AI Captures the Scene, But Misses the Mood with Scenario
- 9 minutes read - 1818 words
Table of Contents
In the realm of AI image generation, capturing the essence of a scene goes beyond simply replicating the elements described. It involves understanding the intended mood, style, and aesthetic. This blog post examines the results of testing an AI model’s ability to generate images based on detailed scene descriptions. While the model demonstrates proficiency in capturing camera position and shot composition, it struggles to match the desired aesthetic style. We explore the model’s strengths and weaknesses, providing insights into the current state of AI image generation and its potential for creative applications.
Created with: scenario
A Solitary Figure in the Setting Sun
A woman, cloaked in brown, walks towards a crumbling building as the sun sets, casting long shadows across a desolate landscape. The scene evokes a sense of solitude, melancholy, and a glimmer of hope.
Prompt
poses walking-away: Melancholy, yet hopeful ; Lone figure in a tattered cloak; wide shot; Heroism; Ruins of a fallen city bathed in the golden light of a setting sun; cinematic
Characteristic
Shot : A lone woman in a cloak stands in the ruins of a building at sunset.
Aesthetic Score : 0.75
Mood : melancholy, desolate, contemplative
Quality
Entropy : 6.57
Noise : 99
Prompt Clip Score : 0.32
AI Evaluation
Likelihood of AI : 0.90
Image errors : The image has some minor artifacts in the sky and the ruins.
Lost in the Emerald Embrace: A Journey Through Mystery and Tranquility
A young woman ventures deep into a lush jungle, sunlight filtering through the dense canopy creating an atmosphere of mystery and adventure. The tranquil scene evokes a sense of peace, while the dramatic play of light adds a touch of intrigue.
Prompt
poses walking-away: Excited, adventurous ; A young adventurer with a backpack; medium shot; Adventure; Lush jungle with a hidden path leading into the unknown; cinematic
Characteristic
Shot : A young woman is walking on a path through a lush jungle, with dense foliage on both sides and a soft, hazy light filtering through the trees.
Aesthetic Score : 0.7
Mood : mysterious, adventurous, serene
Quality
Entropy : 6.79
Noise : 101
Prompt Clip Score : 0.26
AI Evaluation
Likelihood of AI : 0.30
Image errors : The image appears to be slightly overexposed in areas, particularly in the background, and the leaves in the foreground appear to be slightly blurred.
Neon Dreams: A Cyberpunk Night Walk
A young woman, eyes gleaming with determination, navigates a city bathed in vibrant neon light. Her headphones pulse with an unseen rhythm, reflecting the energy of the futuristic cityscape. This cyberpunk scene captures the thrill of urban exploration and the cool confidence of a lone traveler.
Prompt
poses walking-away: Focused, determined ; A gamer with a headset; close-up; Gaming; Neon-lit cityscape reflected in a computer screen; cinematic
Characteristic
Shot : A young woman wearing headphones walks through a neon-lit city street at night.
Aesthetic Score : 0.8
Mood : futuristic, cyberpunk, cool
Quality
Entropy : 6.89
Noise : 93
Prompt Clip Score : 0.32
AI Evaluation
Likelihood of AI : 0.90
Image errors : Slight blurring on the woman’s face and some artifacts around the neon lights.
A Whimsical Stroll Through a European City
A charming scene of three friends, a man and a woman in the foreground and a man in the background, enjoying a leisurely walk down a cobblestone street lined with historic buildings. The mood is lighthearted and romantic, capturing the essence of a playful European adventure.
Prompt
poses walking-away: Romantic, carefree ; A couple holding hands; medium shot; Tourism; Picturesque European street with cobblestone paths and colorful buildings; cinematic
Characteristic
Shot : Three people walking down a cobblestone street in a European city. The people are facing away from the camera and are walking in a line. The buildings on either side of the street are old and have colorful facades.
Aesthetic Score : 0.6
Mood : romantic, nostalgic, charming
Quality
Entropy : 6.65
Noise : 94
Prompt Clip Score : 0.28
AI Evaluation
Likelihood of AI : 0.20
Image errors : There are no visible errors in the image.
A Lone Traveler’s Journey Begins
A melancholic yet hopeful scene unfolds as a traveler, burdened with two suitcases, walks towards a parked airplane on a vast runway. The low-angle perspective emphasizes their solitude and the vastness of the airport, hinting at the adventure that awaits. The pale blue sky with scattered clouds adds a touch of contemplation to the image.
Prompt
poses walking-away: Nostalgic, bittersweet ; A lone traveler with a suitcase; long shot; Travel; Airport runway with a departing airplane in the distance; cinematic
Characteristic
Shot : A woman in a brown coat and hat walks towards a large airplane on a runway, carrying two suitcases. The plane is in the background, and the runway is in the foreground. The sun is setting in the sky, casting a warm glow on the scene.
Aesthetic Score : 0.7
Mood : calm, hopeful, nostalgic
Quality
Entropy : 6.42
Noise : 75
Prompt Clip Score : 0.24
AI Evaluation
Likelihood of AI : 0.80
Image errors : The image is slightly blurry, especially in the background. The plane appears slightly distorted.
Golden Hour Bliss on the Beach
Four friends enjoy a peaceful sunset stroll along a sandy beach, bathed in warm golden light. The scene evokes a sense of calm and happiness, perfect for a relaxing escape.
Prompt
poses walking-away: Joyful, carefree ; A group of friends laughing; wide shot; Groups; Beach at sunset with the ocean waves crashing in the background; cinematic
Characteristic
Shot : Four young women are walking along a sandy beach, holding hands, with a large wave breaking in the background. They are all wearing summer clothes and walking towards the ocean. The setting sun casts a warm golden light on the scene.
Aesthetic Score : 0.7
Mood : tranquil, happy, carefree
Quality
Entropy : 6.56
Noise : 96
Prompt Clip Score : 0.26
AI Evaluation
Likelihood of AI : 0.10
Image errors : No noticeable errors in the image. The color tone is balanced. The exposure is good.
A Warrior’s Journey Begins in the Misty Forest
A female warrior, clad in armor and wielding a sword, strides through a mystical forest shrouded in mist. Her determined gaze and poised stance hint at an adventure about to unfold, leaving viewers captivated by the mystery and intrigue of her journey.
Prompt
poses walking-away: Determined, resolute ; A lone warrior with a sword; medium shot; Heroism; Dark forest with a path leading into the shadows; cinematic
Characteristic
Shot : A female warrior in full armor walks through a misty forest, her sword drawn. The light is soft and ethereal, creating a sense of mystery and intrigue.
Aesthetic Score : 0.7
Mood : mysterious, adventurous, powerful
Quality
Entropy : 6.59
Noise : 110
Prompt Clip Score : 0.27
AI Evaluation
Likelihood of AI : 0.70
Image errors : The image has some minor artifacts, particularly in the trees and mist. The overall detail is good but some elements appear a little soft.
Stepping into Mystery: A Journey Through Ancient Ruins
A group of adventurers embark on a journey through a stone archway, bathed in warm, inviting light. The scene evokes a sense of mystery and adventure, with the light from behind the characters adding depth and intrigue. Prepare to be captivated by the promise of discovery.
Prompt
poses walking-away: Curious, excited ; A group of explorers with maps; wide shot; Adventure; Ancient ruins with a mysterious entrance; cinematic
Characteristic
Shot : A group of people are walking through a stone archway into an ancient temple.
Aesthetic Score : 0.7
Mood : mysterious, adventurous, hopeful
Quality
Entropy : 6.71
Noise : 104
Prompt Clip Score : 0.26
AI Evaluation
Likelihood of AI : 0.90
Image errors : The image has some minor artifacts, particularly around the edges of the figures.
Lost in the Neon Glow: A Woman Embraces the Future of VR
A young woman, captivated by the immersive world of virtual reality, stands bathed in the vibrant glow of neon lights. Her expression speaks of wonder and excitement, hinting at the playful and futuristic adventures that await within the digital realm.
Prompt
poses walking-away: Immersed, excited ; A gamer with a controller; close-up; Gaming; Virtual reality headset with a fantastical world displayed; cinematic
Characteristic
Shot : A young woman wearing a VR headset and headphones in a dimly lit room, likely a gaming room, with computer screens in the background.
Aesthetic Score : 0.7
Mood : futuristic, focused, playful
Quality
Entropy : 6.86
Noise : 82
Prompt Clip Score : 0.26
AI Evaluation
Likelihood of AI : 0.10
Image errors : No noticeable image artifacts or errors.
A Journey Begins: Mother and Child Embrace the Unknown
A nostalgic and hopeful scene unfolds on a train platform, where a mother and her child walk away from the camera, flanked by trains on either side. The composition evokes a sense of anticipation and mystery, leaving viewers wondering about their destination and the future that awaits them.
Prompt
poses walking-away: Emotional, bittersweet ; A family with luggage; long shot; Travel; Train station platform with a departing train in the distance; cinematic
Characteristic
Shot : A mother and child are walking away from the camera on a train platform. The trains are on either side of the platform.
Aesthetic Score : 0.7
Mood : tranquil, hopeful, family
Quality
Entropy : 6.67
Noise : 87
Prompt Clip Score : 0.25
AI Evaluation
Likelihood of AI : 0.20
Image errors : There are no visible artifacts or errors in the image.
Conclusion
The results show that the generative AI model performed well in terms of camera position and shot analysis, but struggled with aesthetic analysis.
Here’s a breakdown:
- Camera Position: The model scored 0.5, which is considered good. This means the model was able to accurately capture the camera position described in the prompt.
- Shot Analysis: The model scored 0.57, also considered good. This indicates the model understood the scene described in the prompt and created an image that reflects that understanding.
- Aesthetic Analysis: The model scored 0.05, which is not very good. This suggests that the generated image did not match the expected aesthetic style described in the prompt.
Overall, the model demonstrates a good understanding of camera position and shot composition, but needs improvement in capturing the desired aesthetic.
Sources:
- https://www.writerswrite.co.za/cheat-sheets-for-writing-body-language/
- https://mads3df.wordpress.com/2013/09/04/storytelling-poses/
- https://www.pinterest.com/pegasister890/character-poses/
- https://www.youtube.com/watch?v=udky6ANxWws
- https://maven.com/articles/storytelling-techniques
- https://www.scenario.com