AI Captures Dramatic Poses, But Struggles with Camera Angles with Flux-dev
- 9 minutes read - 1744 wordsTable of Contents
Dramatic poses are a powerful tool in visual storytelling, conveying emotion and action through the positioning of the human body. From heroic stances to moments of despair, these poses have the ability to draw the viewer in and evoke a range of feelings. This blog post explores the use of AI in generating images with dramatic poses, analyzing its strengths and weaknesses in capturing the essence of these powerful visual elements.
Created with: flux-dev
Silhouetted Hero at Sunset
A lone figure in a red cape stands on a cliff, their silhouette stark against the fiery sunset. The city skyline stretches out behind them, creating a dramatic and contemplative scene. The flowing cape and heroic pose evoke a sense of power and mystery.
Prompt
poses falling: Epic, desperate, hopeful ; A lone figure in a tattered cape; wide shot; Heroism; A burning city skyline; cinematic
Characteristic
Shot : A silhouetted figure stands atop a rocky outcrop, draped in a red cape, against a backdrop of a city skyline bathed in the golden glow of a setting sun.
Aesthetic Score : 0.6
Mood : dramatic, heroic, contemplative
Quality
Entropy : 6.60
Noise : 67
Prompt Clip Score : 0.23
AI Evaluation
Likelihood of AI : 0.20
Image errors : Some minor noise is visible, particularly around the edges of the figure and the cape.
Silhouetted Climber Defies the Mist
A lone figure, silhouetted against a misty cliff face, embarks on a daring climb. The dramatic use of light and shadow creates a sense of mystery and adventure, highlighting the scale of the challenge and the climber’s unwavering determination.
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 lone figure in silhouette, rappelling down a steep, rocky cliff face. The background is obscured by mist and greenery, creating an atmosphere of mystery and isolation.
Aesthetic Score : 0.6
Mood : dramatic, adventurous, mysterious
Quality
Entropy : 6.76
Noise : 77
Prompt Clip Score : 0.29
AI Evaluation
Likelihood of AI : 0.10
Image errors : The image appears to be slightly overexposed, and the colors are somewhat muted. The climber’s silhouette is somewhat lacking in detail. The overall composition feels a little static.
Leap of Faith: A Futuristic Cityscape in Motion
A stylized 3D character, clad in a vibrant red jacket, soars through a colorful urban canyon. The scene bursts with energy and playful futurism, capturing the thrill of movement and action.
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 3D rendered image of a character in a red jacket jumping in between tall buildings.
Aesthetic Score : 0.6
Mood : futuristic, playful, whimsical
Quality
Entropy : 6.76
Noise : 88
Prompt Clip Score : 0.31
AI Evaluation
Likelihood of AI : 1.00
Image errors : The image has some artifacts and errors, such as aliasing around the edges of the character and buildings. The lighting is also not very realistic, making the scene look a bit artificial.
Soaring Serenity: A Hot Air Balloon Adventure Above Majestic Mountains
Experience the breathtaking beauty of a hot air balloon ride against a backdrop of towering mountains. This serene scene evokes a sense of peace and adventure, capturing the grandeur of the balloon and the vastness of the landscape.
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 is floating in the air over mountains, other balloons can be seen in the distance
Aesthetic Score : 0.8
Mood : peaceful, serene, adventurous
Quality
Entropy : 6.47
Noise : 59
Prompt Clip Score : 0.28
AI Evaluation
Likelihood of AI : 0.10
Image errors : No visible errors, just slight compression artifacts.
Daredevil Takes the Plunge: Man Jumps Off Mountain Cliff
An adrenaline-fueled adventure unfolds as a man leaps from a towering cliff, the rushing river below adding to the excitement. This daring feat captures the essence of adventure and the thrill of pushing boundaries.
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 hiker in a red jacket and a green backpack leaps off a cliff, with his arms outstretched, facing a stunning mountain valley scene with a river in the distance. The mountains in the background are green and lush, with a cloudy sky overhead.
Aesthetic Score : 0.7
Mood : adventurous, free, exhilarating
Quality
Entropy : 6.71
Noise : 78
Prompt Clip Score : 0.26
AI Evaluation
Likelihood of AI : 0.20
Image errors : There is a slight blur to the hiker, particularly the legs. The river in the distance is not very clear.
Leap of Faith: Friends Embrace the Exhilaration of a Cliff Jump
Three friends take the plunge, silhouetted against a breathtaking backdrop of azure sky and turquoise ocean. Their carefree leap captures the adventurous spirit and exhilarating thrill of the moment, creating a dramatic scene of grandeur and scale.
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 : Three people are jumping off a cliff into the ocean, with a large wave breaking in the foreground.
Aesthetic Score : 0.7
Mood : adventurous, exciting, carefree
Quality
Entropy : 6.60
Noise : 93
Prompt Clip Score : 0.28
AI Evaluation
Likelihood of AI : 0.10
Image errors : No notable errors
Superman Soars Above the City in Epic Display
A dramatic shot captures Superman in flight, his silhouette piercing the fog against a backdrop of a sprawling cityscape. The upward camera angle emphasizes his heroic stature and the epic scale of the moment.
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 : Superman flying through a foggy city, with a dramatic pose and red cape billowing behind him
Aesthetic Score : 0.6
Mood : epic, dramatic, heroic
Quality
Entropy : 6.83
Noise : 70
Prompt Clip Score : 0.30
AI Evaluation
Likelihood of AI : 0.80
Image errors : The image appears to have some artifacts in the fog and around the figure. There are some unrealistic features such as the lack of detail in the city.
Tiny Figures Against a Majestic Backdrop: Climbers Brave the Mountainside
A breathtaking scene unfolds as four climbers descend a sheer rock face, their small figures dwarfed by the towering mountain range behind them. The vastness of the landscape emphasizes the danger of their adventure, while the serene mood suggests a sense of awe and accomplishment.
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 : Four climbers are rappelling down a steep, rocky cliff face. In the background, there is a dramatic mountain range with a large snow-capped peak.
Aesthetic Score : 0.8
Mood : adventurous, dramatic, peaceful
Quality
Entropy : 6.43
Noise : 92
Prompt Clip Score : 0.29
AI Evaluation
Likelihood of AI : 0.10
Image errors : The image appears to be slightly overexposed, and there is some noise in the shadows.
A Mystical Journey Beckons
A solitary figure ventures down a path shrouded in enchantment, drawn towards a radiant light at its end. The scene evokes a sense of wonder and mystery, hinting at a destination filled with possibility and magic.
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 lone figure walks through a mystical forest path bathed in ethereal light, surrounded by lush foliage
Aesthetic Score : 0.8
Mood : mysterious, magical, serene
Quality
Entropy : 6.74
Noise : 106
Prompt Clip Score : 0.29
AI Evaluation
Likelihood of AI : 0.80
Image errors : Some blurring and artifacts in the background leaves, potentially due to AI generation
Dreamy European Village Soars with Hot Air Balloon
A whimsical scene of a hot air balloon gracefully floating over a charming European village, with colorful houses and cobblestone streets. The balloon adds a touch of magic and a sense of scale to the dreamy, nostalgic atmosphere.
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 floats above a quaint European town, with colorful buildings and lush greenery.
Aesthetic Score : 0.7
Mood : serene, whimsical, charming
Quality
Entropy : 6.64
Noise : 84
Prompt Clip Score : 0.29
AI Evaluation
Likelihood of AI : 0.20
Image errors : Slight blurriness and pixelation visible in the image.
Conclusion
The results show that the generative AI model performed well in terms of understanding the scene and camera position, but struggled with the aesthetic aspect. Here’s a breakdown:
- Camera Position: The model scored 0.48, which is below the “good” range of 0.5 to 0.75. This suggests that the model didn’t perfectly capture the intended camera positions described in the prompt.
- Shot Analysis: The model scored 0.62, falling within the “good” range. This indicates that the model was able to understand the scene and create a shot that was generally consistent with the prompt.
- Aesthetic Analysis: The model scored 0.1, which is within the “very good” range of -0.2 to 0.1. This means that the generated image’s aesthetic was very close to the expected aesthetic described in the prompt.
Overall, the model demonstrated a good understanding of the scene and shot composition, but could improve its ability to accurately capture the intended camera positions. The model’s ability to create an image with the desired aesthetic is a strong point.
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://fal.ai/models/fal-ai/flux/dev/api