AI's Artistic Eye: Capturing the Scene, But Missing the Shot with Midjourney
- 9 minutes read - 1885 words
Table of Contents
In the realm of artificial intelligence, the ability to generate images based on textual descriptions is a fascinating area of exploration. This blog post delves into the results of an experiment where an AI model was tasked with creating images based on specific camera positions and scene descriptions. The model’s performance reveals a mixed bag of results, showcasing strengths in capturing the desired aesthetic but struggling with accurately translating the intended camera angles and scene details. We’ll explore the model’s performance, analyzing its strengths and weaknesses, and discuss potential improvements for future development.
Created with: midjourney
A Solitary Journey Through the Clouds
A lone hiker braves the windswept heights of a snow-covered mountain peak, dwarfed by the swirling clouds and vast landscape. This breathtaking aerial view captures the serenity, power, and adventurous spirit of the moment.
Prompt
Aerial View Aerial View: inspiring, triumphant ; Lone figure standing on a mountain peak; wide shot; heroism; vast, snow-capped mountains with clouds swirling below; cinematic
Characteristic
Shot : A lone hiker walks along the ridge of a snow-capped mountain peak, with clouds swirling around it.
Aesthetic Score : 0.8
Mood : serene, isolated, adventurous
Quality
Entropy : 6.45
Noise : 98
Prompt Clip Score : 0.33
AI Evaluation
Likelihood of AI : 0.20
Image errors : No obvious errors, a few stray pixels could be more pronounced.
A Tiny Balloon, A Vast Jungle: Finding Serenity in the Canopy
Soar above the emerald embrace of a lush jungle in a hot air balloon. This aerial view captures the tranquility and adventure of exploring nature’s grandeur, where the smallness of the balloon against the vastness of the canopy evokes a sense of wonder and perspective.
Prompt
Aerial View Aerial View: exhilarating, adventurous ; A hot air balloon soaring over a lush jungle canopy; aerial tracking shot; adventure; vibrant green foliage stretching as far as the eye can see; cinematic
Characteristic
Shot : A hot air balloon flying over a lush green forest, possibly in a tropical location. The sun is shining brightly, casting long shadows from the trees.
Aesthetic Score : 0.7
Mood : peaceful, tranquil, serene
Quality
Entropy : 6.69
Noise : 133
Prompt Clip Score : 0.39
AI Evaluation
Likelihood of AI : 0.10
Image errors : No obvious errors
A Lone Figure Commands the Cityscape
From an aerial perspective, a sprawling medieval city unfolds beneath a crimson sky. Towering stone buildings and a winding river weave a tapestry of history. A lone figure, cloaked in a flowing red cape, stands on a rooftop, their silhouette a stark contrast against the grandeur of the city. This dramatic scene evokes a sense of isolation and power, leaving the viewer to ponder the figure’s story and the secrets held within the city walls.
Prompt
Aerial View Aerial View: epic, fantastical ; A player character standing atop a towering castle, overlooking a sprawling fantasy city; high-angle shot; gaming; vibrant, detailed cityscape with magical effects; cinematic
Characteristic
Shot : A high-angle view of a sprawling fantasy city, with a lone figure standing on a high point overlooking the city, which is bisected by a river. The city is built in a medieval style, with many towers, bridges, and cobblestone streets.
Aesthetic Score : 0.8
Mood : epic, mysterious, dramatic
Quality
Entropy : 6.86
Noise : 123
Prompt Clip Score : 0.35
AI Evaluation
Likelihood of AI : 0.90
Image errors : Some aliasing is noticeable in the detailed areas of the city, especially the towers.
A Symphony of Colors: Life in Motion at an Indian Marketplace
From above, the vibrant chaos of an Indian marketplace unfolds. Stalls overflow with colorful goods, and the bustling crowd creates a sense of constant movement. This aerial view captures the energy and scale of this lively hub, offering a glimpse into the heart of Indian life.
Prompt
Aerial View Aerial View: lively, energetic ; A bustling marketplace in a vibrant city, with people moving like ants; bird’s-eye view; tourism; colorful stalls, vibrant clothing, and bustling crowds; cinematic
Characteristic
Shot : An aerial view of a bustling marketplace in India. The image is taken from a high vantage point, looking down on a crowd of people shopping and selling goods. The scene is full of vibrant colors, from the colorful clothing of the people to the many stalls selling fruits, vegetables, and other goods.
Aesthetic Score : 0.8
Mood : lively, chaotic, vibrant
Quality
Entropy : 6.76
Noise : 120
Prompt Clip Score : 0.32
AI Evaluation
Likelihood of AI : 0.20
Image errors : There is a little bit of noise in the image and some compression artifacts.
Paradise Found: A Sailboat Anchored in Pristine Turquoise Waters
Escape to a tropical paradise with this breathtaking aerial view. A sailboat rests peacefully in crystal-clear turquoise waters, just off a pristine white sand beach and a lush green island. The vibrant colors and dramatic contrast create a sense of serenity and awe, highlighting the vastness of the ocean.
Prompt
Aerial View Aerial View: peaceful, tranquil ; A lone sailboat navigating a turquoise lagoon surrounded by white sand beaches; aerial tracking shot; travel; crystal-clear water, lush vegetation, and a sense of serenity; cinematic
Characteristic
Shot : A bird’s-eye view of a sailboat sailing near a white sand beach and lush green tropical island
Aesthetic Score : 0.8
Mood : tranquil, serene, adventurous
Quality
Entropy : 6.69
Noise : 107
Prompt Clip Score : 0.34
AI Evaluation
Likelihood of AI : 0.10
Image errors : No artifacts or errors in the image
A Family’s Journey Through the Emerald Canopy
From high above, a family of five ventures into a lush green forest, their small figures dwarfed by the towering trees. The aerial perspective captures the tranquility and wonder of their adventure, highlighting the peaceful and happy mood as they explore the vast wilderness.
Prompt
Aerial View Aerial View: warm, nostalgic ; A family holding hands and walking along a winding path through a forest; aerial tracking shot; family; lush green trees, dappled sunlight, and a sense of togetherness; cinematic
Characteristic
Shot : A family of five is walking through a lush green forest. The sun is shining through the trees, and the family is smiling and laughing.
Aesthetic Score : 0.7
Mood : joyful, peaceful, relaxing
Quality
Entropy : 6.78
Noise : 134
Prompt Clip Score : 0.32
AI Evaluation
Likelihood of AI : 0.20
Image errors : No noticeable errors
A Lone Starship Navigates the Cosmic Tapestry
Witness the awe-inspiring journey of a solitary spaceship as it traverses a breathtaking nebula, its path illuminated by swirling gas and dust. This cosmic adventure evokes a sense of wonder and exploration, highlighting the vastness of space and the intrepid spirit of those who dare to venture beyond.
Prompt
Aerial View Aerial View: awe-inspiring, futuristic ; A lone spaceship soaring through a field of stars; wide shot; heroism; vast, star-filled galaxy with swirling nebulae; cinematic
Characteristic
Shot : A spaceship flying through a vast, colorful nebula with stars and swirling gas clouds.
Aesthetic Score : 0.8
Mood : mysterious, awe-inspiring, futuristic
Quality
Entropy : 6.71
Noise : 115
Prompt Clip Score : 0.29
AI Evaluation
Likelihood of AI : 0.90
Image errors : Some artifacts and noise are visible in the image.
Conquering the Cascade: Climbers Brave the Majestic Waterfall
A breathtaking aerial view captures the raw power of a cascading waterfall, with daring climbers scaling the sheer rock face. The dramatic perspective highlights the vastness of nature and the courage of those who challenge its might.
Prompt
Aerial View Aerial View: intense, thrilling ; A group of adventurers rappelling down a sheer cliff face; aerial tracking shot; adventure; rugged mountain terrain, cascading waterfalls, and a sense of danger; cinematic
Characteristic
Shot : A waterfall cascading down a steep cliff face with three climbers ascending the rock wall.
Aesthetic Score : 0.8
Mood : dramatic, adventurous, serene
Quality
Entropy : 6.74
Noise : 128
Prompt Clip Score : 0.34
AI Evaluation
Likelihood of AI : 0.10
Image errors : The image has some minor noise and compression artifacts. The color balance is slightly cool.
Monster Rampage: City Under Siege!
A fiery behemoth wreaks havoc on a helpless city, its destructive power evident in the chaotic explosions and flying debris. The aerial view captures the full scale of the monster’s rampage, leaving viewers breathless with the intensity of the scene.
Prompt
Aerial View Aerial View: intense, action-packed ; A player character battling a giant monster in a virtual world; high-angle shot; gaming; detailed, fantastical environment with explosions and special effects; cinematic
Characteristic
Shot : A giant monster is attacking a city, with many explosions and people fleeing for their lives. The monster is covered in flames and has a menacing expression.
Aesthetic Score : 0.7
Mood : intense, chaotic, dramatic
Quality
Entropy : 6.46
Noise : 122
Prompt Clip Score : 0.33
AI Evaluation
Likelihood of AI : 0.90
Image errors : The image has some minor artifacts, such as the blurry textures on the monster’s skin and the jagged edges of the buildings.
Sunset Serenity: A Hot Air Balloon Soars Through Golden Clouds
Witness the breathtaking beauty of a hot air balloon gliding through a sky ablaze with sunset hues. The sun’s rays pierce through the clouds, casting a golden glow on the balloon and creating a sense of awe and tranquility. This serene scene evokes feelings of peace and hope, leaving you with a sense of wonder.
Prompt
Aerial View Aerial View: romantic, heartwarming ; A hot air balloon carrying a family over a breathtaking sunset; aerial tracking shot; family; vibrant colors of the sky, silhouetted mountains, and a sense of joy; cinematic
Characteristic
Shot : A hot air balloon flying over a mountainous landscape at sunset. The sun is setting behind the balloon, and its rays are shining through the clouds.
Aesthetic Score : 0.8
Mood : serene, peaceful, hopeful
Quality
Entropy : 6.84
Noise : 91
Prompt Clip Score : 0.33
AI Evaluation
Likelihood of AI : 0.30
Image errors : No visible image errors or artifacts.
Conclusion
The results show that the generative AI model performed well in understanding the scene and camera positions, but struggled with the aesthetic aspect. Here’s a breakdown:
- Camera Position: The model scored 0.175, which is considered below average. This suggests that the model didn’t accurately capture the intended camera positions described in the prompt.
- Shot Analysis: The model scored 0.47, which is considered below average. This indicates that the model didn’t fully understand the scene described in the prompt and didn’t create an image that accurately reflected it.
- Aesthetic Analysis: The model scored 0.09, which is considered very good. This means that the generated image closely matched the expected aesthetic style, despite the issues with camera position and scene understanding.
Overall, the model seems to be better at capturing the desired aesthetic than understanding the scene and camera positions. This suggests that the model might need further training to improve its ability to interpret and translate complex visual descriptions into images.