Surreal Landscapes and Melting Clocks: Exploring the 'style-aesthetic' AI Challenge with Imagen-v3-fast
- 9 minutes read - 1896 wordsTable of Contents
The ‘style-aesthetic’ prompt presents a unique challenge for generative AI models. It requires the AI to not only understand the scene and camera position but also to capture a specific artistic style, often characterized by surreal elements, vibrant colors, and a sense of wonder. This blog post explores the results of a generative AI model tasked with creating images based on the ‘style-aesthetic’ prompt, highlighting its strengths and weaknesses in capturing the desired aesthetic.
Created with: imagen-v3-fast
A Knight’s Tale: Mystery and Majesty on the Still Lake
A lone knight stands sentinel on a rocky shore, gazing out at a vast, still lake. In the distance, a floating castle and clock tower pierce the dramatic sky, creating an atmosphere of mystical wonder and melancholic adventure. The contrasting light and shadow, the ethereal architecture, and the knight’s solitary stance weave a tale of mystery and grandeur.
Prompt
style-aesthetic Surrealist: Epic and melancholic ; A lone knight; wide shot; Heroism; A vast, surreal landscape with floating castles and giant, melting clocks.; cinematic
Characteristic
Shot : A lone knight stands on a rocky shore, looking out at a vast, still lake, with a floating castle and clock tower in the distance, framed by a dramatic sky.
Aesthetic Score : 0.7
Mood : mystical, melancholic, adventurous
Quality
Entropy : 6.78
Noise : 67
Prompt Clip Score : 0.34
AI Evaluation
Likelihood of AI : 0.90
Image errors : Some minor artifacts and blurriness in the background, especially around the edges.
A Solitary Figure Embarks on a Path of Mystery and Hope
A lone figure stands amidst a dark, fantastical forest, bathed in the ethereal glow of bioluminescent flowers. The path ahead beckons, promising both mystery and hope in this eerie, yet captivating scene.
Prompt
style-aesthetic Surrealist: Eerie, otherworldly wonder ; A lone figure, silhouetted against a vibrant tapestry of bioluminescent fungi and gargantuan, whispering blossoms.; cinematic
Characteristic
Shot : A solitary figure stands in a dark, fantastical forest, illuminated by glowing, bioluminescent flowers, with a path leading forward into the unknown.
Aesthetic Score : 0.8
Mood : mysterious, eerie, hopeful
Quality
Entropy : 6.38
Noise : 74
Prompt Clip Score : 0.34
AI Evaluation
Likelihood of AI : 1.00
Image errors : Some aliasing is visible on the edges of the flowers and the figure, which could be improved with more careful rendering.
Immerse Yourself in the Future: Action-Packed Gaming Scene
This captivating image captures the essence of futuristic gaming. A gamer holds a PS4 controller, their focus drawn to the vibrant, action-packed scene unfolding on the screen. The futuristic city, bathed in contrasting blue and red tones, bursts with detail and depth, creating an immersive experience that’s both exciting and visually stunning.
Prompt
style-aesthetic Surrealist: Intriguing and disorienting ; A gamer’s hand holding a controller; close-up; Gaming; A pixelated world bleeding into the real world, with characters and objects from the game appearing in the background.; cinematic
Characteristic
Shot : A gamer is holding a PS4 controller, with an animated scene from a video game playing on a screen in the background. The scene is a futuristic city with characters, lights, and effects, with a strong sense of depth and perspective. The scene is divided into two halves, one with a blue tone and the other with a red tone.
Aesthetic Score : 0.7
Mood : futuristic, action-packed, immersive
Quality
Entropy : 6.28
Noise : 43
Prompt Clip Score : 0.28
AI Evaluation
Likelihood of AI : 0.90
Image errors : The image quality is good overall, but there are some areas where the lighting is uneven or there are some artifacts. The scene in the background appears slightly blurry, and the details are slightly less sharp than expected.
Lost in a World of Candy and Ice Cream
A lone figure captures the whimsical beauty of a surreal cityscape crafted entirely from candy and ice cream. The perspective draws you into this playful, dreamlike world, leaving you with a sense of wonder and intrigue.
Prompt
style-aesthetic Surrealist: Humorous and absurd ; A tourist taking a selfie; medium shot; Tourism; A city skyline made entirely of candy, with giant, melting ice cream cones in the background.; cinematic
Characteristic
Shot : A surreal cityscape made of candy and ice cream with a lone figure taking a picture.
Aesthetic Score : 0.7
Mood : whimsical, playful, surreal
Quality
Entropy : 6.76
Noise : 84
Prompt Clip Score : 0.35
AI Evaluation
Likelihood of AI : 0.90
Image errors : There are some minor artifacts and blurriness in the image, particularly in the background.
A Whimsical Journey to the Sunset
A family soars through a dreamy landscape of floating islands as the sun dips below the horizon. This breathtaking scene, captured through a window, evokes a sense of wonder, adventure, and a touch of melancholy.
Prompt
style-aesthetic Surrealist: Dreamy and fantastical ; A family traveling in a hot air balloon; long shot; Travel; A sky filled with floating islands and giant, whimsical creatures.; cinematic
Characteristic
Shot : A family is riding in a hot air balloon over a whimsical landscape of floating islands, the sun is setting, the image is framed by the view from an airplane or a car window.
Aesthetic Score : 0.8
Mood : whimsical, dreamy, hopeful
Quality
Entropy : 6.42
Noise : 63
Prompt Clip Score : 0.34
AI Evaluation
Likelihood of AI : 0.90
Image errors : The image has some minor artifacts, particularly around the edges of the floating islands, and the family figures are slightly pixelated. The window frame is slightly too sharp, but the effect is minor.
The Feline Philosopher: A Surreal Encounter on a Cloud
A whimsical and mysterious image of a man with a cat head, perched thoughtfully on a cloud. The dramatic lighting and the cat’s expression create an air of intrigue, leaving you wondering about the secrets this feline philosopher holds.
Prompt
style-aesthetic Surrealist: Eerie and whimsical ; A lone figure sits amidst a swirling cloud of smoke, a giant, talking cat perched on their shoulder.; cinematic
Characteristic
Shot : A man with a cat head sitting on a cloud, looking up with a thoughtful expression
Aesthetic Score : 0.7
Mood : surreal, whimsical, mysterious
Quality
Entropy : 6.38
Noise : 44
Prompt Clip Score : 0.33
AI Evaluation
Likelihood of AI : 1.00
Image errors : There are no noticeable artifacts or errors in the image.
A Solitary Figure Bathed in Hope Amidst the City’s Shadows
A lone figure stands atop a towering skyscraper, silhouetted against a brilliant light piercing through the clouds. The cityscape stretches out below, shrouded in darkness, creating a stark contrast that evokes a sense of drama, hope, and mystery. The image captures a moment of isolation and contemplation, leaving viewers to ponder the figure’s story and the meaning behind the celestial glow.
Prompt
style-aesthetic Surrealist: Uneasy, oppressive, and foreboding ; A lone figure stands atop a towering, warped skyscraper, silhouetted against a sky of swirling, ominous clouds. The city below stretches out in a chaotic, melting landscape.; cinematic
Characteristic
Shot : A lone figure stands on top of a skyscraper, silhouetted against a bright light in the clouds above. The cityscape stretches out below.
Aesthetic Score : 0.7
Mood : dramatic, hopeful, mysterious
Quality
Entropy : 6.67
Noise : 73
Prompt Clip Score : 0.36
AI Evaluation
Likelihood of AI : 0.90
Image errors : Some of the buildings in the cityscape are blurry and lack detail. The figure’s silhouette is somewhat pixelated.
Silhouettes of Adventure in a Crystal Cave
Three figures stand silhouetted against a glowing, crystal-encrusted cave passage, bathed in a mysterious light. The scene evokes a sense of awe and adventure, promising a journey into the unknown.
Prompt
style-aesthetic Surrealist: Mysterious and awe-inspiring ; A group of adventurers exploring a cave; medium shot; Adventure; A cave filled with glowing crystals and strange, bioluminescent creatures.; cinematic
Characteristic
Shot : Three figures silhouetted against a glowing, crystal-encrusted cave passage. The passage is lit by a bright light source from the top, emphasizing the depth of the cave.
Aesthetic Score : 0.7
Mood : mysterious, awe, adventurous
Quality
Entropy : 6.42
Noise : 78
Prompt Clip Score : 0.33
AI Evaluation
Likelihood of AI : 0.90
Image errors : The crystals are somewhat pixelated and lack intricate detail. The lighting is slightly unrealistic.
Intense Gaze, Mysterious Past: A Portrait of Unseen Secrets
A close-up portrait captures the serious expression of a man, his gaze intense and unwavering. The blurry figure in the background adds a layer of mystery, hinting at a story waiting to be told. The dramatic close-up shot and the subject’s powerful presence create a sense of suspense and intrigue.
Prompt
style-aesthetic Surrealist: Intense and immersive ; A gamer’s face illuminated by the screen; close-up; Gaming; A digital world bleeding into the real world, with characters and objects from the game appearing in the background.; cinematic
Characteristic
Shot : A close-up portrait of a man with a serious expression, with a blurry figure in the background.
Aesthetic Score : 0.7
Mood : intense, serious, mysterious
Quality
Entropy : 6.48
Noise : 78
Prompt Clip Score : 0.27
AI Evaluation
Likelihood of AI : 0.90
Image errors : Some minor blurring and pixelation in the background, some minor artifacts in the man’s beard.
A Dreamy Escape: Couple Gazes at a Floating City in the Clouds
A couple stands on a mountaintop, their eyes fixed on a fantastical floating city nestled amongst the clouds. The scene evokes a sense of wonder and hope, with the city’s grandeur dwarfing the couple and their earthly concerns.
Prompt
style-aesthetic Surrealist: Romantic and otherworldly ; A couple standing on a mountaintop; long shot; Travel; A mountain range with peaks that reach into the clouds, with a giant, floating city in the distance.; cinematic
Characteristic
Shot : A couple standing on a mountaintop, looking up at a floating city in the distance, with a sea of clouds between them.
Aesthetic Score : 0.7
Mood : dreamy, hopeful, fantastical
Quality
Entropy : 6.83
Noise : 61
Prompt Clip Score : 0.33
AI Evaluation
Likelihood of AI : 0.80
Image errors : The image appears to be generated by AI, and some details are slightly blurry and unnatural.
Conclusion
The results of the analysis 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 0.25, which is below the “good” range of 0.5 to 0.75. This indicates that the model didn’t accurately capture the intended camera position in the prompt.
- Shot Analysis: The model scored 0.615, which falls within the “good” range. This means the model was able to understand the scene described in the prompt reasonably well.
- Aesthetic Analysis: The model scored 0.28, which is far from the “very good” range of -0.2 to 0.1. This suggests that the generated image’s aesthetic significantly deviated from the expected aesthetic described in the prompt.
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-3/