Surreal Landscapes and Melting Clocks: Exploring the 'style-aesthetic' AI Challenge with Flux-schnell
- 10 minutes read - 1956 wordsTable of Contents
The ‘style-aesthetic’ is a fascinating challenge for generative AI models. It requires the AI to not only understand the scene and camera position but also to capture a specific visual style. This style can range from the whimsical and fantastical to the gritty and realistic. In this blog post, we explore the ‘style-aesthetic’ challenge through a series of prompts that test the AI’s ability to generate images with surreal elements, such as melting clocks, floating castles, and candy cities. We analyze the results and discuss the strengths and weaknesses of the AI model in capturing these unique aesthetics.
Created with: flux-schnell
Lost in the Mist: A Silhouette Against the City
A lone figure stands silhouetted against a misty cityscape, their journey shrouded in mystery. The towering clock tower dominates the skyline, adding a sense of haunting intrigue to this adventurous scene. The play of light and shadow creates a dramatic effect, leaving the figure’s purpose and destination unknown.
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 figure stands in the foreground, gazing towards a large, gothic clock tower. The tower is shrouded in mist and appears to be part of a sprawling, medieval city. The sky is a mix of cloudy and clear, with a hint of orange sunset.
Aesthetic Score : 0.7
Mood : mysterious, ethereal, atmospheric
Quality
Entropy : 6.73
Noise : 91
Prompt Clip Score : 0.27
AI Evaluation
Likelihood of AI : 0.70
Image errors : The edges of the image appear slightly blurred. There is a noticeable lack of detail in the far background.
A Moment of Wonder: A Boy’s Pensive Gaze Amidst Blurry Mushrooms
A young boy, adorned with a hat and backpack, gazes thoughtfully to the side, his expression hinting at curiosity and wonder. The soft lighting and the blurry background of yellow mushrooms create a sense of mystery and intrigue, inviting viewers to ponder the boy’s thoughts and the secrets hidden within the scene.
Prompt
style-aesthetic Surrealist: Curious and whimsical ; A young adventurer; close-up; Adventure; A jungle filled with giant, talking flowers and glowing mushrooms.; cinematic
Characteristic
Shot : A young boy wearing a brown hat and a brown shirt is looking directly at the camera, with a blurred background of yellow mushrooms.
Aesthetic Score : 0.8
Mood : pensive, melancholic, introspective
Quality
Entropy : 6.68
Noise : 82
Prompt Clip Score : 0.26
AI Evaluation
Likelihood of AI : 0.10
Image errors : There are no noticeable image errors.
Lost in the Digital City
A hand grips a video game controller, the focus sharp and intense, against a backdrop of a blurred, futuristic cityscape. The image evokes a sense of isolation and immersion in a digital world.
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 hand is holding a video game controller in front of a blurred background of a city. The controller is in focus, the background is blurry, and the lighting is dim.
Aesthetic Score : 0.6
Mood : intense, focused, techy
Quality
Entropy : 6.94
Noise : 68
Prompt Clip Score : 0.26
AI Evaluation
Likelihood of AI : 0.50
Image errors : No visible artifacts or errors in the image.
Cityscape Smiles: Two Friends Enjoying a Sweet Treat
Two men stand against a vibrant cityscape, sharing a laugh and a giant ice cream cone. The playful mood and whimsical prop create a lighthearted and fun atmosphere.
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 : Two men are standing on a rooftop with a view of the city skyline. They are holding ice cream cones and looking at the camera. The man on the left is smiling broadly, while the man on the right is looking more serious.
Aesthetic Score : 0.6
Mood : happy, playful, lighthearted
Quality
Entropy : 6.87
Noise : 84
Prompt Clip Score : 0.29
AI Evaluation
Likelihood of AI : 0.10
Image errors : The image is slightly blurry, especially in the background.
Soaring High: A Couple’s Serene Adventure in a Hot Air Balloon
Capture the breathtaking beauty of a hot air balloon ride with this serene image. A couple enjoys the peaceful tranquility as they float above the world, surrounded by other balloons and a distant airplane. The perspective creates a sense of scale and grandeur, making you feel like you’re right there with them.
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 hot air balloon ride with a couple in a basket, other hot air balloons are in the background, a small plane is in the distance, and the sky is a vibrant blue with fluffy clouds.
Aesthetic Score : 0.7
Mood : tranquil, romantic, adventurous
Quality
Entropy : 6.63
Noise : 89
Prompt Clip Score : 0.27
AI Evaluation
Likelihood of AI : 0.60
Image errors : Slight blurring around the edges of the balloons, some artifacts in the sky and clouds, and some color banding.
Where Reality Meets Whimsy: A Man, a Couch, and a Cloud Cat
A serene living room scene takes a fantastical turn with a fluffy white cat perched on a cloud in the background. The juxtaposition of the ordinary and the extraordinary creates a sense of wonder and whimsy, leaving you questioning the boundaries of reality.
Prompt
style-aesthetic Surrealist: Warm and surreal ; A family portrait; medium shot; Family; A living room with furniture made of clouds and a giant, talking cat.; cinematic
Characteristic
Shot : A man sits on a couch in a living room, looking at a large cat in a cloud. The cat is gazing intently at the man. The room is decorated in a modern style.
Aesthetic Score : 0.7
Mood : dreamy, whimsical, surreal
Quality
Entropy : 6.75
Noise : 91
Prompt Clip Score : 0.33
AI Evaluation
Likelihood of AI : 0.90
Image errors : The cloud-cat is a bit blurry, and the lighting is a bit artificial.
Heroic Silhouette Against a Dramatic Sky
A lone figure in a red cape stands atop a skyscraper, silhouetted against a breathtaking sky. A large, vibrant cloud, seemingly rising from the building, adds a touch of mystery and hope to the scene. The image evokes a sense of power and wonder, hinting at a story of heroism and triumph.
Prompt
style-aesthetic Surrealist: Powerful and unsettling ; A superhero standing on a skyscraper; wide shot; Heroism; A city with buildings that twist and turn like melting wax, with the sky filled with swirling clouds.; cinematic
Characteristic
Shot : A man in a red cape stands on a rooftop, looking out at a cityscape. The sky is filled with clouds, and a large, fiery cloud is in the background, possibly representing an explosion or some other disaster.
Aesthetic Score : 0.6
Mood : dramatic, mysterious, powerful
Quality
Entropy : 6.72
Noise : 84
Prompt Clip Score : 0.27
AI Evaluation
Likelihood of AI : 0.80
Image errors : The cloud in the background looks a little bit fake and the lighting is inconsistent between the foreground and the background.
Lost in a World of Glowing Crystals
Venture into a mysterious cave where blue light illuminates shimmering crystals and silhouettes a group of explorers. The contrast between darkness and light creates a magical and adventurous atmosphere.
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 : Four figures are silhouetted in a dark cave with a light at the end of the tunnel. The cave walls are textured with interesting rock formations. The figures are standing around glowing crystals.
Aesthetic Score : 0.6
Mood : mysterious, adventurous, mystical
Quality
Entropy : 6.00
Noise : 96
Prompt Clip Score : 0.29
AI Evaluation
Likelihood of AI : 0.20
Image errors : There is a slight chromatic aberration along the edges of the image.
Lost in the Neon Glow: A Gamer’s Intense Focus
A young gamer, headphones on and eyes glued to the screen, is completely immersed in their virtual world. The blurred background and neon lighting create a sense of isolation and intensity, highlighting the power of gaming to transport us to other realities.
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 young man is sitting in a dimly lit room, wearing headphones and looking at a computer screen. The room is filled with various computer screens, and there is a blurred figure in the background.
Aesthetic Score : 0.6
Mood : intense, focused, determined
Quality
Entropy : 6.58
Noise : 62
Prompt Clip Score : 0.23
AI Evaluation
Likelihood of AI : 0.70
Image errors : The image appears to be slightly grainy and the lighting is a bit uneven. There are also some artifacts around the edges of the image.
Silhouettes on the Edge of Wonder
Three figures stand on a mountain peak, their forms silhouetted against a sea of clouds. A distant castle, seemingly floating in the sky, adds a touch of mystery and majesty to this dreamy, ethereal scene.
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 group of three people standing on a mountaintop overlooking a vast sea of clouds and a majestic castle in the distance, bathed in the soft golden light of the setting sun.
Aesthetic Score : 0.7
Mood : serene, magical, awe-inspiring
Quality
Entropy : 6.37
Noise : 68
Prompt Clip Score : 0.27
AI Evaluation
Likelihood of AI : 0.60
Image errors : The clouds appear somewhat pixelated and lack realism. The lighting is slightly unnatural.
Conclusion
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 0.2, indicating it didn’t perform well in matching the camera position described in the prompt. This suggests the model may not be very sensitive to camera position instructions.
- Shot Analysis: The model scored 0.7, indicating it performed well in understanding the scene described in the prompt. This suggests the model is capable of generating images that match the overall scene composition.
- Aesthetic Analysis: The model scored 0.33, indicating it didn’t perform well in matching the expected aesthetic. This suggests the model may not be able to accurately capture the desired visual style.
Overall, the model shows promise in understanding the scene and shot composition, but needs improvement in accurately capturing the desired camera position and 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://fal.ai/models/fal-ai/flux/schnell/api