Surreal Landscapes and Melting Clocks: Exploring the 'style-aesthetic' AI Challenge with Midjourney
- 10 minutes read - 2093 wordsTable of Contents
The ‘style-aesthetic’ challenge in AI art generation refers to the difficulty in replicating the unique artistic vision and style of a particular aesthetic. This challenge is particularly evident when dealing with surreal and whimsical styles, where the desired outcome involves capturing a specific mood, atmosphere, and visual language. For example, imagine trying to generate an image that embodies the ‘style-aesthetic’ of Salvador Dali, with its melting clocks, distorted figures, and dreamlike landscapes. While AI models can generate images based on specific prompts, they often struggle to capture the nuances and subtleties that define a particular artistic style. This blog post explores the ‘style-aesthetic’ challenge through the lens of a generative AI model, analyzing its performance in creating images based on various scenes and aesthetics.
Created with: midjourney
A Majestic Castle Suspended in Time
A whimsical fantasy scene unfolds with a majestic castle perched precariously on a cliff, overlooking a vast, cloudy landscape. The ominous clockwork moon hangs in the sky, adding a touch of mystery to this isolated and breathtaking vista.
Prompt
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 fantasy world with a floating castle and a giant clock moon in the sky. A lone figure stands at the edge of a cliff, gazing at the scene.
Aesthetic Score : 0.7
Mood : dreamy, mystical, adventurous
Quality
Entropy : 6.75
Noise : 114
Prompt Clip Score : 0.29
AI Evaluation
Likelihood of AI : 0.90
Image errors : There are some minor artifacts and errors in the image, such as the clouds and the sky. The figure’s posture appears slightly unnatural.
A Boy’s Journey Through a Dreamy, Glowing Forest
A young boy ventures into a magical forest, where luminous flowers and mushrooms illuminate his path. The interplay of light and shadow creates an atmosphere of wonder and mystery, leaving the viewer captivated by the boy’s solitary exploration.
Prompt
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 person walks through a magical forest with large, glowing flowers and mushrooms. The scene is brightly lit with a soft, ethereal glow.
Aesthetic Score : 0.8
Mood : magical, dreamy, whimsical
Quality
Entropy : 6.94
Noise : 107
Prompt Clip Score : 0.27
AI Evaluation
Likelihood of AI : 0.80
Image errors : No visible errors, however, the image seems to have some AI-generated elements, which make it look a bit unnatural.
Lost in the Game: A Surreal and Imaginative World
This vibrant and chaotic scene captures the immersive experience of video gaming. Dripping paint, a giant tree growing from the wall, and countless details create a surreal and adventurous world that draws you in. The dramatic effect of the image transports you into the game, leaving you wanting to explore further.
Prompt
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 person is playing a video game, with the background of the game projected into the real world.
Aesthetic Score : 0.7
Mood : fantasy, surreal, immersive
Quality
Entropy : 6.90
Noise : 104
Prompt Clip Score : 0.31
AI Evaluation
Likelihood of AI : 0.90
Image errors : The image has some minor artifacts around the edges of the game world, and the colors are a bit oversaturated.
Lost in a World of Whimsy: A Surreal Ice Cream City
A lone figure captures the wonder of a fantastical cityscape crafted entirely from ice cream. The playful contrast between the real and the surreal evokes a sense of childlike delight and sugary charm.
Prompt
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 scene of a person standing in a cityscape made entirely of ice cream cones and dripping pink and white frosting. The person is taking a selfie in front of the melting cityscape, with a clear sky and sunset in the background.
Aesthetic Score : 0.7
Mood : dreamy, whimsical, playful
Quality
Entropy : 6.62
Noise : 104
Prompt Clip Score : 0.35
AI Evaluation
Likelihood of AI : 0.90
Image errors : The ice cream textures are slightly blurry in places, and the lighting on the cityscape is uneven. Some elements, like the person’s backpack, have a slightly artificial look.
Whimsical Floating Islands: A Dreamy Escape
Journey to a fantastical world where three unique islands, connected by ropes and hot air balloons, float amidst a dreamy, cloudy sky. This surreal scene evokes a sense of wonder and adventure, inviting you to explore its magical atmosphere.
Prompt
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 fantastical scene of floating islands in a cloudy sky, with hot air balloons and whimsical buildings
Aesthetic Score : 0.8
Mood : magical, whimsical, dreamy
Quality
Entropy : 6.76
Noise : 108
Prompt Clip Score : 0.33
AI Evaluation
Likelihood of AI : 0.90
Image errors : Some of the textures, particularly in the clouds, appear slightly pixelated or blurry.
Cloud Cat Whispers Secrets to Two Girls
In a room filled with whimsical charm, two girls share a moment of wonder as a giant, cloud-formed cat watches over them. The scene is brimming with playful magic, inviting viewers to step into a world where dreams take flight.
Prompt
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 : Two little girls are playing in a room with a giant cat made of clouds. The room looks to be an old home with wood floors, a couch, and a chair. The cat is looking down at the girls with an expression of mild amusement.
Aesthetic Score : 0.7
Mood : playful, whimsical, surreal
Quality
Entropy : 6.47
Noise : 99
Prompt Clip Score : 0.32
AI Evaluation
Likelihood of AI : 1.00
Image errors : The cloud-cat is very blurry, and the girls look like they’ve been photoshopped in. The lighting is flat and there is a bit of a halo effect around the cat. Overall, the image has a very artificial feel.
Lost in the Golden Mist: A Solitary Figure Contemplates the City Below
A lone figure stands on the precipice of a swirling, abstract cloud formation, gazing down upon a city shrouded in mist and fog. The setting sun casts a golden glow, creating a surreal and ethereal atmosphere. The dramatic clouds and the solitary figure evoke a sense of isolation and contemplation, leaving the viewer to ponder the mysteries of the scene.
Prompt
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 lone figure stands on a cloud-like structure overlooking a city shrouded in fog. The city appears to be composed of towering buildings with a surreal, abstract twist.
Aesthetic Score : 0.7
Mood : mysterious, surreal, contemplative
Quality
Entropy : 6.58
Noise : 105
Prompt Clip Score : 0.33
AI Evaluation
Likelihood of AI : 0.90
Image errors : The image has some minor artifacts, particularly in the sky and cloud-like structure. The figure’s details are not very well-defined.
Lost in a Crystal Cavern: Explorers Uncover a Glowing Secret
Venture into a vast, mysterious cave where glowing green crystals illuminate the darkness. A team of explorers in dark suits navigate the cavern, their presence adding a sense of scale and wonder to this eerie, adventurous landscape.
Prompt
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 : A group of figures in dark clothing explore a cavernous landscape filled with glowing green crystals, a sense of mystery and awe emanates from the scene.
Aesthetic Score : 0.7
Mood : mysterious, magical, adventurous
Quality
Entropy : 6.70
Noise : 113
Prompt Clip Score : 0.32
AI Evaluation
Likelihood of AI : 0.90
Image errors : The image exhibits some artifacts, primarily in the form of aliasing along edges and some blurring in the background. The crystal textures could be improved to appear more realistic.
Unveiling the Digital Self: A Glimpse into a Futuristic Transformation
A close-up shot of a man’s face, shrouded in a futuristic, sci-fi overlay, evokes a sense of mystery and intrigue. The dramatic effect suggests a transformation or a connection to a digital world, leaving viewers captivated by the unknown.
Prompt
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 of a man’s face with a futuristic overlay, possibly a video game or sci-fi theme.
Aesthetic Score : 0.7
Mood : futuristic, mysterious, intense
Quality
Entropy : 6.20
Noise : 85
Prompt Clip Score : 0.28
AI Evaluation
Likelihood of AI : 0.70
Image errors : The overlay effect appears slightly artificial and the edges are not perfectly blended with the face.
A Solitary Figure Contemplates the Misty Depths
A lone figure stands on a mountain peak, gazing out over a vast, misty valley. The scene evokes a sense of mystery and solitude, with the distant city partially obscured by clouds adding to the ethereal atmosphere.
Prompt
Surrealist: Romantic and otherworldly ; 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 lone figure stands on a mountain peak overlooking a vast, misty landscape. The mountains are jagged and the sky is filled with clouds. A city can be seen in the distance, partially obscured by the clouds.
Aesthetic Score : 0.6
Mood : lonely, epic, ethereal
Quality
Entropy : 6.45
Noise : 104
Prompt Clip Score : 0.28
AI Evaluation
Likelihood of AI : 0.90
Image errors : The image has some minor artifacts, particularly in the clouds and the city in the distance. The figure is also somewhat pixelated.
Conclusion
The generative AI model performed well in terms of understanding the scene and camera position, but struggled with the aesthetic. Here’s a breakdown:
- Camera Position: The model scored 0.25, indicating it’s not very good at reacting to camera positions in prompts. A score between 0.5 and 0.75 would be considered good, and above 0.75 very good.
- Shot Analysis: The model scored 0.58, which is good. This means it’s able to understand the scene in the prompt reasonably well. A score between 0.5 and 0.75 is considered good, and above 0.75 very good.
- Aesthetic Analysis: The model scored 0.31, which is not very good. A score between -0.2 and 0.1 would be considered very good, indicating the generated image closely matches the expected aesthetic.
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://midjourney.com