intently on the screen, his expression tense and his hands poised over the keyboard. He appears to be playing a video game or engaged in a demanding task.

Aesthetic Score : 0.6

Mood : intense, focused, determined

Quality

Entropy : 6.04

Noise : 64

Prompt Clip Score : 0.28

AI Evaluation

Likelihood of AI : 0.20

Image errors : Some slight artifacts are visible in the shadows and highlights.

Solitude at Sunset’s Edge

A lone figure stands on a cliff, dwarfed by the vastness of the ocean and the breathtaking beauty of a dramatic sunset. This image evokes a sense of serenity, majesty, and contemplation, capturing the awe-inspiring scale of nature.

Prompt

facial-expressions Excitement: Awe-inspiring, liberating ; A woman standing on a cliff overlooking a vast ocean; eye-level; Single Person; dramatic clouds and a setting sun; cinematic

Characteristic

Shot : A lone figure stands on a clifftop overlooking a vast ocean at sunset. The sky is filled with dramatic clouds, and the sun is setting in a blaze of golden light.

Aesthetic Score : 0.8

Mood : serene, contemplative, dramatic

Quality

Entropy : 6.75

Noise : 79

Prompt Clip Score : 0.29

AI Evaluation

Likelihood of AI : 0.10

Image errors : No visible errors

Chaos Reigns: A Collage of Fantasy Warfare

Witness the intensity of a fantasy battle through this chaotic collage of nine images. Smoke, fire, and fierce warriors clash in a scene that captures the raw energy and violence of war.

Prompt

facial-expressions Excitement: Brave, adrenaline-fueled ; A hero charging into battle; low-angle; Hero; a chaotic battlefield with explosions and smoke; cinematic

Characteristic

Shot : A collage of 9 images depicting a battle scene, mostly featuring warriors with weapons and fiery explosions

Aesthetic Score : 0.6

Mood : intense, chaotic, heroic

Quality

Entropy : 6.90

Noise : 82

Prompt Clip Score : 0.28

AI Evaluation

Likelihood of AI : 0.70

Image errors : The image has some visible artifacts, particularly in the fire and the background, suggesting some level of AI manipulation.

Birthday Joy: A Celebration Filled with Laughter and Love

Capture the essence of a joyous birthday celebration with this heartwarming photo. A group of friends and family gather around a beautifully decorated cake, their smiles radiating happiness and the balloons adding a touch of festive cheer. The cozy living room setting creates an intimate atmosphere, making this a perfect snapshot of a special occasion.

Prompt

facial-expressions Excitement: Happy, celebratory ; A family celebrating a birthday; eye-level; Normal People; a brightly decorated living room with balloons and streamers; cinematic

Characteristic

Shot : A group of friends are celebrating a birthday. They are all smiling and laughing and there is a birthday cake in the center of the table. There are balloons in the background and the table is decorated with confetti.

Aesthetic Score : 0.7

Mood : joyful, celebratory, friendly

Quality

Entropy : 6.87

Noise : 76

Prompt Clip Score : 0.30

AI Evaluation

Likelihood of AI : 0.10

Image errors : There are no visible image errors or artifacts.

Lost in the Neon Glow: A Hacker’s Focus

A young man, eyes locked on a vibrant computer screen, is bathed in the dramatic glow of red and blue neon lights. His intense focus and the mysterious aura of the scene hint at a world of digital intrigue.

Prompt

facial-expressions Excitement: Engrossed, focused ; A gamer’s face illuminated by the screen; close-up; Gamer; a dark room with neon lights reflecting on the screen; cinematic

Characteristic

Shot : A young man wearing headphones in a dark room with colorful lights behind him.

Aesthetic Score : 0.7

Mood : mysterious, focused, intense

Quality

Entropy : 6.06

Noise : 61

Prompt Clip Score : 0.26

AI Evaluation

Likelihood of AI : 0.20

Image errors : There are no noticeable errors in the image.

Screaming with Delight: The Thrill of the Roller Coaster Ride

Capture the raw excitement of a roller coaster ride as a man screams with joy, his face a blur of exhilaration. The image evokes a sense of speed and thrill, capturing the essence of this exhilarating experience.

Prompt

facial-expressions Excitement: Thrilling, exhilarating ; A man riding a rollercoaster; POV shot; Single Person; a fast-paced ride with twists and turns; cinematic

Characteristic

Shot : A man is riding a roller coaster with a look of excitement and fear on his face. He’s shouting and his arms are outstretched. The background is blurry, but you can see the roller coaster track.

Aesthetic Score : 0.5

Mood : exciting, thrilling, adrenaline

Quality

Entropy : 6.80

Noise : 69

Prompt Clip Score : 0.30

AI Evaluation

Likelihood of AI : 0.20

Image errors : There are no visible artifacts or errors in the image.

Stormy Cityscape Reflects the Man’s Fury

A man, radiating anger, stands on a rooftop overlooking a city shrouded in dark clouds. The dramatic setting amplifies his intense emotions, creating a palpable sense of tension.

Prompt

facial-expressions Excitement: Victorious, powerful ; A hero standing triumphantly on a rooftop; high-angle; Hero; a cityscape with a dramatic storm in the background; cinematic

Characteristic

Shot : A man in a leather jacket stands on a rooftop, screaming into the sky with a city skyline behind him. The sky is dark and cloudy, giving the scene a dramatic feel.

Aesthetic Score : 0.7

Mood : dramatic, intense, powerful

Quality

Entropy : 6.87

Noise : 74

Prompt Clip Score : 0.24

AI Evaluation

Likelihood of AI : 0.20

Image errors : There is a slight blurriness in the image, particularly in the background, possibly due to a slight camera shake or post-processing.

Conclusion

The results show that the generative AI model performed well in terms of camera position and shot analysis, but struggled with aesthetic analysis.

Here’s a breakdown:

• Camera Position: The model scored 0.35, which is below the “good” range of 0.5 to 0.75. This suggests that the model didn’t fully capture the intended camera positions described in the prompt.
• Shot Analysis: The model scored 0.455, also below the “good” range. This indicates that the model didn’t fully understand the scene described in the prompt and didn’t create the expected shot composition.
• Aesthetic Analysis: The model scored 0.17, which is within the “very good” range of -0.2 to 0.1. This means the generated image’s aesthetic closely matched the expected aesthetic described in the prompt.

Overall, the model seems to be better at understanding the desired aesthetic than the camera positions and shot composition. This suggests that the model might need further training to improve its ability to interpret and translate camera positions and shot descriptions into visual representations.