AI's Artistic Struggle: Capturing the Dramatic Pose with Freepik
- 9 minutes read - 1829 wordsTable of Contents
Dramatic poses are a powerful tool in storytelling, conveying emotion, action, and tension. They are often used in film, photography, and visual art to create a sense of drama and excitement. In this experiment, we tasked a generative AI model with creating images based on various dramatic poses and scenes. While the model demonstrated a good understanding of camera position and scene composition, it struggled to capture the desired aesthetic, highlighting the challenges of AI in replicating artistic nuances.
Created with: freepik
Hope Amidst the Ashes: A Lone Figure Stands Defiant in a Burning City
A solitary figure, cloaked in flames, gazes out at a cityscape consumed by fire. The dramatic contrast of light and shadow, the vibrant colors, and the hopeful stance of the figure create a powerful image of resilience in the face of destruction.
Prompt
poses falling: Epic, desperate, hopeful ; A lone figure in a tattered cape; wide shot; Heroism; A burning city skyline; cinematic
Characteristic
Shot : A lone figure in a cape stands amidst a burning city skyline. The figure is silhouetted against the fiery backdrop, with the flames licking at their feet. The city skyline is shrouded in smoke and haze, lending a sense of desolation and destruction to the scene.
Aesthetic Score : 0.8
Mood : dramatic, apocalyptic, solitary
Quality
Entropy : 6.78
Noise : 55
Prompt Clip Score : 0.24
AI Evaluation
Likelihood of AI : 0.80
Image errors : The flames and smoke in the background look slightly too uniform and unrealistic. The cityscape could be more detailed.
A Tightrope Walk Through the Mist
A lone figure navigates a treacherous tightrope high above a jungle canyon. The misty atmosphere and dramatic lighting create a sense of suspense and adventure, as the man’s determination shines through.
Prompt
poses falling: Suspenseful, thrilling, determined ; A lone explorer clinging to a rope ladder; close-up; Adventure; A vast, misty jungle canyon; cinematic
Characteristic
Shot : A man is walking on a rope bridge in a jungle, with lush vegetation and mist in the background. He looks up in a tense and determined expression, adding drama to the scene.
Aesthetic Score : 0.7
Mood : adventurous, daring, intense
Quality
Entropy : 6.82
Noise : 62
Prompt Clip Score : 0.30
AI Evaluation
Likelihood of AI : 0.30
Image errors : No significant image errors are observed.
Neon City Leap: A Futuristic Action Shot
A young woman, clad in a dark jacket and blue jeans, defies gravity with a daring leap over a city street. The futuristic cityscape, bathed in vibrant pink and blue neon lights, creates a dynamic and action-packed scene. The contrast of light and dark, the woman’s powerful movement, and the perspective of the city all contribute to a dramatic and captivating image.
Prompt
poses falling: Energetic, chaotic, playful ; A pixelated character plummeting through a digital landscape; medium shot; Gaming; A neon-lit cityscape with glowing buildings; cinematic
Characteristic
Shot : A woman in a cyberpunk-style city, jumping in the air over a street with neon signs and blurred cars.
Aesthetic Score : 0.8
Mood : futuristic, action, edgy
Quality
Entropy : 6.80
Noise : 67
Prompt Clip Score : 0.32
AI Evaluation
Likelihood of AI : 0.90
Image errors : Some slight artifacts and blurriness in the background.
Soaring Serenity: A Hot Air Balloon Ride Over Majestic Mountains
Experience the breathtaking beauty of a hot air balloon journey over a valley nestled amidst snow-capped peaks. The serene atmosphere and panoramic views evoke a sense of adventure and wonder, leaving you feeling peaceful and inspired.
Prompt
poses falling: Exhilarating, awe-inspiring, carefree ; A hot air balloon basket with tourists; long shot; Tourism; A breathtaking view of a mountain range with snow-capped peaks; cinematic
Characteristic
Shot : A hot air balloon with passengers is flying over a valley with snow-capped mountains in the background. The sky is clear and blue.
Aesthetic Score : 0.7
Mood : peaceful, adventurous, serene
Quality
Entropy : 6.71
Noise : 81
Prompt Clip Score : 0.34
AI Evaluation
Likelihood of AI : 0.30
Image errors : There are no noticeable artifacts or errors.
Precarious Climb: A Man’s Adventurous Journey
A hiker, backpack in tow, clings to a rocky path, his surprised expression hinting at the danger he faces. The breathtaking valley below, with its cascading waterfall, adds to the sense of adventure and suspense. This image captures the thrill and potential peril of exploring the wild.
Prompt
poses falling: Adrenaline-fueled, chaotic, humorous ; A backpacker tumbling down a rocky hillside; close-up; Travel; A lush green valley with a winding river; cinematic
Characteristic
Shot : A man is crawling on a rocky path in a mountainous landscape, looking over his shoulder with a surprised expression. A waterfall is visible in the distance, and a river winds its way through the valley.
Aesthetic Score : 0.7
Mood : adventure, suspense, playful
Quality
Entropy : 6.71
Noise : 76
Prompt Clip Score : 0.32
AI Evaluation
Likelihood of AI : 0.10
Image errors : The image appears to have some slight noise and artifacting, particularly in the background.
Five Friends Embrace the Power of the Ocean
A breathtaking scene of five individuals standing on a cliff edge, their hands intertwined as they gaze out at the dramatic ocean below. The crashing waves and vast expanse create a sense of awe and adventure, highlighting the power of nature and the strength of human connection.
Prompt
poses falling: Heart-stopping, terrifying, bonding ; A group of friends holding hands, falling from a cliff; wide shot; Groups; A dramatic ocean coastline with crashing waves; cinematic
Characteristic
Shot : A group of five friends stand on a cliff overlooking the ocean, with large waves crashing against the rocks below.
Aesthetic Score : 0.7
Mood : adventurous, awe-inspiring, dramatic
Quality
Entropy : 6.68
Noise : 90
Prompt Clip Score : 0.32
AI Evaluation
Likelihood of AI : 0.30
Image errors : The image is slightly blurry and could benefit from more sharpening.
Heroic Flight Through a City in Flames
A powerful superhero, possibly Superman, soars through a devastated city engulfed in fire and smoke. The dramatic scene evokes a sense of intensity and heroism, leaving viewers on the edge of their seats.
Prompt
poses falling: Dramatic, heroic, determined ; A superhero in mid-air, falling towards a collapsing building; close-up; Heroism; A cityscape with smoke and debris; cinematic
Characteristic
Shot : A superhero, likely Superman, is flying through the air over a destroyed city. There are fires and smoke in the background, and the city appears to be in ruins. The superhero is in mid-air, with his cape billowing behind him.
Aesthetic Score : 0.7
Mood : dramatic, intense, heroic
Quality
Entropy : 6.82
Noise : 56
Prompt Clip Score : 0.29
AI Evaluation
Likelihood of AI : 0.80
Image errors : The image appears to have some minor artifacts, particularly in the smoke and fire. The overall lighting is also a little flat.
Conquering the Peak: Climbers Embrace the Epic Challenge
A team of climbers, roped together and clad in bright orange, ascend a steep rock face. The breathtaking vista behind them showcases distant mountains, valleys, and a winding river, creating a sense of awe and adventure. This image captures the essence of their daring climb, highlighting the precariousness of their position and the immense accomplishment they strive for.
Prompt
poses falling: Thrilling, adventurous, daring ; A group of adventurers rappelling down a sheer rock face; long shot; Adventure; A towering mountain peak with a breathtaking view; cinematic
Characteristic
Shot : A group of climbers are ascending a steep rock face, with a stunning mountain vista in the background. The climbers are equipped with ropes and harnesses, and they appear to be making good progress.
Aesthetic Score : 0.8
Mood : adventure, majestic, awe-inspiring
Quality
Entropy : 6.55
Noise : 88
Prompt Clip Score : 0.28
AI Evaluation
Likelihood of AI : 0.10
Image errors : The image contains no visible artifacts or errors.
Enchanted Forest: A Woman Glows with Mystical Power
A young woman stands bathed in pink energy, radiating magic in a whimsical forest. The twilight scene, filled with vibrant flowers and blurred background, creates an atmosphere of wonder and mystery, drawing the viewer’s eye to her captivating presence.
Prompt
poses falling: Magical, surreal, exciting ; A player character falling through a virtual world; medium shot; Gaming; A vibrant, fantastical landscape with glowing flora; cinematic
Characteristic
Shot : A young woman with red hair stands in a magical forest. She is surrounded by glowing pink energy and flowers.
Aesthetic Score : 0.75
Mood : fantasy, whimsical, powerful
Quality
Entropy : 6.69
Noise : 68
Prompt Clip Score : 0.30
AI Evaluation
Likelihood of AI : 0.80
Image errors : Some blurriness around the woman’s hair, likely from post-processing
Soaring Above a Quaint European Town
Experience the serenity and adventure of a hot air balloon ride over a charming European town. Imagine the wonder and awe as you float above rows of red-tiled houses, taking in the idyllic scenery.
Prompt
poses falling: Romantic, nostalgic, heartwarming ; A family in a hot air balloon, falling towards a picturesque village; long shot; Tourism; A charming village with cobblestone streets and colorful houses; cinematic
Characteristic
Shot : A hot air balloon carrying passengers flies over a picturesque village with red-tiled roofs and lush greenery.
Aesthetic Score : 0.7
Mood : peaceful, adventurous, whimsical
Quality
Entropy : 6.64
Noise : 77
Prompt Clip Score : 0.30
AI Evaluation
Likelihood of AI : 0.20
Image errors : Some minor artifacts are present in the sky around the balloon. There is a slight blur in the background, possibly due to motion or depth of field.
Conclusion
The results show that the generative AI model performed well in understanding the scene and camera position, but struggled with the aesthetic aspect. Here’s a breakdown:
- Camera Position: The model scored 4.5/10, indicating a moderate understanding of the camera position specified in the prompt. This suggests the model is able to capture the general camera angle and perspective, but may not be perfectly aligned with the desired position.
- Shot Analysis: The model scored 5.9/10, indicating a good understanding of the scene described in the prompt. This means the model was able to create an image that closely matches the overall composition and elements of the scene.
- Aesthetic Analysis: The model scored 0.4/10, indicating a poor performance in capturing the desired aesthetic. This suggests the generated image deviates significantly from the expected aesthetic style, potentially lacking the desired mood, color palette, or overall visual appeal.
Overall, the model demonstrates a good understanding of the scene and camera position, 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.freepik.com