AI Captures the Essence of Poses, But Struggles with the Aesthetics with Imagen-v3
- 9 minutes read - 1856 wordsTable of Contents
Dramatic poses are a powerful tool in visual storytelling, conveying emotions and narratives through body language. They are often used in photography, film, and art to create impactful and memorable images. This analysis explores the ability of a generative AI model to understand and recreate these dramatic poses, focusing on its performance in capturing camera position, shot analysis, and aesthetic style.
Created with: imagen-v3
Hope Amidst the Ruins: A Lone Figure Walks Towards the Sunset
A solitary figure, cloaked in mystery, strides through the remnants of a fallen city as the sun sets, casting a warm glow on the scene. The image evokes a sense of dramatic hope and melancholic beauty, suggesting a journey of resilience and a yearning for a brighter future.
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 figure walks through the ruins of a city at sunset. The sun is setting in the background, casting a warm glow on the scene. The figure is wearing a long cloak and is walking towards the light.
Aesthetic Score : 0.7
Mood : dramatic, melancholic, hopeful
Quality
Entropy : 6.77
Noise : 80
Prompt Clip Score : 0.33
AI Evaluation
Likelihood of AI : 0.80
Image errors : The image has a slight blur, making it appear somewhat artificial.
Into the Green Unknown: A Journey Begins
A solitary figure stands at the edge of a lush jungle path, bathed in dappled sunlight. The air is thick with mystery and the promise of adventure. Where will this path lead?
Prompt
poses walking-away: Intrigued, determined, anticipation ; A lone figure, backpack slung low, stands at the edge of a dense jungle. Sunlight filters through the canopy, illuminating a hidden path leading deeper into the emerald green.; cinematic
Characteristic
Shot : A single person stands on a path in a lush green jungle. The path leads into the dense foliage, and the sunlight filters through the trees creating a dappled effect on the ground.
Aesthetic Score : 0.7
Mood : mysterious, adventurous, serene
Quality
Entropy : 5.91
Noise : 92
Prompt Clip Score : 0.34
AI Evaluation
Likelihood of AI : 0.60
Image errors : The image has some minor artifacts, such as the edges of the leaves being slightly jagged. The person’s figure is also slightly blurred.
Neon Glow, Intense Focus: A Gamer’s World
A young man is lost in the digital realm, his face illuminated by the vibrant glow of neon lights. The dimly lit room adds to the sense of intensity and mystery, capturing the focused energy of a gamer in their element.
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 man is sitting in a dimly lit room with neon lights, playing a video game on a computer.
Aesthetic Score : 0.6
Mood : intense, focused, futuristic
Quality
Entropy : 6.44
Noise : 72
Prompt Clip Score : 0.33
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image has some slight noise and graininess, especially in the darker areas. This could be due to the low lighting conditions or the compression used to save the image. The neon lights are slightly overexposed, creating a halo effect.
Lost in a European Romance
A couple strolls hand-in-hand down a charming cobblestone street, their silhouettes fading into the distance. The warm glow of the yellow buildings and the romantic atmosphere create a sense of nostalgia and intrigue.
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 : A couple is walking away from the camera down a cobblestone street in a European city. The buildings on either side of the street are old and have a yellow facade.
Aesthetic Score : 0.6
Mood : romantic, nostalgic, cozy
Quality
Entropy : 6.88
Noise : 103
Prompt Clip Score : 0.34
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image is slightly blurry, especially in the background. The color saturation is a little bit too high, making the image look unnatural.
Silhouetted Figure, Awaiting Departure
A solitary man walks towards a distant plane on a muted, overcast tarmac. The silhouetted figure and the plane’s presence evoke a sense of melancholy, loneliness, and anticipation. The scene suggests a journey into the unknown, leaving behind a life that is perhaps filled with regret or longing.
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 lone man walks towards a plane on a tarmac, carrying a suitcase. The sky is overcast and muted.
Aesthetic Score : 0.7
Mood : melancholy, lonely, contemplative
Quality
Entropy : 6.58
Noise : 76
Prompt Clip Score : 0.30
AI Evaluation
Likelihood of AI : 0.10
Image errors : No noticeable errors.
Sunset Friends: A Celebration of Joy and Laughter
Capture the essence of carefree friendship with this heartwarming scene. A group of friends run along a beach at sunset, their laughter echoing in the golden light. The warm glow of the setting sun creates a romantic backdrop, highlighting the joyful mood of the moment.
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 : A group of friends are running along a beach at sunset, laughing and holding hands.
Aesthetic Score : 0.7
Mood : joyful, carefree, celebratory
Quality
Entropy : 6.91
Noise : 103
Prompt Clip Score : 0.32
AI Evaluation
Likelihood of AI : 0.20
Image errors : No noticeable artifacts or errors.
A Solitary Figure Vanishes into the Mist
A lone, armored figure, cloaked in shadow, walks a path shrouded in mist. The scene evokes a sense of mystery and adventure, leaving the viewer to wonder about the figure’s destination and purpose.
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 lone figure, clad in armor and a hooded cloak, walks along a forest path shrouded in mist.
Aesthetic Score : 0.7
Mood : mysterious, somber, adventurous
Quality
Entropy : 6.02
Noise : 96
Prompt Clip Score : 0.34
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image appears slightly blurry, and there’s a slight graininess in the background. The contrast could be improved.
Uncharted Territory: A Journey Begins
Four adventurers embark on a quest through a lush jungle, their path illuminated by the sun’s rays filtering through the canopy. The air crackles with anticipation as they approach a massive stone gateway, promising secrets and danger ahead. This captivating scene evokes the spirit of classic adventure films, with a touch of mystery and hope.
Prompt
poses walking-away: Curious, excited ; A group of explorers with maps; wide shot; Adventure; Ancient ruins with a mysterious entrance; cinematic
Characteristic
Shot : Four people are walking towards a large stone gateway in a jungle setting, the sun is shining through the trees and there is a sense of mystery and adventure in the air. The image has a classic Indiana Jones feel to it.
Aesthetic Score : 0.7
Mood : mysterious, adventurous, hopeful
Quality
Entropy : 6.41
Noise : 106
Prompt Clip Score : 0.32
AI Evaluation
Likelihood of AI : 0.70
Image errors : The image has some blurriness on the edges of the image, and some of the details in the background are not very clear. The characters’ faces are not visible, which is a bit of a missed opportunity to bring the image more alive.
Young Gamer Triumphs in Futuristic Cityscape
A young boy celebrates a victory in a futuristic video game, his excitement palpable against the backdrop of a fantastical alien cityscape. The image captures the thrill of achievement and the immersive world of science fiction gaming.
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 boy, standing in front of a large screen, celebrating a victory in a futuristic video game, as the screen displays a fantastical alien cityscape, possibly from a science fiction game.
Aesthetic Score : 0.6
Mood : exciting, futuristic, triumphant
Quality
Entropy : 6.89
Noise : 84
Prompt Clip Score : 0.28
AI Evaluation
Likelihood of AI : 0.80
Image errors : Some minor blurriness is noticeable in the alien cityscape and the boy’s figure, and there are slight inconsistencies in the lighting and shadows, particularly around the edges of the screen.
Waiting for the Unknown
A solitary figure stands on a train platform, suitcase in hand, his gaze fixed on the distance. The scene evokes a sense of melancholy and loneliness, as the man waits, seemingly lost in thought. The scattered luggage and the train in the background hint at a journey, but the uncertainty of his destination adds to the dramatic effect.
Prompt
poses walking-away: Melancholy, introspective ; A lone figure stands on a deserted train platform, their back to the camera, watching a departing train disappear into the distance. The platform is littered with abandoned luggage.; cinematic
Characteristic
Shot : A man is standing on a train platform with a suitcase, waiting for his train. He is looking away from the camera and is standing with a suitcase by his side. There are luggage bags scattered around the platform, and a train is in the background.
Aesthetic Score : 0.5
Mood : melancholy, lonely, reflective
Quality
Entropy : 6.10
Noise : 84
Prompt Clip Score : 0.34
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image is slightly blurry, and the colors are not very vivid.
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 0.45, which is considered good. This indicates that the model was able to accurately capture the camera position described in the prompt.
- Shot Analysis: The model also scored 0.45, which is good. This suggests that the model understood the scene described in the prompt and was able to create an image that reflected that understanding.
- Aesthetic Analysis: The model scored 0.1, which is considered very good. This means that the generated image closely matched the expected aesthetic style.
Overall, the model demonstrated a good understanding of the prompt’s instructions regarding camera position and shot composition. However, it struggled to fully capture 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://deepmind.google/technologies/imagen-3/