AI Captures the Emotion, But Misses the Angle: A Look at Facial Expressions in AI-Generated Images with Midjourney
- 10 minutes read - 1922 wordsTable of Contents
Facial expressions are a powerful tool for conveying emotion and storytelling. In the realm of AI-generated imagery, the ability to capture these expressions realistically is crucial for creating compelling and engaging visuals. This blog post explores the capabilities of AI in generating images with dramatic facial expressions, examining how well these models understand the nuances of human emotion and the impact of camera positioning on the overall narrative.
Created with: midjourney
Lost in the Rain: A Silhouette of Solitude
A solitary figure stands shrouded in shadow under a streetlight, their form a stark contrast against the rain-slicked alleyway. The scene evokes a sense of melancholy and loneliness, with the dramatic use of light and shadow adding to the mystery and isolation.
Prompt
Guilt Downcast eyes, furrowed brow, slight trembling of lips: Desolate, regretful ; A lone figure; eye-level; Single Person; Empty street at night, rain falling; cinematic
Characteristic
Shot : A solitary figure stands under a streetlight on a rainy night, with a city street in the background
Aesthetic Score : 0.7
Mood : melancholy, lonely, somber
Quality
Entropy : 5.90
Noise : 114
Prompt Clip Score : 0.25
AI Evaluation
Likelihood of AI : 0.60
Image errors : The image appears to be slightly overexposed, with some of the highlights blown out. The rain streaks also appear slightly artificial.
Superman: A Hero Amidst the Ruins
A solitary Superman stands defiant on a rubble-strewn rooftop, his heroic pose a stark contrast to the ruined cityscape and somber sky. The image evokes a sense of loss and resilience, capturing the dramatic and melancholic mood of a world in need of a hero.
Prompt
Guilt Grimaced, eyes filled with sorrow, clenched jaw: Heavy, burdened, conflicted ; A superhero, cape billowing in the wind; medium shot; Hero; City skyline, destroyed buildings in the background; cinematic
Characteristic
Shot : Superman stands on a destroyed city rooftop, the cityscape behind him is obscured by fog and smoke, suggesting a post-apocalyptic setting
Aesthetic Score : 0.7
Mood : dark, dramatic, heroic
Quality
Entropy : 6.69
Noise : 89
Prompt Clip Score : 0.29
AI Evaluation
Likelihood of AI : 0.10
Image errors : The image is slightly blurry in places, particularly in the background
A Moment of Reflection in a Dimly Lit Kitchen
A young woman stands in a dimly lit kitchen, her gaze fixed on a framed picture. An empty plate rests in her hand, hinting at a meal left unfinished. The low light and her pensive expression create a sense of melancholy and longing, leaving the viewer to wonder about the story behind this solitary moment.
Prompt
Guilt Tears welling up, a faint smile, a look of longing: Nostalgic, melancholic ; A woman holding a photo of a loved one; close-up; Normal Person; A cluttered kitchen, dishes piled in the sink; cinematic
Characteristic
Shot : A young woman is standing in a kitchen, looking at a picture, holding a plate of food, with a lot of dirty dishes in the background
Aesthetic Score : 0.7
Mood : melancholy, contemplative, lonely
Quality
Entropy : 6.03
Noise : 81
Prompt Clip Score : 0.31
AI Evaluation
Likelihood of AI : 0.10
Image errors : The image has some noise and a slight artifact on the subject’s face.
White Eyes in the Red Light: A Glimpse into a Futuristic World
A man with unsettling white eyes stares intensely at the camera, bathed in a crimson glow. His focused gaze and the blurry background hint at a world of mystery and intrigue. Is he working, playing, or something else entirely? This image captures the intensity and futuristic feel of a world yet to be explored.
Prompt
Guilt Eyes wide with fear, a nervous twitch, a defeated sigh: Isolated, self-loathing ; A gamer, hunched over a computer screen; close-up; Gamer; Neon lights reflecting in their eyes, empty pizza boxes scattered around; cinematic
Characteristic
Shot : A man is sitting in front of a computer with red and blue lighting, looking directly at the viewer.
Aesthetic Score : 0.7
Mood : intense, futuristic, mysterious
Quality
Entropy : 6.13
Noise : 97
Prompt Clip Score : 0.28
AI Evaluation
Likelihood of AI : 0.90
Image errors : Some slight blurring and noise artifacts are present, especially on the man’s face.
Lost in the Shadows: A Moment of Solitude Amidst the Celebration
A man stands alone in a dimly lit room, his gaze cast downwards, a stark contrast to the dancing figures in the background. The image evokes a sense of melancholy and introspection, capturing a moment of quiet contemplation amidst the vibrant energy of the party.
Prompt
Guilt Blank stare, shoulders slumped, a sense of detachment: Alienated, invisible ; A man standing in a crowded room, looking lost; wide shot; Single Person; A party, people laughing and dancing, oblivious to him; cinematic
Characteristic
Shot : A man in a white shirt stands in the middle of a dance floor, looking down. People are dancing in the background. The lighting is dim and there is a lot of smoke or haze.
Aesthetic Score : 0.6
Mood : melancholy, lonely, introspective
Quality
Entropy : 6.52
Noise : 100
Prompt Clip Score : 0.23
AI Evaluation
Likelihood of AI : 0.10
Image errors : The image is a bit blurry, especially in the background.
A Shadow in the Dust: Mystery and Loss in a Desolate Landscape
A cloaked figure stands tall in a stark, black and white landscape, their presence casting a long shadow over a fallen figure. The image evokes a sense of mystery, isolation, and somber reflection, leaving the viewer to ponder the story behind this dramatic scene.
Prompt
Guilt Hesitant, a flicker of pain in their eyes, a heavy sigh: Torn, conflicted, remorseful ; A hero, standing over a fallen villain; medium shot; Hero; A battlefield, smoke and debris everywhere; cinematic
Characteristic
Shot : A hooded figure stands over a fallen figure in a desolate, mist-filled landscape. The figure’s cloak billows in the wind, while debris flies in the air.
Aesthetic Score : 0.7
Mood : dramatic, somber, mysterious
Quality
Entropy : 6.59
Noise : 102
Prompt Clip Score : 0.23
AI Evaluation
Likelihood of AI : 0.90
Image errors : The image appears to have been slightly overexposed, resulting in some areas of the image being blown out.
A Moment of Grace: Family Prayer Before a Meal
A serene and intimate scene of a family of five gathered around a table, heads bowed in prayer before a meal. The low lighting and their posture create a sense of quiet reverence and spirituality.
Prompt
Guilt Avoiding eye contact, forced smiles, fidgeting hands: Awkward, strained, unspoken ; A family gathered around a table, but the atmosphere is tense; medium shot; Normal People; A dimly lit dining room, empty chairs at the table; cinematic
Characteristic
Shot : A family of five is gathered around a table, heads bowed in prayer before a meal.
Aesthetic Score : 0.8
Mood : peaceful, reverent, heartwarming
Quality
Entropy : 5.27
Noise : 69
Prompt Clip Score : 0.25
AI Evaluation
Likelihood of AI : 0.80
Image errors : There are no significant errors in the image, but some minor imperfections in the rendering of the skin tones and hair could be addressed.
Lost in the Neon Glow: A Cyberpunk Gamer’s Sanctuary
A solitary figure, bathed in the flickering light of a screen, navigates a digital world. Empty spray paint cans litter the floor, hinting at a life lived on the edge. This gritty cyberpunk scene captures the intensity of gaming in a world where shadows hold secrets.
Prompt
Guilt Blank stare, a sense of emptiness, a defeated slump: Disillusioned, defeated, empty ; A gamer, staring at a blank screen, controller in hand; close-up; Gamer; A dimly lit room, empty energy drink cans scattered around; cinematic
Characteristic
Shot : A man in a dark room illuminated by blue and red lighting, sitting on the floor playing a video game
Aesthetic Score : 0.7
Mood : intense, mysterious, gritty
Quality
Entropy : 6.46
Noise : 103
Prompt Clip Score : 0.30
AI Evaluation
Likelihood of AI : 0.80
Image errors : There are some minor artifacts around the edges of the image, specifically the cans on the floor.
Lost in the City’s Blur
A solitary figure navigates the bustling urban landscape, the blur of passing crowds highlighting their isolation and contemplative mood. The image captures the feeling of being both surrounded and alone in the heart of the city.
Prompt
Guilt Head down, shoulders slumped, a sense of isolation: Lonely, isolated, rejected ; A woman walking away from a group of friends; long shot; Single Person; A bustling city street, people rushing by; cinematic
Characteristic
Shot : A woman is walking in the middle of a busy street in the city, all the people around her are blurred and she is in focus, the image is in black and white
Aesthetic Score : 0.6
Mood : solitude, urban, dramatic
Quality
Entropy : 5.73
Noise : 91
Prompt Clip Score : 0.23
AI Evaluation
Likelihood of AI : 0.30
Image errors : The image has a slight amount of grain and noise, which is likely due to the use of a high ISO setting. There is also a bit of blur around the edges of the image, which could be a result of camera shake or a lack of focus.
Silhouetted Solitude: A Moment of Melancholy in the Moonlight
A lone figure stands on a rooftop, their silhouette stark against the backdrop of a moonlit cityscape. The scene evokes a sense of melancholic mystery, with the mist-shrouded city adding to the atmospheric feel. The dramatic effect of the silhouette highlights the figure’s isolation, creating a poignant image of solitude.
Prompt
Guilt A look of determination, a hint of hope, a sense of resolve: Reflective, contemplative, seeking redemption ; A hero, standing on a rooftop, looking out at the city; wide shot; Hero; A cityscape bathed in moonlight, a sense of peace; cinematic
Characteristic
Shot : A lone figure stands on a rooftop overlooking a nighttime cityscape with a large moon in the sky.
Aesthetic Score : 0.75
Mood : mysterious, lonely, contemplative
Quality
Entropy : 6.02
Noise : 90
Prompt Clip Score : 0.19
AI Evaluation
Likelihood of AI : 0.80
Image errors : The image has some minor artifacts, such as a slight blurriness around the edges.
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 0.4, 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 0.59, 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 0.04, 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 shot composition, but needs improvement in accurately capturing the intended camera position. The aesthetic quality of the generated image is very good.
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