AI's Artistic Struggle: Capturing the Essence of Poses with Midjourney
- 10 minutes read - 1953 words
Table of Contents
In the realm of artificial intelligence, the ability to generate images that capture the essence of human expression and emotion remains a significant challenge. This blog post delves into the results of an experiment where an AI model was tasked with generating images based on specific poses and scenes. While the model demonstrates a good grasp of camera positioning and shot composition, it falls short in capturing the intended aesthetic, highlighting the ongoing challenges in AI’s artistic development. Dramatic style poses, often used in photography and film, aim to convey a sense of emotion, action, or narrative through the positioning of the subject’s body. These poses are often used to create a sense of drama, tension, or excitement, and can be found in a variety of contexts, from fashion photography to action movies. This experiment aimed to assess the AI model’s ability to understand and recreate these dramatic poses, capturing the intended emotion and narrative.
Created with: midjourney
Lost in the Stars: Astronauts Reflect on the Vastness of Space
Two astronauts, their helmets reflecting the celestial tapestry, stand against a backdrop of deep blue and twinkling stars. The image evokes a sense of awe, mystery, and the profound isolation of human existence in the vast universe.
Prompt
forehead-to-forehead forehead-to-forehead, gazing at the stars: awe, determination, camaraderie ; Two astronauts; close-up; heroism; the vast, dark expanse of space with stars twinkling in the distance; cinematic
Characteristic
Shot : Two astronauts in space suits, facing each other, against a backdrop of stars and a nebula. The helmets are reflective, showing images of the spacecraft’s interior and the surrounding cosmos.
Aesthetic Score : 0.8
Mood : mysterious, hopeful, futuristic
Quality
Entropy : 6.50
Noise : 121
Prompt Clip Score : 0.27
AI Evaluation
Likelihood of AI : 0.10
Image errors : The painting appears to be free of significant errors.
Lost in the Green: A Moment of Mystery and Intimacy
Two figures, silhouetted against the sun-drenched foliage, stand face-to-face in a dense forest. Their backpacks suggest adventure, while the backlighting creates a sense of mystery and intimacy, hinting at a story waiting to unfold.
Prompt
forehead-to-forehead forehead-to-forehead, looking at each other with determination: excitement, anticipation, trust ; A seasoned explorer and a young adventurer; medium shot; adventure; a dense jungle with sunlight filtering through the canopy; cinematic
Characteristic
Shot : A man and a woman, both wearing backpacks and hiking gear, are standing face-to-face in a lush, tropical forest. Sunbeams pierce through the dense canopy, creating a dramatic effect. The couple appears to be lost in thought, their expressions unreadable.
Aesthetic Score : 0.7
Mood : mysterious, romantic, adventurous
Quality
Entropy : 6.09
Noise : 95
Prompt Clip Score : 0.28
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image is slightly overexposed, resulting in a loss of detail in the highlights. The overall image is also somewhat blurry.
The Codebreakers: A Glimpse into the Heart of the Digital Battlefield
Two young men, bathed in the stark glow of blue and red light, hunched over a computer screen. Their expressions are intense, focused, and serious, hinting at a world of code and competition. The close-up shot and dramatic lighting create a sense of mystery and intrigue, leaving you wondering what secrets they are unlocking.
Prompt
forehead-to-forehead forehead-to-forehead, eyes locked on the screen: intense focus, concentration, friendly rivalry ; Two gamers; close-up; gaming; a brightly lit gaming room with multiple monitors displaying a competitive game; cinematic
Characteristic
Shot : Two young men in a dimly lit room, possibly a gaming room or an office, looking intently at a screen.
Aesthetic Score : 0.6
Mood : intense, focused, serious
Quality
Entropy : 6.09
Noise : 70
Prompt Clip Score : 0.24
AI Evaluation
Likelihood of AI : 0.30
Image errors : The image appears to be slightly overexposed, and the colors are a bit too saturated. There is also some minor graininess.
Lost in the Clouds: A Romantic Escape on a Mountaintop
A couple embraces the breathtaking vista from a mountain peak, enveloped in a sea of clouds and fog. The dramatic lighting and snow-capped mountains in the distance create a sense of mystery and isolation, perfect for a romantic and contemplative moment.
Prompt
forehead-to-forehead forehead-to-forehead, gazing at the scenery: romance, wonder, shared experience ; A couple; medium shot; tourism; a breathtaking view of a mountain range with clouds swirling around the peaks; cinematic
Characteristic
Shot : A couple stands on a mountaintop looking out over a misty valley, with snow-capped peaks in the distance.
Aesthetic Score : 0.7
Mood : romantic, serene, adventurous
Quality
Entropy : 6.33
Noise : 109
Prompt Clip Score : 0.28
AI Evaluation
Likelihood of AI : 0.10
Image errors : No noticeable artifacts or errors.
Love in the Midst of Chaos: An Intimate Embrace at the Train Station
In this romantic and candid scene, a couple shares a tender moment amidst the hustle and bustle of a busy train station. The background is beautifully blurred, creating a sense of privacy and intimacy, while the dramatic effect highlights the couple’s connection, making them the sole focus of the image.
Prompt
forehead-to-forehead forehead-to-forehead, looking at each other with smiles: excitement, anticipation, camaraderie ; A group of friends; wide shot; travel; a bustling airport terminal with people rushing around; cinematic
Characteristic
Shot : A couple in love, embracing in a bustling train station, the background is blurred, creating a sense of intimacy and privacy amidst the chaos.
Aesthetic Score : 0.7
Mood : romantic, intimate, candid
Quality
Entropy : 6.61
Noise : 96
Prompt Clip Score : 0.27
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image exhibits some noise and slight graininess, especially in the background, likely due to low light conditions.
A Moment of Majesty: Hiker Meets Mountain Goat in Breathtaking Landscape
Experience the awe-inspiring beauty of a majestic mountain landscape as a lone hiker encounters a mountain goat. The contrast between the vastness of the mountains and the small figures creates a sense of scale and wonder, capturing a serene and adventurous mood.
Prompt
forehead-to-forehead forehead-to-forehead, looking at each other with curiosity: respect, connection with nature, shared journey ; A lone hiker and a mountain goat; close-up; adventure; a rugged mountain trail with snow-capped peaks in the background; cinematic
Characteristic
Shot : A man with a backpack stands on a mountain path, looking at a white mountain goat.
Aesthetic Score : 0.7
Mood : tranquil, awe-inspiring, adventurous
Quality
Entropy : 6.74
Noise : 119
Prompt Clip Score : 0.32
AI Evaluation
Likelihood of AI : 0.30
Image errors : The image has a slightly overexposed sky and the colors are a little too saturated.
Brotherhood in the Face of War: Two Soldiers Share a Moment of Vulnerability
Amidst the chaos of a war zone, two American soldiers stand close, their faces marked with blood and dirt, reflecting the intensity and despair of their situation. The dim lighting and smoke-filled background heighten the sense of urgency and danger, while the intimacy between the soldiers creates a poignant moment of vulnerability amidst the chaos.
Prompt
forehead-to-forehead forehead-to-forehead, looking at each other with unwavering resolve: determination, camaraderie, sacrifice ; A group of soldiers; medium shot; heroism; a battlefield with smoke and explosions in the distance; cinematic
Characteristic
Shot : Two soldiers, one on each side of the frame, are facing each other with their helmets touching. They are both covered in dirt and blood, and there is a sense of intensity and tension in the air. The background is blurry and indistinct, suggesting that they are in the midst of a battle. A canteen is partially visible in the foreground.
Aesthetic Score : 0.7
Mood : dramatic, intense, somber
Quality
Entropy : 6.67
Noise : 101
Prompt Clip Score : 0.29
AI Evaluation
Likelihood of AI : 0.10
Image errors : The image quality is good, with no noticeable artifacts or errors.
Lost in the Sands of Time
Two figures, clad in desert garb, stand silhouetted against the vast, barren landscape. Ancient ruins peek out in the distance, hinting at a forgotten past. The air is thick with mystery and adventure, beckoning the viewer to explore the unknown.
Prompt
forehead-to-forehead forehead-to-forehead, looking at the ruins with wonder: curiosity, discovery, shared purpose ; Two explorers; close-up; adventure; a vast desert landscape with ancient ruins in the distance; cinematic
Characteristic
Shot : Two women in desert garb stand looking out over a vast desert landscape. In the distance, there are ancient ruins or temples.
Aesthetic Score : 0.7
Mood : mysterious, adventurous, contemplative
Quality
Entropy : 6.24
Noise : 74
Prompt Clip Score : 0.25
AI Evaluation
Likelihood of AI : 0.80
Image errors : There are some slight artifacts in the image, particularly around the edges of the figures and the ruins.
Concert Spotlight: A Night of Excitement and Hope
Capture the energy of a vibrant concert with dramatic spotlights illuminating a cheering crowd. This scene evokes feelings of excitement, hope, and celebration, making it a perfect visual for a memorable event.
Prompt
forehead-to-forehead forehead-to-forehead, singing along to the music: joy, excitement, shared experience ; A group of friends; wide shot; groups; a crowded concert venue with flashing lights and music pulsating; cinematic
Characteristic
Shot : A concert stage with a large crowd of people in the front, the stage is lit by bright spotlights with confetti and fog creating a dramatic effect.
Aesthetic Score : 0.7
Mood : exciting, energetic, vibrant
Quality
Entropy : 6.12
Noise : 101
Prompt Clip Score : 0.22
AI Evaluation
Likelihood of AI : 0.10
Image errors : There is some noise in the image. The image could be sharper.
Tranquil Romance on the Cliffside
A couple stands hand-in-hand, gazing out at the endless turquoise ocean. The back view captures their awe and wonder as they embrace the peaceful beauty of the moment.
Prompt
forehead-to-forehead forehead-to-forehead, looking at the ocean with smiles: happiness, togetherness, relaxation ; A family; medium shot; travel; a scenic beach with turquoise water and white sand; cinematic
Characteristic
Shot : A couple is silhouetted against a beautiful turquoise ocean with whitecaps in the distance. The sky is a soft blue with wispy clouds.
Aesthetic Score : 0.7
Mood : romantic, tranquil, serene
Quality
Entropy : 6.39
Noise : 75
Prompt Clip Score : 0.23
AI Evaluation
Likelihood of AI : 0.10
Image errors : The image is slightly overexposed and the colors are a bit washed out.
Conclusion
The results show that the generative AI model performed well in understanding the camera position and shot composition, but struggled with the aesthetic aspect.
Here’s a breakdown:
- Camera Position: The model scored 0.44, which is slightly below the “good” range of 0.5 to 0.75. This suggests that the model’s ability to accurately interpret and recreate the camera position specified in the prompt is moderate.
- Shot Analysis: The model scored 0.53, which falls within the “good” range. This indicates that the model was able to understand and implement the shot type described in the prompt with a decent level of accuracy.
- Aesthetic Analysis: The model scored 0.08, which is significantly lower than the “very good” range of -0.2 to 0.1. This suggests that the generated image’s aesthetic deviated considerably from the expected aesthetic based on the prompt.
Overall, the model demonstrates a good understanding of camera position and shot composition, but needs improvement in generating images that align with 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://midjourney.com