AI's Artistic Journey: Capturing the Essence of Poses with Midjourney
- 10 minutes read - 1963 wordsTable of Contents
Dramatic poses are a powerful tool in visual storytelling, conveying emotions, actions, and relationships. From the heroic stance of a lone figure to the dynamic energy of a group, poses can add depth and impact to any image. In this blog post, we’ll explore how AI models are learning to understand and generate these dramatic poses, analyzing their strengths and weaknesses in capturing the desired aesthetic and camera angles. We’ll use examples from a recent experiment to illustrate how AI is evolving in its ability to translate textual prompts into visually compelling images.
Created with: midjourney
A Solitary Figure in a City of Ruins
A lone figure stands on a rocky outcrop, gazing out at a ruined cityscape bathed in the golden light of a setting sun. The scene evokes a sense of melancholy and solitude, with the figure’s isolation highlighting the vastness of the destruction. The image captures the beauty of decay and the haunting silence of a lost civilization.
Prompt
looking-back Looking back at the ruins with a determined expression: 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 stands on a rocky outcrop overlooking a ruined city at sunset.
Aesthetic Score : 0.7
Mood : melancholy, ominous, contemplative
Quality
Entropy : 6.67
Noise : 111
Prompt Clip Score : 0.25
AI Evaluation
Likelihood of AI : 0.80
Image errors : The edges of the city skyline are slightly jagged, and the figure’s cloak is slightly blurred.
Unveiling the Secrets of the Ancient Temple
A group of adventurers embark on a journey through a lush jungle, their path leading them towards a majestic temple complex shrouded in mystery. The sun bathes the scene in a warm glow, highlighting the scale and grandeur of the ancient ruins. This inspiring image captures the spirit of adventure and the allure of the unknown.
Prompt
looking-back Looking back at the path they’ve traveled, their faces filled with wonder: Excited, adventurous ; A group of explorers; medium shot; Adventure; Lush jungle with ancient temples in the distance; cinematic
Characteristic
Shot : A group of people are walking through a jungle, heading towards a large ancient temple in the distance. The path is stone, and the temple is surrounded by trees.
Aesthetic Score : 0.7
Mood : adventurous, mysterious, serene
Quality
Entropy : 6.53
Noise : 122
Prompt Clip Score : 0.26
AI Evaluation
Likelihood of AI : 0.80
Image errors : There are some minor artifacts and blurriness around the edges of the image, particularly in the foliage.
Lost in the Code: A Hacker’s Focus Under Neon Lights
A close-up shot captures the intensity of a programmer working late into the night. The dimly lit room, bathed in pink and blue hues, creates a futuristic and mysterious atmosphere. The out-of-focus background emphasizes the isolation and focus on the task at hand, leaving the viewer to wonder what secrets are being unlocked within the code.
Prompt
looking-back Looking back at the screen, eyes glued to the action: Intense, focused ; A gamer’s hands on a keyboard; close-up; Gaming; Neon lights reflecting on the screen, displaying a virtual world; cinematic
Characteristic
Shot : A person is typing on a keyboard in front of a computer monitor. The screen shows code and data. The background is blurry and has a pink and blue neon glow.
Aesthetic Score : 0.7
Mood : cyberpunk, futuristic, intense
Quality
Entropy : 6.80
Noise : 106
Prompt Clip Score : 0.21
AI Evaluation
Likelihood of AI : 0.30
Image errors : There are some artifacts and noise in the background. Some parts of the image seem blurry and out of focus.
Conquering the Peak: A Moment of Inspiration
A lone hiker stands triumphant on a mountain summit, arms outstretched, embracing the breathtaking panorama of a snow-capped valley. The clear blue sky and vibrant colors evoke a sense of adventure and serenity, capturing the awe-inspiring beauty of nature.
Prompt
looking-back Looking back at the vast landscape, arms outstretched: Awe-inspiring, peaceful ; A lone traveler standing on a mountain peak; long shot; Tourism; Breathtaking panoramic view of a snow-capped mountain range; cinematic
Characteristic
Shot : A lone hiker stands on a mountain peak with his arms outstretched, overlooking a vast and breathtaking valley with snow-capped mountains in the distance. The sky is a bright blue with fluffy white clouds.
Aesthetic Score : 0.8
Mood : serene, adventurous, inspiring
Quality
Entropy : 6.78
Noise : 112
Prompt Clip Score : 0.25
AI Evaluation
Likelihood of AI : 0.10
Image errors : The image is slightly over-saturated, and the colors are a bit too vibrant, giving it a slightly artificial look.
Epic Sunset Ride Through the Desert
A steam locomotive train races through a sun-drenched desert landscape, its smoke and dust trailing behind as it rounds a bend. The dramatic high-angle shot captures the train’s journey against a backdrop of towering rock formations and a vibrant orange sky, evoking a sense of adventure and nostalgia.
Prompt
looking-back Looking back at the receding city, a sense of longing in their eyes: Nostalgic, adventurous ; A vintage train speeding through a desert landscape; medium shot; Travel; Sun setting over the horizon, casting long shadows; cinematic
Characteristic
Shot : A steam train is travelling through a desert landscape at sunset. The train is on a curved track and the sun is setting behind it. The train is giving off steam from the engine. There are large rocks in the distance.
Aesthetic Score : 0.7
Mood : nostalgic, adventurous, dramatic
Quality
Entropy : 6.48
Noise : 83
Prompt Clip Score : 0.24
AI Evaluation
Likelihood of AI : 0.80
Image errors : The image appears to have some rendering artifacts, particularly in the foreground. The sand appears to be flat and unrealistic, and the train has a slight blur in places, as though it has been rendered at low resolution.
Laughter and Graffiti: A Day of Joyful Friendship
A group of friends stroll down a vibrant street, their laughter echoing against a backdrop of colorful graffiti. The contrast between the muted tones of their clothing and the bold artwork creates a visually captivating scene, capturing the essence of carefree joy and shared camaraderie.
Prompt
looking-back Looking back at a memorable moment, their faces lit with laughter: Joyful, carefree ; A group of friends laughing and talking; medium shot; Groups; A bustling city street with vibrant street art; cinematic
Characteristic
Shot : Three young adults are standing in front of a colorful graffiti wall, laughing and enjoying each other’s company. The vibrant colors of the wall create a fun and energetic atmosphere.
Aesthetic Score : 0.7
Mood : joyful, playful, carefree
Quality
Entropy : 6.58
Noise : 77
Prompt Clip Score : 0.17
AI Evaluation
Likelihood of AI : 0.10
Image errors : No visible errors
A Moment of Solitude in the Vastness of Space
An astronaut floats amidst the inky blackness of space, a tiny speck against the backdrop of a breathtaking Earth. The image evokes a sense of melancholy, awe, and profound solitude, highlighting the astronaut’s isolation and the overwhelming scale of the cosmos.
Prompt
looking-back Looking back at Earth, a sense of wonder and responsibility in their eyes: Awe-inspiring, contemplative ; A lone astronaut floating in space; long shot; Heroism; Earth hanging in the distance, a blue marble against the black void; cinematic
Characteristic
Shot : An astronaut floats in space with the Earth below them.
Aesthetic Score : 0.7
Mood : lonely, serene, mysterious
Quality
Entropy : 3.11
Noise : 48
Prompt Clip Score : 0.26
AI Evaluation
Likelihood of AI : 0.80
Image errors : The stars in the background appear to be a bit too evenly spaced and lack natural variation. The Earth’s surface lacks depth and realism.
Adrenaline Rush: Whitewater Rafting Adventure
Experience the thrill of whitewater rafting as a raft is tossed around in the rapids, capturing the intense and adventurous spirit of the sport. The image evokes a sense of excitement and danger, showcasing the raw power of nature.
Prompt
looking-back Looking back at the rapids they’ve just navigated, adrenaline coursing through their veins: Thrilling, exhilarating ; A group of adventurers on a raft; medium shot; Adventure; Rapids churning whitewater, a sense of danger and excitement; cinematic
Characteristic
Shot : Four people in a raft going down rapids. The water is churning and splashing.
Aesthetic Score : 0.6
Mood : intense, adventurous, thrilling
Quality
Entropy : 6.54
Noise : 110
Prompt Clip Score : 0.26
AI Evaluation
Likelihood of AI : 0.10
Image errors : Slight blurriness, particularly on the water. Color balance is a bit off, especially in the sky.
A Moment of Solitude on the Mountaintop
A lone hiker stands in awe of the majestic snow-capped peaks, finding peace and inspiration in the vastness of the mountain landscape. The scene evokes a sense of tranquility and the journey of self-discovery.
Prompt
looking-back Looking back at the challenges they’ve overcome, a sense of pride in their eyes: Triumphant, accomplished ; A gamer’s avatar standing on a virtual mountain peak; close-up; Gaming; A vast, fantastical landscape stretching out before them; cinematic
Characteristic
Shot : A lone figure stands on a mountain peak, gazing at a majestic snow-capped mountain range in the distance. The sky is a bright blue with fluffy clouds, and the sun is shining.
Aesthetic Score : 0.75
Mood : serene, inspiring, adventurous
Quality
Entropy : 6.52
Noise : 72
Prompt Clip Score : 0.27
AI Evaluation
Likelihood of AI : 0.90
Image errors : The painting style is a bit cartoonish and the colors are a bit saturated. The textures could be more detailed and realistic.
Silhouettes of Love Against a Fiery Sunset
A couple stands hand-in-hand, their silhouettes stark against the vibrant hues of a sunset over a tranquil beach. The scene evokes a sense of romance, serenity, and hope, with the dramatic effect of the silhouette adding to the emotional impact.
Prompt
looking-back Looking back at the setting sun, their silhouettes framed against the fiery sky: Romantic, peaceful ; A couple walking hand-in-hand on a beach; long shot; Tourism; Sunset painting the sky in vibrant hues of orange and pink; cinematic
Characteristic
Shot : A couple silhouetted against a fiery sunset, standing on a beach at the edge of the water.
Aesthetic Score : 0.7
Mood : romantic, serene, melancholic
Quality
Entropy : 6.45
Noise : 111
Prompt Clip Score : 0.26
AI Evaluation
Likelihood of AI : 0.10
Image errors : The image is slightly blurred, especially in the foreground.
Conclusion
The results show that the generative AI model performed moderately well in understanding and executing the prompt. Here’s a breakdown:
- Camera Position: The model scored 0.3, indicating a below average ability to accurately interpret and reproduce the intended camera position. This suggests the generated image may not have the desired perspective or angle.
- Shot Analysis: The model scored 0.52, indicating a good understanding of the scene described in the prompt. This means the generated image likely captures the overall composition and elements of the scene as intended.
- Aesthetic Analysis: The model scored 0.05, indicating a very good ability to match the expected aesthetic. This means the generated image likely has a visual style that closely aligns with the desired aesthetic.
Overall, the model demonstrates a good understanding of the scene and its aesthetic, but struggles with accurately capturing the intended camera position.
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://midjourney.com