AI Captures Emotion, But Struggles with Camera Angles with Freepik
- 9 minutes read - 1856 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 quiet sadness of a lone figure, these expressions can draw viewers in and create a powerful connection. This blog post explores how a generative AI model captures these expressions, analyzing its strengths and weaknesses in creating images that evoke specific emotions and aesthetics.
Created with: freepik
Lost in the Shadows: A Melancholy Night
A young man, cloaked in darkness, stands alone on a rain-slicked street. The city lights cast long shadows, highlighting his isolation and creating a mood of quiet melancholy. The dramatic interplay of light and shadow evokes a sense of loneliness and introspection.
Prompt
facial-expressions Guilt: Desolate, regretful ; A lone figure; eye-level; Single Person; Empty street at night, rain falling; cinematic
Characteristic
Shot : A man in a black coat stands on a wet street at night. The street is lit by streetlights and the rain is falling.
Aesthetic Score : 0.7
Mood : melancholy, mysterious, lonely
Quality
Entropy : 6.82
Noise : 64
Prompt Clip Score : 0.23
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image is slightly blurry, possibly due to rain droplets on the lens.
Hope Rises from the Ashes: Superhero Stands Tall Amidst City’s Ruin
A powerful image captures the aftermath of disaster, with a superhero in a red cape standing defiantly on a rooftop, overlooking a smoke-filled cityscape. The dramatic lighting and the hero’s posture evoke a sense of hope and resilience amidst the destruction.
Prompt
facial-expressions Guilt: Heavy, burdened, conflicted ; A superhero, cape billowing in the wind; medium shot; Hero; City skyline, destroyed buildings in the background; cinematic
Characteristic
Shot : A lone Superman stands on a rooftop overlooking a city skyline, with a large cloud of smoke behind him. The city appears to be in ruins, with debris visible in the foreground.
Aesthetic Score : 0.7
Mood : dramatic, heroic, epic
Quality
Entropy : 6.73
Noise : 45
Prompt Clip Score : 0.28
AI Evaluation
Likelihood of AI : 0.70
Image errors : No obvious artifacts or errors
A Moment in Time: A Woman Reflects on Her Past
A woman stands in a familiar kitchen, holding a photograph of her younger self. The image captures a moment of nostalgia, as she gazes at her past self, dressed in a plaid shirt and apron, engaged in the simple act of cooking. The scene evokes a sense of melancholy and thoughtfulness, leaving the viewer to ponder the woman’s reflections and the passage of time.
Prompt
facial-expressions Guilt: 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 woman in a blue shirt is holding a photo of another woman in a kitchen. The photo is being held over a kitchen sink, with a tray of waffles in the background.
Aesthetic Score : 0.6
Mood : melancholy, pensive, reflective
Quality
Entropy : 6.87
Noise : 54
Prompt Clip Score : 0.30
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image has some minor artifacts, such as the slight blurring around the edges of the photo. The lighting is also a little bit flat and the shadows are not very defined.
The Hacker’s Focus
A young man sits intently at his desk, illuminated by the green glow of his monitor. The blurred background hints at a world of data and code, while the pizza slice and box suggest a late night of work. His serious expression and the dramatic lighting create a sense of mystery and intrigue.
Prompt
facial-expressions Guilt: 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 young man sitting at a desk with a computer and two pizzas in front of him. He looks tired and bored, possibly from playing video games for a long time.
Aesthetic Score : 0.6
Mood : melancholy, bored, tired
Quality
Entropy : 6.66
Noise : 48
Prompt Clip Score : 0.35
AI Evaluation
Likelihood of AI : 0.10
Image errors : The image is slightly grainy, which could be caused by low light or the camera settings. The focus is also not perfectly sharp.
A Moment of Shared Joy in the Crowd
A man stands amidst a sea of faces, all gazing upwards with laughter and shared delight. The warm glow of the lights in the background adds a cinematic touch, capturing a moment of pure joy and hope.
Prompt
facial-expressions Guilt: 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 light-colored shirt stands in the middle of a crowd of people, looking up with a wide smile and open mouth. The crowd is blurred in the background.
Aesthetic Score : 0.7
Mood : joyful, positive, celebratory
Quality
Entropy : 6.83
Noise : 56
Prompt Clip Score : 0.20
AI Evaluation
Likelihood of AI : 0.10
Image errors : Slight blurriness in the background and some noise in the shadows.
Unwavering in the Face of Chaos
A lone soldier stands defiant amidst the fiery ruins of a city, his stoic expression a testament to his unwavering resolve. The dramatic contrast between his calm and the burning cityscape creates a powerful image of heroism and resilience.
Prompt
facial-expressions Guilt: Torn, conflicted, remorseful ; A hero, standing over a fallen villain; medium shot; Hero; A battlefield, smoke and debris everywhere; cinematic
Characteristic
Shot : A man in a military uniform stands in the middle of a war-torn landscape, with burning buildings and debris in the background. He is looking directly at the camera with a serious expression.
Aesthetic Score : 0.7
Mood : dramatic, intense, somber
Quality
Entropy : 6.80
Noise : 56
Prompt Clip Score : 0.24
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image has a slight amount of noise, especially in the shadows.
A Gathering of Secrets: What Lies Beyond the Frame?
A dimly lit room, a table laden with food, and a group of people whose gazes are fixed on something unseen. The atmosphere is thick with mystery and tension, leaving the viewer to wonder what secrets are being shared or what danger lurks just outside the frame.
Prompt
facial-expressions Guilt: 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 group of four people are seated around a dining table in a dimly lit room, seemingly in a tense or uncomfortable situation. The table is set with plates and glasses, and there is a lit candle in the center.
Aesthetic Score : 0.7
Mood : tense, suspenseful, uncomfortable
Quality
Entropy : 6.76
Noise : 51
Prompt Clip Score : 0.27
AI Evaluation
Likelihood of AI : 0.10
Image errors : No significant errors detected.
The Gamer’s Focus: A Moment of Intense Concentration
A young man sits engrossed in a dimly lit room, his gaze fixed on the TV screen. The cluttered table and shelves filled with soda cans hint at a casual, focused atmosphere. The lighting and his intense expression create a sense of anticipation, suggesting a moment of high stakes in the game.
Prompt
facial-expressions Guilt: 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 young man sits at a table with gaming controllers in front of him, surrounded by gaming memorabilia and snacks.
Aesthetic Score : 0.6
Mood : casual, focused, determined
Quality
Entropy : 6.64
Noise : 58
Prompt Clip Score : 0.30
AI Evaluation
Likelihood of AI : 0.10
Image errors : The image appears to be slightly underexposed, especially in the shadows.
Lost in the City Lights
A young woman walks through a bustling city street, her gaze lost in thought. The shallow depth of field and the soft glow of the streetlights create a melancholic and contemplative mood, highlighting the solitude of the urban landscape.
Prompt
facial-expressions Guilt: 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 young woman walks down a city street at night, looking directly at the camera with a serious expression. The street is lined with buildings and stores, and there are lights and people in the background.
Aesthetic Score : 0.7
Mood : melancholy, pensive, urban
Quality
Entropy : 6.86
Noise : 56
Prompt Clip Score : 0.25
AI Evaluation
Likelihood of AI : 0.20
Image errors : Minor noise in the background, especially on the buildings.
Lost in the City Lights: A Moment of Melancholy on the Rooftop
A young man stands silhouetted against the vibrant cityscape, bathed in the soft glow of the moon. His solitary figure evokes a sense of contemplation and loneliness, highlighting the vastness of the urban landscape.
Prompt
facial-expressions Guilt: 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 young man stands on a rooftop overlooking a city skyline at night. The city lights are visible in the distance, and the moon is visible in the sky.
Aesthetic Score : 0.7
Mood : lonely, contemplative, urban
Quality
Entropy : 6.59
Noise : 39
Prompt Clip Score : 0.24
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image has some minor artifacts in the background, especially around the edges of buildings. The overall sharpness is good, but there could be more details in the scene.
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 0.6, 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 0.08, which is considered very good. This means that the generated image closely matched the expected aesthetic style.
Overall, the model demonstrated a good understanding of the scene and its aesthetic, but struggled with 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://www.freepik.com