AI's Struggle with Noir: Capturing the Gritty Aesthetic with Imagen-v2
- 9 minutes read - 1850 wordsTable of Contents
Film noir, with its stark contrasts, shadowy figures, and gritty realism, has captivated audiences for decades. Its distinctive aesthetic, often characterized by low-key lighting, dramatic angles, and a sense of urban decay, has become synonymous with crime, mystery, and intrigue. But can AI truly capture the essence of this iconic style? This blog post explores the challenges and successes of using AI to generate images with a film noir aesthetic, examining how well it can translate the key elements of this genre into visual form. We’ll look at examples of AI-generated images, analyzing their strengths and weaknesses in capturing the mood, atmosphere, and visual language of film noir.
Created with: imagen-v2
Lost in the Neon Shadows
A solitary figure, shrouded in mystery, navigates the rain-slicked streets of a neon-drenched city. The play of light and shadow creates a dramatic atmosphere, hinting at secrets lurking in the darkness.
Prompt
Film noir: Gritty, determined, melancholic ; A lone detective; medium shot; Heroism; A dimly lit alleyway with rain pouring down, neon signs reflecting in puddles.; cinematic
Characteristic
Shot : A man in a trench coat and fedora walks through a rainy city alleyway. The alley is lit by neon signs and reflections of the city lights on the wet pavement.
Aesthetic Score : 0.75
Mood : dark, mysterious, noir
Quality
Entropy : 6.72
Noise : 103
Prompt Clip Score : 0.32
AI Evaluation
Likelihood of AI : 0.90
Image errors : The image has a bit of noise and blurriness in the background.
Lost in the Shadows: A Mysterious Stroll Down a Wet Street
A lone figure walks through a dimly lit, rain-soaked street, their shadow stretching long in front of them. The scene is filled with mystery and intrigue, inviting you to explore the secrets hidden within the shadows.
Prompt
Film noir: Suspenseful, mysterious, thrilling ; A shadowy figure escaping through a maze of narrow streets; long shot; Adventure; A bustling night market with flickering lanterns and crowded stalls.; cinematic
Characteristic
Shot : A lone figure in a long coat walks through a dimly lit, narrow alleyway lined with lanterns and stalls, suggesting a marketplace.
Aesthetic Score : 0.7
Mood : mysterious, atmospheric, lonely
Quality
Entropy : 6.53
Noise : 106
Prompt Clip Score : 0.27
AI Evaluation
Likelihood of AI : 0.90
Image errors : The image exhibits a somewhat painterly style, which might be deliberate, but adds a slight blurriness to the edges and some artifacts in the shadows and lights. The figure’s head and hat are disproportionately small.
A Handful of Mystery: Ace of Spades and a Heart in the Shadows
A close-up shot reveals a hand holding two cards, an ace of spades and a heart, against a dark backdrop. The scene evokes a sense of mystery and suspense, hinting at a high-stakes game or a clandestine encounter. The darkness and the close-up framing create a dramatic effect, leaving the viewer to wonder what secrets these cards hold.
Prompt
Film noir: Intense, suspenseful, dangerous ; A gambler’s hand holding a pair of aces; close-up; Gaming; A smoky, dimly lit casino with flashing lights and the sound of slot machines.; cinematic
Characteristic
Shot : A hand holding two playing cards, an ace of spades and a queen of hearts, in front of a dark background.
Aesthetic Score : 0.6
Mood : mysterious, suspenseful, gambling
Quality
Entropy : 5.30
Noise : 95
Prompt Clip Score : 0.27
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image has some noise and graininess, likely due to the dark lighting.
Lost in the Storm: A Lonely Drive Through a Desolate Landscape
A solitary car navigates a rain-slicked road, disappearing into the distance under a brooding, stormy sky. A faded motel sign offers a glimmer of hope in this melancholic and atmospheric scene, leaving viewers to ponder the driver’s journey and the secrets hidden within the desolate landscape.
Prompt
Film noir: Lonely, melancholic, atmospheric ; A vintage car speeding through a deserted highway; wide shot; Tourism; A desolate, rain-soaked landscape with a lone motel in the distance.; cinematic
Characteristic
Shot : A black car driving down a lonely highway in the desert, with a neon sign in the distance and a dark, ominous sky.
Aesthetic Score : 0.7
Mood : melancholy, lonely, atmospheric
Quality
Entropy : 6.69
Noise : 93
Prompt Clip Score : 0.31
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image has some minor artifacts, such as the blurry reflection of the car.
Melancholy in Monochrome: A Woman Gazes at the Rainy City
A solitary figure, silhouetted against a window, contemplates the rain-soaked cityscape. The stark black and white palette amplifies the mood of melancholy, while the woman’s vibrant red lips add a touch of intrigue. This image captures the essence of urban solitude, inviting viewers to delve into the mystery of her thoughts.
Prompt
Film noir: Nostalgic, melancholic, introspective ; A woman looking out of a train window at a passing cityscape; medium shot; Travel; A dark, rainy cityscape with towering buildings and flickering streetlights.; cinematic
Characteristic
Shot : A woman sits by a window, looking out at a rainy cityscape. The window is dirty and streaked with water.
Aesthetic Score : 0.6
Mood : melancholy, contemplative, introspective
Quality
Entropy : 6.15
Noise : 104
Prompt Clip Score : 0.38
AI Evaluation
Likelihood of AI : 0.30
Image errors : The windowpane is very dirty and streaked with water, which is distracting.
Whispers in the Shadows: A Moment of Shared Mystery
A dimly lit room, a group of figures huddled together, and a sense of unspoken tension. This evocative scene captures a moment of shared mystery, with the man in the hat at the center of attention. The lighting and composition create a sense of intimacy and drama, leaving the viewer to wonder what secrets are being shared.
Prompt
Film noir: Intimate, tense, claustrophobic ; A family huddled together in a dimly lit room; medium shot; Family; A cramped apartment with peeling paint and a flickering gas lamp.; cinematic
Characteristic
Shot : A family portrait of a woman, a man, and two children, posed in a dimly lit room with a vintage oil lamp in the foreground.
Aesthetic Score : 0.8
Mood : nostalgic, somber, intimate
Quality
Entropy : 6.49
Noise : 80
Prompt Clip Score : 0.30
AI Evaluation
Likelihood of AI : 0.10
Image errors : No notable artifacts or errors detected
Shadows and Secrets: A Noir Scene Unfolds
A man shrouded in mystery, cigarette smoke swirling in the air, stands in a dimly lit room bathed in the red glow of a neon sign. This evocative image captures the essence of noir, with its shadowy figures and sense of intrigue.
Prompt
Film noir: Mysterious, brooding, contemplative ; A detective’s silhouette against a window, cigarette smoke swirling around him; low-angle shot; Heroism; A rain-soaked city street with neon signs reflecting in the puddles.; cinematic
Characteristic
Shot : Silhouette of a man in a fedora smoking a cigarette, standing in front of a red and white neon sign.
Aesthetic Score : 0.7
Mood : mysterious, noir, shadowy
Quality
Entropy : 5.15
Noise : 100
Prompt Clip Score : 0.31
AI Evaluation
Likelihood of AI : 0.20
Image errors : Minor noise visible in the background. No noticeable artifacts.
A Hand Reaches Out from the Shadows
A close-up shot captures a hand extending towards the viewer in a dimly lit room, bathed in a single, mysterious light source. The low-key lighting and the outstretched hand create a palpable sense of suspense and intrigue, leaving the viewer wondering what lies beyond the darkness.
Prompt
Film noir: Suspenseful, unpredictable ; A close-up of a hand; extreme close-up; Adventure; A dark, smoky back alley with a flickering streetlight.; cinematic
Characteristic
Shot : A close-up of a hand reaching out from the darkness, illuminated by a soft light source.
Aesthetic Score : 0.6
Mood : mysterious, suspenseful, dramatic
Quality
Entropy : 6.02
Noise : 91
Prompt Clip Score : 0.28
AI Evaluation
Likelihood of AI : 0.20
Image errors : There are no visible errors in the image. However, the lighting could be more even and the hand could be sharper.
The Spin of Fate: A Roulette Wheel’s Suspenseful Dance
A close-up shot captures the heart-stopping moment as the roulette ball spins, its path uncertain. The dark, suspenseful mood amplifies the anticipation, leaving viewers on the edge of their seats as they await the final outcome.
Prompt
Film noir: Intense, suspenseful, unpredictable ; A roulette wheel spinning, the ball landing on a single number; close-up; Gaming; A dimly lit casino with the sound of chips clinking and people whispering.; cinematic
Characteristic
Shot : Close-up shot of a roulette wheel in a casino setting, the focus is on the wheel and the spinning ball, the background is out of focus.
Aesthetic Score : 0.7
Mood : dark, suspenseful, intense
Quality
Entropy : 5.61
Noise : 69
Prompt Clip Score : 0.30
AI Evaluation
Likelihood of AI : 0.20
Image errors : No visible errors
Lost in the Fog: A Solitary Figure Seeks the Lighthouse
A lone figure braves the stormy sea, walking towards a distant lighthouse on a long, fog-shrouded pier. The dramatic scene evokes a sense of mystery and isolation, leaving the viewer wondering what secrets lie ahead.
Prompt
Film noir: Lonely, melancholic, atmospheric ; A lone figure walking down a deserted pier, the ocean waves crashing against the pilings; long shot; Travel; A foggy, desolate coastline with a lighthouse in the distance.; cinematic
Characteristic
Shot : A lone figure walks towards a lighthouse on a pier in foggy weather. The waves crash against the pier’s wall, creating a sense of solitude and mystery.
Aesthetic Score : 0.7
Mood : solitary, melancholic, mysterious
Quality
Entropy : 6.64
Noise : 55
Prompt Clip Score : 0.32
AI Evaluation
Likelihood of AI : 0.10
Image errors : There are no visible artifacts or errors in the image.
Conclusion
The results show that the generative AI model performed well in understanding the scene and camera position, but struggled with the aesthetic. Here’s a breakdown:
- Camera Position: The model scored 0.44, which is slightly below average. This suggests that the model’s ability to accurately represent the camera position described in the prompt is not particularly strong.
- Shot Analysis: The model scored 0.56, which is considered good. This indicates that the model was able to understand the scene described in the prompt and create an image that reflects it reasonably well.
- Aesthetic Analysis: The model scored 0.33, which is significantly below average. This suggests that the generated image did not match the expected aesthetic style as closely as it could have.
Overall, the model shows promise in understanding the scene and camera position, but needs improvement in capturing the desired aesthetic.
Sources:
- https://heartofnoir.com/knowing-noir/aesthetic-of-noir/
- https://www.yellowbrick.co/blog/film/maximizing-the-visual-impact-unveiling-the-art-of-film-aesthetics
- https://www.questjournals.org/jrhss/papers/vol10-issue8/1008255260.pdf
- https://www.jstor.org/stable/3331672
- https://www.cinepoetics.fu-berlin.de/activities/workshops/2020-12-ws/index.html
- https://resource.download.wjec.co.uk/vtc/2016-17/16-17_1-22/eng/Part%201%20What%20is%20Aesthetics.pdf
- https://deepmind.google/technologies/imagen-2/