AI's Facial Expressions: A Mixed Bag of Success with Midjourney
- 9 minutes read - 1809 wordsTable of Contents
Facial expressions are a powerful tool in storytelling, conveying emotions and intentions without words. In the realm of generative AI, the ability to create images with nuanced facial expressions is a crucial step towards realistic and engaging content. This blog post explores the capabilities of a generative AI model in capturing facial expressions and shot composition, analyzing its performance across various scenarios. We’ll delve into the model’s strengths and weaknesses, highlighting its ability to understand camera angles and aesthetics while revealing areas for improvement in capturing intended camera positions. Through this analysis, we gain insights into the potential and limitations of AI in creating visually compelling and emotionally resonant imagery.
Created with: midjourney
A Moment of Quiet Reflection
A close-up portrait captures a young woman lost in thought, her eyes closed and gaze directed downwards. The soft lighting and her serene expression evoke a sense of melancholy and introspection, creating an intimate and vulnerable atmosphere.
Prompt
Attentiveness Attentive, slightly wistful: Melancholy, yet observant ; A lone figure; close-up; Single Person; cinematic
Characteristic
Shot : Close-up portrait of a woman with her eyes closed. She is wearing a black lace top and has a soft, dreamy look. The background is out of focus and has a soft, bluish hue.
Aesthetic Score : 0.7
Mood : melancholy, dreamy, soft
Quality
Entropy : 6.38
Noise : 91
Prompt Clip Score : 0.19
AI Evaluation
Likelihood of AI : 0.90
Image errors : The image has some oversharpening on the left side of the image, especially around the hairline. Also, there is a slight bluriness in the background.
Heroic Silhouette Against the City Lights
A superhero stands tall on a rooftop, their silhouette a stark contrast against the vibrant cityscape. The night sky is dark, emphasizing the dramatic mood and the hero’s contemplative stance. This image evokes a sense of heroism and power, leaving viewers wondering what challenges lie ahead.
Prompt
Attentiveness Focused, serious: Determined, vigilant ; A superhero standing on a rooftop, looking out over the city; eye-level; Hero; cityscape with twinkling lights; cinematic
Characteristic
Shot : A superhero figure stands on a rooftop overlooking a city skyline at night, with the Empire State Building visible in the distance.
Aesthetic Score : 0.6
Mood : dramatic, heroic, mysterious
Quality
Entropy : 6.14
Noise : 99
Prompt Clip Score : 0.31
AI Evaluation
Likelihood of AI : 0.30
Image errors : The image has a slight blur, particularly around the hero’s head. This might be due to camera shake or poor focus.
Lost in the Pages, Bathed in Golden Light
A woman finds solace in a book, the warm glow of the window illuminating her face as she escapes into a world of words. The scene evokes a sense of calm contemplation and introspective peace.
Prompt
Attentiveness Concentrated, peaceful: Focused, absorbed ; A woman reading a book on a train; eye-level; Normal Person; blurred passengers and train windows; cinematic
Characteristic
Shot : A young woman is reading a book on a train. The window is open and we can see the city passing by.
Aesthetic Score : 0.8
Mood : calm, contemplative, introspective
Quality
Entropy : 6.20
Noise : 109
Prompt Clip Score : 0.29
AI Evaluation
Likelihood of AI : 0.10
Image errors : The image is slightly blurry in the background.
The Code Whisperer: A Night of Focused Innovation
A young programmer, bathed in the blue and orange glow of his monitor, delves deep into a world of code. The image captures the intensity and solitude of late-night work, highlighting the power of technology to drive innovation.
Prompt
Attentiveness Intense, determined: Thrilled, competitive ; A gamer intensely focused on a screen, fingers flying across the keyboard; close-up; Gamer; dimly lit room with glowing monitor; cinematic
Characteristic
Shot : A young man is working on a computer in a dark room with blue lights. The screen of the computer is brightly lit and has a lot of code on it. The room looks like a server room.
Aesthetic Score : 0.6
Mood : intense, focused, futuristic
Quality
Entropy : 6.16
Noise : 74
Prompt Clip Score : 0.22
AI Evaluation
Likelihood of AI : 0.10
Image errors : There is some noise in the image, particularly in the shadows.
Lost in the City Lights
A solitary figure navigates the bustling urban landscape, shrouded in the soft glow of streetlights. The blurred background and muted colors evoke a sense of isolation and mystery, leaving the viewer to ponder the man’s journey and destination.
Prompt
Attentiveness Thoughtful, distant: Lost in thought, introspective ; A man crowded street; eye-level::2; Single Person; bustling city street with people and traffic; cinematic
Characteristic
Shot : A young man walking through a busy city street with a backpack, the background is blurred and lights are visible.
Aesthetic Score : 0.7
Mood : lonely, urban, pensive
Quality
Entropy : 5.57
Noise : 58
Prompt Clip Score : 0.25
AI Evaluation
Likelihood of AI : 0.20
Image errors : No obvious image errors are visible.
Lone Soldier Amidst the Inferno
A solitary figure in camouflage navigates a fiery battlefield, their silhouette a stark contrast against the chaos and smoke. The scene evokes a sense of grim intensity and dramatic isolation.
Prompt
Attentiveness Focused, determined: Brave, fearless ; A hero standing in the middle of a battle, eyes locked on the enemy; eye-level; Hero; chaotic battlefield with explosions and smoke; cinematic
Characteristic
Shot : A soldier in camouflage gear stands in a smoky, fiery landscape, likely a battlefield. The background is blurry and the soldier is the focus.
Aesthetic Score : 0.6
Mood : intense, dramatic, somber
Quality
Entropy : 6.54
Noise : 106
Prompt Clip Score : 0.27
AI Evaluation
Likelihood of AI : 0.70
Image errors : There are no apparent artifacts or errors in the image. The lighting and composition are well done, and the image appears to be clean and well-produced.
Intimate Moment: Young Girl and Mentor Share a Cozy Reading Session
In this heartwarming scene, a young girl is engrossed in a book while seated comfortably on a couch. An older woman, possibly a mentor or family member, watches on with interest, creating an intimate and contemplative atmosphere. The lighting highlights the focus on the girl and her book, emphasizing the importance of this shared reading experience.
Prompt
Attentiveness Intrigued, attentive: Curious, engaged ; A young girl listening intently to her grandmother tell a story; eye-level; Normal Person; cozy living room with warm lighting; cinematic
Characteristic
Shot : A young girl sits on a couch beside an older woman, both are looking at a book in the woman’s lap. The scene is lit by a lamp in the background and there is a cozy, intimate atmosphere.
Aesthetic Score : 0.7
Mood : cozy, intimate, warm
Quality
Entropy : 6.10
Noise : 97
Prompt Clip Score : 0.35
AI Evaluation
Likelihood of AI : 0.10
Image errors : There is a slight amount of noise in the shadows.
Gaming Victory: Captured in a Moment of Pure Joy
A young man, radiating pure excitement, throws his arm in the air after a triumphant gaming victory. The dramatic lighting highlights his infectious grin and the intensity of the moment, showcasing the raw emotion of a true gamer.
Prompt
Attentiveness Excited, elated: Joyful, triumphant ; A gamer celebrating a victory, eyes wide with excitement; close-up; Gamer; brightly lit room with cheering friends; cinematic
Characteristic
Shot : A young man is sitting in a gaming chair, wearing glasses, and excitedly raising his fist in the air. He is lit by neon pink and blue lights, creating a vibrant and dynamic atmosphere.
Aesthetic Score : 0.7
Mood : energetic, excited, playful
Quality
Entropy : 6.71
Noise : 96
Prompt Clip Score : 0.29
AI Evaluation
Likelihood of AI : 0.20
Image errors : No visible artifacts or errors.
Lost in Thought: A Moment of Contemplation in a Bustling Cafe
A young woman sits alone at a cafe table, her gaze fixed on something beyond the frame. The bustling activity around her fades into a blur, highlighting her isolation and introspective mood. A cup of coffee sits untouched, a silent witness to her pensive thoughts. This image captures a moment of quiet contemplation, leaving the viewer to wonder what secrets lie within her mind.
Prompt
Attentiveness Curious, thoughtful: Observant, introspective ; A woman sitting alone in a cafe, observing the people around her; eye-level; Single Person; bustling cafe with tables and chairs; cinematic
Characteristic
Shot : A woman sits alone at a cafe table, looking out of frame, with a cup of coffee in front of her. The cafe is busy, but out of focus, creating a sense of solitude.
Aesthetic Score : 0.7
Mood : pensive, melancholic, contemplative
Quality
Entropy : 6.17
Noise : 106
Prompt Clip Score : 0.26
AI Evaluation
Likelihood of AI : 0.20
Image errors : No visible image errors.
Superman, Alone in the Haze
A Superman figurine sits contemplatively on a rock, bathed in soft light against a hazy background. The scene evokes a sense of melancholy and isolation, highlighting the hero’s inner struggles.
Prompt
Attentiveness Serious, determined: Reflective, contemplative ; A hero looking down a cliff::0.5; close-up; Hero; clouds and sunlight; cinematic
Characteristic
Shot : Superman figure sitting on a rock with a cloudy, blurry background, likely representing a sunset or sunrise.
Aesthetic Score : 0.7
Mood : melancholy, contemplative, powerful
Quality
Entropy : 6.00
Noise : 90
Prompt Clip Score : 0.22
AI Evaluation
Likelihood of AI : 0.20
Image errors : The background appears slightly blurry, which may be due to the depth of field effect. The image also appears to have some noise, which is common in low-light photography.
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 0.25, 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 0.595, which is considered good. This indicates that the model was able to understand and translate the scene description from the prompt into a visually coherent shot.
- Aesthetic Analysis: The model scored 0.15, which is considered very good. This means that the generated image closely matched the expected aesthetic style described in the prompt.
Overall, the model demonstrates a good understanding of shot composition and a strong ability to achieve the desired aesthetic. However, it 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://midjourney.com