Steampunk Dreams: A Generative AI's Journey Through a Clockwork World with Imagen-v2
- 10 minutes read - 1985 wordsTable of Contents
The steampunk aesthetic, with its blend of Victorian-era technology and fantastical inventions, has captivated imaginations for decades. This unique style, characterized by intricate gears, steam-powered contraptions, and a sense of wonder, has found its way into literature, film, and even video games. In this blog post, we explore how a generative AI model interprets and recreates this captivating aesthetic, analyzing its strengths and limitations in capturing the essence of steampunk.
Created with: imagen-v2
Steampunk Adventurer Gazes Upon a City of Tomorrow
A mysterious figure in a steampunk helmet and goggles stands poised before a sprawling futuristic city, an airship hovering in the background. The dramatic lighting and intense gaze of the man evoke a sense of adventure and intrigue, hinting at a world of wonder and danger.
Prompt
Steampunk: Epic, determined ; A lone, determined airship pilot; close-up; Heroism; A sprawling cityscape with towering clockwork structures and smoke billowing from chimneys.; cinematic
Characteristic
Shot : A close-up portrait of a man in steampunk attire, with a blurry background of a futuristic city and an airship.
Aesthetic Score : 0.8
Mood : mysterious, futuristic, adventurous
Quality
Entropy : 6.69
Noise : 69
Prompt Clip Score : 0.32
AI Evaluation
Likelihood of AI : 0.80
Image errors : Some minor artifacts and blurriness around the edges of the image.
Lost in the Jungle of Wonder
A group of explorers venture through a dense, bioluminescent jungle, their path illuminated by glowing orbs. A colossal steampunk contraption looms in the background, shrouded in mystery. This fantastical scene evokes a sense of adventure and intrigue, leaving you wondering what secrets lie ahead.
Prompt
Steampunk: Intriguing, adventurous ; A group of adventurers navigating a treacherous jungle; wide shot; Adventure; Lush, overgrown jungle with ancient ruins and steam-powered contraptions.; cinematic
Characteristic
Shot : A group of four adventurers are walking through a dense jungle. There are large, metallic, and seemingly clockwork machines in the background, obscured by foliage. The scene is set in a steampunk world.
Aesthetic Score : 0.6
Mood : mysterious, adventurous, whimsical
Quality
Entropy : 6.98
Noise : 117
Prompt Clip Score : 0.35
AI Evaluation
Likelihood of AI : 0.70
Image errors : The image has some minor errors, like the fuzzy edges on the figures and some artifacts in the foliage, indicating a possible AI generated image.
Steampunk Dreams: A Hand Reaches for the Unknown
A close-up of a intricate steampunk automaton, crafted from brass and gears, is brought to life by a reaching hand. The blurred background, bathed in soft green hues and out-of-focus lights, adds a touch of mystery and intrigue to this futuristic scene.
Prompt
Steampunk: Intriguing, focused ; A player’s hand manipulating gears and levers on a complex automaton; close-up; Gaming; A dimly lit workshop filled with intricate machinery and glowing dials.; cinematic
Characteristic
Shot : A close-up of a steampunk-style clockwork automaton, possibly a robot or a machine, with a hand reaching towards it. It has intricate gears and mechanisms, and the lights in the background add to the mysterious and atmospheric setting.
Aesthetic Score : 0.7
Mood : mysterious, intricate, whimsical
Quality
Entropy : 6.85
Noise : 64
Prompt Clip Score : 0.31
AI Evaluation
Likelihood of AI : 0.80
Image errors : The image seems to be well-defined with no noticeable errors.
Where Steam Punk Meets Market Magic
A captivating scene unfolds beneath a towering steampunk clocktower, where bustling market life collides with intricate, imposing machinery. The juxtaposition of scale and activity creates a whimsical and visually striking fantasy world.
Prompt
Steampunk: Energetic, bustling ; A bustling marketplace filled with exotic goods and steam-powered vehicles; wide shot; Tourism; A vibrant, colorful marketplace with ornate clockwork contraptions and bustling crowds.; cinematic
Characteristic
Shot : A bustling steampunk marketplace beneath a large, intricate clockwork machine, with steam and smoke filling the air. There are many vendors and shoppers, as well as some carriages and other vehicles.
Aesthetic Score : 0.6
Mood : fantastical, crowded, busy
Quality
Entropy : 6.97
Noise : 112
Prompt Clip Score : 0.34
AI Evaluation
Likelihood of AI : 0.80
Image errors : The image has some artifacts and blurriness, particularly in the background. Some of the details are also a bit too fine and could be simplified.
Airship Soaring Above Majestic Peaks
An airship, dwarfed by towering snow-capped mountains, glides through a cloudy sunset sky. The vastness of the landscape and the airship’s delicate presence create a sense of epic adventure and dreamy wonder.
Prompt
Steampunk: Awe-inspiring, majestic ; A luxurious airship soaring over a breathtaking mountain range; wide shot; Travel; Majestic mountains with snow-capped peaks and a vast, cloudy sky.; cinematic
Characteristic
Shot : A steampunk-style airship flying over a snow-capped mountain range. The airship is made of gold and is flying over the valley
Aesthetic Score : 0.7
Mood : fantasy, adventurous, majestic
Quality
Entropy : 6.65
Noise : 84
Prompt Clip Score : 0.36
AI Evaluation
Likelihood of AI : 0.80
Image errors : The airship has some artifacts and looks a bit blurry, particularly around the edges. The mountains are quite pixelated. The sky has a blurry, slightly plastic effect.
Secrets Whispered in the Firelight
A trio gathers around a dimly lit table, their faces shrouded in shadow. The antique-filled room, warmed by a crackling fireplace, whispers of secrets and intrigue. What mysteries unfold in this cozy, yet mysterious setting?
Prompt
Steampunk: Warm, nostalgic ; A family gathered around a crackling fireplace, sharing stories and playing a board game; medium shot; Family; A cozy living room with plush furniture, antique clocks, and warm lighting.; cinematic
Characteristic
Shot : A cozy living room with a fireplace, a large clock on the wall, and three men seated around a table, seemingly playing a board game.
Aesthetic Score : 0.7
Mood : warm, inviting, mysterious
Quality
Entropy : 6.71
Noise : 93
Prompt Clip Score : 0.34
AI Evaluation
Likelihood of AI : 0.90
Image errors : There are some noticeable artifacts and blending issues in the image, particularly on the walls and the rug. The lighting appears a bit flat and lacks depth.
A Young Inventor’s Enchanting Workshop
A young boy, clad in goggles and a tie, meticulously constructs a complex metal contraption in a warm, steampunk workshop. The scene is filled with a sense of wonder and mystery, as the child’s intense focus draws you into his enchanting world of invention.
Prompt
Steampunk: Curious, inventive ; A young inventor tinkering with a complex clockwork device; close-up; Heroism; A cluttered workshop filled with tools, gears, and blueprints.; cinematic
Characteristic
Shot : A young boy wearing goggles and a vest is meticulously working on a complex mechanical device, likely in a workshop or inventor’s studio. The setting is reminiscent of a steampunk world, with intricate gears and brass accents visible in the background.
Aesthetic Score : 0.7
Mood : intrigued, curious, imaginative
Quality
Entropy : 6.74
Noise : 70
Prompt Clip Score : 0.35
AI Evaluation
Likelihood of AI : 0.80
Image errors : There are some minor artifacts in the image, particularly in the hair and the metallic surfaces. The rendering of the mechanical device appears slightly blurry and lacks fine detail. The lighting is somewhat uneven, creating some dark areas in the scene.
Into the Unknown: A Glimpse of a Decaying Future
A group of figures venture through a crumbling archway, illuminated by an eerie glow emanating from a mysterious metallic object. The scene evokes a sense of adventure and mystery, set against the backdrop of a decaying, futuristic cityscape.
Prompt
Steampunk: Mysterious, adventurous ; A group of explorers navigating a labyrinthine underground city; wide shot; Adventure; A vast, dimly lit underground city with intricate tunnels and glowing crystals.; cinematic
Characteristic
Shot : The image depicts a group of figures in a dark, abandoned, and potentially magical, or steampunk-inspired, hall. The hall is filled with stone arches, intricate structures, and lighting that suggests a forgotten, or otherwise mystical, civilization.
Aesthetic Score : 0.7
Mood : mysterious, suspenseful, haunting
Quality
Entropy : 6.91
Noise : 104
Prompt Clip Score : 0.33
AI Evaluation
Likelihood of AI : 0.90
Image errors : There are some minor artifacts and errors in the image, such as the blurry details and some unrealistic textures. The image has some slight color banding.
Steampunk Nightmare: A Mechanical Menace Awaits
A close-up shot reveals a menacing steampunk creature with glowing eyes, its metallic form radiating an eerie presence. The image evokes a sense of dread and anticipation, leaving viewers to wonder about the creature’s true capabilities.
Prompt
Steampunk: Exciting, immersive ; A player’s avatar battling a mechanical beast in a virtual reality game; close-up; Gaming; A futuristic gaming room with holographic displays and advanced controls.; cinematic
Characteristic
Shot : A close-up of a mechanical creature, possibly a dog, with glowing eyes and a menacing expression, set against a backdrop of blurred smoke and machinery.
Aesthetic Score : 0.8
Mood : dark, futuristic, ominous
Quality
Entropy : 6.61
Noise : 63
Prompt Clip Score : 0.26
AI Evaluation
Likelihood of AI : 0.90
Image errors : The image is slightly blurry and there is some noise present.
A Blast from the Past: Steam Locomotive Departs, Leaving a Trail of Nostalgia
A vintage steam locomotive chugs out of a train station, billowing smoke and leaving behind a sense of nostalgia. The dramatic composition, with the locomotive dominating the scene, captures the anticipation and movement of this iconic moment.
Prompt
Steampunk: Nostalgic, bustling ; A vintage steam train pulling into a bustling station; wide shot; Travel; A grand train station with ornate architecture, steam billowing from the train, and crowds of passengers.; cinematic
Characteristic
Shot : A steam locomotive is pulling out of a station, with people standing on the platform. The train is emitting smoke and steam.
Aesthetic Score : 0.7
Mood : nostalgic, romantic, dramatic
Quality
Entropy : 6.76
Noise : 86
Prompt Clip Score : 0.31
AI Evaluation
Likelihood of AI : 0.80
Image errors : Some areas of the image appear overly sharp and lack a natural depth of field. The smoke seems overly uniform and lacks a sense of natural randomness.
Conclusion
The results show that the generative AI model performed okay in terms of camera position and shot analysis, but very well in terms of aesthetic analysis. Here’s a breakdown:
- Camera Position Analysis: The score of 0.4 indicates that the model’s ability to react to camera positions in the prompt is slightly below average. A score between 0.5 and 0.75 would be considered good, and above 0.75 very good.
- Shot Analysis: The score of 0.55 indicates that the model’s ability to understand the scene in a prompt and create the appropriate shot is slightly above average. A score between 0.5 and 0.75 would be considered good, and above 0.75 very good.
- Aesthetic Analysis: The score of 0.33 indicates that the model is very good at creating images that match the expected aesthetic. A score between -0.2 and 0.1 is considered very good.
Overall, the model seems to be better at capturing the desired aesthetic than accurately interpreting camera positions and shot descriptions.
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/