AI's Facial Expressions: A Mixed Bag of Success with Midjourney
- 9 minutes read - 1780 wordsTable of Contents
Facial expressions are a powerful tool in storytelling, conveying emotions and adding depth to characters. Generative AI models are increasingly being used to create realistic and expressive faces, but how well do they capture the nuances of human emotion? This blog post explores the capabilities of AI in generating facial expressions, analyzing its performance across various scenes and highlighting its strengths and weaknesses.
Created with: midjourney
Lost in the Urban Labyrinth
A solitary figure contemplates the vastness of the city, dwarfed by towering buildings and an empty street. The overcast sky and sense of anonymity evoke a mood of solitude and quiet reflection.
Prompt
Interest Interest: Intrigued, observant ; A lone figure; eye-level; Single Person; bustling city street; cinematic
Characteristic
Shot : A city street scene, viewed from a high angle, looking down a long street lined with tall buildings. The street is busy with traffic and pedestrians. In the foreground, a lone man stands in the middle of the street, looking down the street. The painting is done in a realistic style, with a focus on light and shadow.
Aesthetic Score : 0.7
Mood : lonely, urban, contemplative
Quality
Entropy : 6.76
Noise : 120
Prompt Clip Score : 0.24
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image is slightly blurry, and the paint strokes are visible in some areas. This is a stylistic choice and may not be considered an error for some.
The Flash Races Against Time to Save the City
A burning building casts an ominous glow on the cityscape as the Flash, clad in his iconic red and gold suit, kneels with a determined expression. The scene is filled with intensity and drama, hinting at a desperate fight for survival.
Prompt
Interest Interest: Focused, determined ; A superhero in a dramatic pose; medium shot; Hero; cityscape with a burning building in the background; cinematic
Characteristic
Shot : A superhero, dressed in a red and gold suit, is crouched in an urban setting with a fire in the background.
Aesthetic Score : 0.7
Mood : intense, dramatic, powerful
Quality
Entropy : 6.62
Noise : 98
Prompt Clip Score : 0.27
AI Evaluation
Likelihood of AI : 0.70
Image errors : Some areas of the image appear to be slightly blurry, especially the fire in the background. There is also some noise present, particularly in the shadows.
Lost in the Pages: A Moment of Tranquility in a Cozy Cafe
A young woman finds solace in a dimly lit cafe, the warm glow of the window illuminating her face as she immerses herself in a book. The scene evokes a sense of cozy intimacy and pensive reflection, capturing a moment of peace and tranquility.
Prompt
Interest Interest: Engrossed, absorbed ; A woman reading a book in a coffee shop; eye-level; Normal People; warm, inviting cafe interior; cinematic
Characteristic
Shot : A young woman is sitting at a cafe table, reading a book. She is bathed in soft, natural light.
Aesthetic Score : 0.8
Mood : cozy, intimate, contemplative
Quality
Entropy : 6.68
Noise : 99
Prompt Clip Score : 0.29
AI Evaluation
Likelihood of AI : 0.10
Image errors : Some minor noise in the background, but it does not detract from the image.
Caught in the Moment: Intensity and Surprise in a Blue-Lit Scene
A young man, illuminated by a striking blue and yellow light, sits at his computer, headset on, his face a picture of surprise. The scene captures a moment of intense focus and unexpected excitement, leaving the viewer wondering what has just transpired.
Prompt
Interest Interest: Excited, concentrated ; A gamer intensely focused on a screen; close-up; Gamer; dimly lit room with glowing monitor; cinematic
Characteristic
Shot : A young man with headphones is sitting at a computer, looking surprised and with his mouth open. The background is dark, lit by blue light.
Aesthetic Score : 0.6
Mood : intense, shocked, excited
Quality
Entropy : 5.65
Noise : 84
Prompt Clip Score : 0.25
AI Evaluation
Likelihood of AI : 0.20
Image errors : No significant errors
Silhouetted Against the Storm
A solitary figure sits by a window, their silhouette stark against the backdrop of a stormy sky. The dark room and dramatic lighting evoke a sense of melancholy and isolation, hinting at a contemplative mood and a feeling of foreboding.
Prompt
Interest Interest: Contemplative, thoughtful ; A man gazing out a window at a stormy sky; eye-level; Single Person; dark, moody interior; cinematic
Characteristic
Shot : A man is silhouetted against a window, looking out at a stormy sky. The room is dimly lit and the curtains are drawn.
Aesthetic Score : 0.6
Mood : melancholy, contemplative, somber
Quality
Entropy : 5.05
Noise : 98
Prompt Clip Score : 0.30
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image is slightly overexposed and the colors are somewhat muted.
Silhouette of Power: A Lone Figure Contemplates the City’s Fate
A muscular, black-clad figure stands on a rooftop, their silhouette stark against the fiery sunset. The sprawling cityscape below stretches out, hinting at a future both hopeful and uncertain. This image evokes a sense of heroic determination, a lone warrior facing the unknown.
Prompt
Interest Interest: Confident, determined ; A hero standing on a rooftop overlooking a city; wide shot; Hero; panoramic cityscape with dramatic lighting; cinematic
Characteristic
Shot : A muscular, silhouetted figure stands on a rooftop overlooking a city at sunrise. The city stretches out in front of him, a dense mass of buildings. The sky is a soft, hazy blue, with wispy clouds.
Aesthetic Score : 0.6
Mood : epic, dramatic, hopeful
Quality
Entropy : 6.50
Noise : 100
Prompt Clip Score : 0.29
AI Evaluation
Likelihood of AI : 0.80
Image errors : The cityscape is slightly blurry, and there are some artifacts around the edges of the figure.
Laughter and Warmth: Friends Sharing a Joyful Meal
A group of friends gather around a table, their laughter filling the air. The warm lighting and cozy setting create a sense of intimacy and togetherness, capturing the joy of shared moments.
Prompt
Interest Interest: Happy, engaged ; A group of friends laughing together at a dinner table; eye-level; Normal People; cozy, homey dining room; cinematic
Characteristic
Shot : A group of friends are having dinner together at a table. The table is lit by a lamp hanging above, and there are many dishes of food on the table.
Aesthetic Score : 0.7
Mood : happy, cozy, casual
Quality
Entropy : 6.78
Noise : 91
Prompt Clip Score : 0.30
AI Evaluation
Likelihood of AI : 0.10
Image errors : No visible errors, good quality
The Blue and Orange Glow of Focus
A close-up shot captures the intensity of a gamer’s hand as it navigates a keyboard and mouse, bathed in a dramatic blue and orange lighting. The scene evokes a sense of focus and digital immersion.
Prompt
Interest Interest: Thrilled, focused ; A gamer’s hands rapidly moving across a keyboard and mouse; close-up; Gamer; brightly lit gaming setup with flashing lights; cinematic
Characteristic
Shot : A close-up shot of a hand using a mouse on a keyboard with colorful lighting, likely in a gaming setup.
Aesthetic Score : 0.5
Mood : intense, focused, digital
Quality
Entropy : 6.62
Noise : 106
Prompt Clip Score : 0.25
AI Evaluation
Likelihood of AI : 0.20
Image errors : There is some slight blurriness in the background, potentially due to motion blur or out-of-focus settings.
Lost in Art: A Moment of Contemplation
A woman, dressed in black, stands transfixed before a grand painting in an art gallery. The scene evokes a sense of tranquility and artistic contemplation, with the woman’s back to the camera emphasizing her focus on the artwork. The dark grey walls and rich brown wood floor create a sophisticated backdrop for this moment of quiet reflection.
Prompt
Interest Interest: Appreciative, curious ; A woman looking at a painting in a museum; eye-level; Single Person; grand museum hall with intricate artwork; cinematic
Characteristic
Shot : A woman in a black dress is standing in an art gallery, facing a large painting of a scene with many figures. The gallery has a dark gray wall and wooden floors. There is another painting to the left of the woman, and another to the right.
Aesthetic Score : 0.7
Mood : thoughtful, contemplative, artistic
Quality
Entropy : 6.61
Noise : 103
Prompt Clip Score : 0.28
AI Evaluation
Likelihood of AI : 0.10
Image errors : The image has no noticeable artifacts or errors.
Silhouette of Danger: A Moment of Intensity
A stark silhouette of a man firing a gun, smoke and sparks swirling around him, captures a moment of raw tension and danger. The dark, dramatic mood amplifies the intensity of the scene, leaving a lasting impression of the power and consequence of the action.
Prompt
Interest Interest: Intense, focused ; A hero facing off against a villain; medium shot; Hero; dramatic, action-packed scene with explosions and smoke; cinematic
Characteristic
Shot : A man in a dark jacket is firing a gun in a dimly lit room. There is smoke and light particles surrounding the gun and muzzle flash.
Aesthetic Score : 0.6
Mood : intense, action, suspenseful
Quality
Entropy : 6.37
Noise : 86
Prompt Clip Score : 0.24
AI Evaluation
Likelihood of AI : 0.80
Image errors : The smoke and light particles appear somewhat artificial and lack natural detail.
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 0.22, which is below the “good” range of 0.5 to 0.75. This suggests that the model didn’t accurately capture the intended camera position described in the prompt.
- Shot Analysis: The model scored 0.5, 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 0.17, which is slightly above the “very good” range of -0.2 to 0.1. This suggests that the generated image’s aesthetic deviated somewhat from the expected aesthetic described in the prompt.
Overall, the model demonstrated a good understanding of the scene and shot composition, but needs improvement in accurately capturing the intended camera position and achieving 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://midjourney.com