AI's Artistic Struggle: Capturing the Perfect Pose with Midjourney
- 8 minutes read - 1692 wordsTable of Contents
In the realm of artificial intelligence, the ability to generate images based on textual descriptions is a rapidly evolving field. While impressive progress has been made, there are still challenges in capturing the nuances of visual composition, particularly when it comes to conveying dramatic poses. This blog post delves into the results of a generative AI model tasked with creating images based on specific descriptions, focusing on its ability to capture camera position, shot composition, and aesthetic style. Through this analysis, we gain valuable insights into the strengths and limitations of current AI models in translating complex visual instructions.
Created with: midjourney
Lost in the Mist: A Solitary Figure Walks into the Unknown
A lone figure, shrouded in a dark cloak, traverses a desolate path through a misty, mountainous landscape. The overcast sky and the figure’s silhouette against the backdrop create a sense of mystery and isolation, leaving the viewer to ponder their journey and destination. This evocative image evokes feelings of loneliness, melancholy, and intrigue.
Prompt
running running: determined, hopeful ; A lone figure in a tattered cloak; wide shot; Heroism; a desolate wasteland with a storm brewing in the distance; cinematic
Characteristic
Shot : A lone figure in a black cloak walks away from the camera on a path through a desolate landscape with a mountain range in the distance and a muted sky overhead.
Aesthetic Score : 0.7
Mood : mysterious, lonely, dramatic
Quality
Entropy : 6.30
Noise : 103
Prompt Clip Score : 0.26
AI Evaluation
Likelihood of AI : 0.20
Image errors : There are no visible errors in the image.
Unveiling the Secrets of the Jungle Temple
A lone woman ventures through a lush, overgrown jungle towards a mysterious stone temple. The moody atmosphere and her determined stride promise an adventure filled with intrigue and discovery.
Prompt
running running: excited, curious ; A young adventurer with a backpack; medium shot; Adventure; a lush jungle with ancient ruins in the background; cinematic
Characteristic
Shot : A woman walks towards an ancient temple ruins in the jungle, with greenery, moss, and stone structures around. There is a mist or fog in the air, adding to the mysterious atmosphere.
Aesthetic Score : 0.7
Mood : mysterious, adventurous, ancient
Quality
Entropy : 6.63
Noise : 111
Prompt Clip Score : 0.31
AI Evaluation
Likelihood of AI : 0.20
Image errors : No obvious artifacts or errors in the image.
Blurred Intensity: Capturing the Thrill of Gaming
This image captures the raw energy of gaming, with a dynamic red and blue scene, intense lighting, and a strong blur effect that emphasizes the speed and movement of the action. The mood is electric, reflecting the player’s focus and the intensity of the game.
Prompt
running running: intense, focused ; A gamer’s hands on a keyboard and mouse; close-up; Gaming; a brightly lit gaming room with a monitor displaying a virtual world; cinematic
Characteristic
Shot : A person’s hands typing on a keyboard with a computer screen in the background. The screen is displaying a game or image with bright red and blue lights.
Aesthetic Score : 0.6
Mood : intense, futuristic, energetic
Quality
Entropy : 6.86
Noise : 100
Prompt Clip Score : 0.25
AI Evaluation
Likelihood of AI : 0.50
Image errors : The lighting creates harsh shadows, and some blurring, especially on the screen, makes the scene less clear.
Lost in the Labyrinth of Color: A Day at the Market
A bustling outdoor market comes alive with vibrant colors and the energy of a thousand stories. Sunlight bathes the scene in a warm glow, while the backlighting and narrow depth of field create a sense of mystery as shoppers disappear into the colorful maze.
Prompt
running running: energetic, joyful ; A group of tourists running through a bustling marketplace; long shot; Tourism; a vibrant marketplace with colorful stalls and vendors; cinematic
Characteristic
Shot : A group of people are walking down a narrow street lined with shops, the street is full of colorful fabrics and decorations. There is a sense of vibrancy and energy.
Aesthetic Score : 0.6
Mood : vibrant, colorful, busy
Quality
Entropy : 6.63
Noise : 93
Prompt Clip Score : 0.27
AI Evaluation
Likelihood of AI : 0.10
Image errors : The image has some slight compression artifacts, but they are not very noticeable.
Hand in Hand, Lost in the Moment
A couple strolls along a pristine beach, their love story unfolding against the backdrop of a serene ocean. The high angle shot captures their intimacy and isolation, creating a sense of romantic bliss and carefree abandon.
Prompt
running running: romantic, carefree ; A couple running hand-in-hand along a beach; medium shot; Travel; a beautiful beach with turquoise water and white sand; cinematic
Characteristic
Shot : A couple is walking hand-in-hand along a sandy beach, with the ocean waves crashing in the background.
Aesthetic Score : 0.8
Mood : romantic, serene, peaceful
Quality
Entropy : 5.91
Noise : 113
Prompt Clip Score : 0.25
AI Evaluation
Likelihood of AI : 0.10
Image errors : No visible errors or artifacts
Sun-Kissed Joy: A Tranquil Run Through the Park
Capture the essence of a carefree day with this image of a group running through a sun-drenched park. The warm light and vibrant greenery create a sense of tranquility and cheerfulness, while the active scene evokes a feeling of energy and vitality.
Prompt
running running: happy, playful ; A group of friends running through a park; wide shot; Groups; a sunny park with green grass and trees; cinematic
Characteristic
Shot : A group of people running through a park, a large tree in the foreground, the sun shining through the leaves.
Aesthetic Score : 0.6
Mood : peaceful, active, happy
Quality
Entropy : 6.65
Noise : 117
Prompt Clip Score : 0.29
AI Evaluation
Likelihood of AI : 0.20
Image errors : No major errors or artifacts
Superman’s Blurred Fury: A Hero in Motion
Witness the raw power of Superman as he streaks through the city at incredible speed, leaving a trail of motion blur in his wake. This dynamic image captures the hero’s strength and determination, creating a sense of awe and excitement.
Prompt
running running: powerful, confident ; A superhero in a bright costume; close-up; Heroism; a city skyline with skyscrapers and flashing lights; cinematic
Characteristic
Shot : Superman running through a city at super speed
Aesthetic Score : 0.6
Mood : heroic, action, dynamic
Quality
Entropy : 6.78
Noise : 91
Prompt Clip Score : 0.27
AI Evaluation
Likelihood of AI : 0.80
Image errors : The image appears to be digitally rendered, and the motion blur is slightly artificial.
A Runner’s Solitude Amidst Majestic Peaks
A lone figure traverses a snowy mountain valley, dwarfed by the towering, snow-capped peaks. The scene evokes a sense of serenity, vastness, and adventure, highlighting the human spirit’s resilience against the grandeur of nature.
Prompt
running running: determined, adventurous ; A lone explorer running through a snow-covered mountain pass; long shot; Adventure; a majestic mountain range with snow-capped peaks; cinematic
Characteristic
Shot : A lone runner in a vast snowy valley framed by towering, snow-capped mountains. The scene is bright with a slight blue tint, creating a serene atmosphere.
Aesthetic Score : 0.8
Mood : serene, vast, adventurous
Quality
Entropy : 6.52
Noise : 99
Prompt Clip Score : 0.28
AI Evaluation
Likelihood of AI : 0.10
Image errors : None
A Woman Races Through a Glowing, Fantastical Forest
Experience the wonder and excitement of a mystical journey through a surreal forest. Lush vegetation and glowing trees create an otherworldly atmosphere, while the woman’s running figure adds a sense of urgency and adventure.
Prompt
running running: immersive, exciting ; A gamer’s avatar running through a virtual world; close-up; Gaming; a vibrant and detailed virtual world with fantastical creatures; cinematic
Characteristic
Shot : A woman runs through a glowing, fantastical forest path.
Aesthetic Score : 0.7
Mood : magical, mysterious, surreal
Quality
Entropy : 6.69
Noise : 110
Prompt Clip Score : 0.26
AI Evaluation
Likelihood of AI : 0.80
Image errors : There is a slight blurring and artificiality to the image, particularly noticeable in the woman’s hair and the foliage.
Chasing the Sunset: A Family’s Tranquil Adventure
A heartwarming scene of a family running down a winding rural road, bathed in the golden light of the setting sun. The image evokes feelings of tranquility, hope, and adventure, capturing the essence of a perfect family moment.
Prompt
running running: happy, carefree ; A family running along a scenic road; medium shot; Travel; a winding road with rolling hills and a picturesque countryside; cinematic
Characteristic
Shot : A family of four runs along a winding country road, with rolling hills and a golden sunset in the background.
Aesthetic Score : 0.8
Mood : serene, hopeful, joyful
Quality
Entropy : 6.63
Noise : 108
Prompt Clip Score : 0.34
AI Evaluation
Likelihood of AI : 0.20
Image errors : No visible artifacts or errors
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 0.4, which is considered below average. This suggests that the model didn’t accurately capture the intended camera position described in the prompt.
- Shot Analysis: The model scored 0.495, which is also below average. This indicates that the model didn’t fully understand the scene and its elements as described in the prompt.
- Aesthetic Analysis: The model scored 0.09, which is considered very good. This means that the generated image closely matched the expected aesthetic style.
Overall, the model seems to be better at capturing the desired aesthetic than understanding the camera position and shot composition. This suggests that the model might need further training to improve its ability to interpret and translate complex visual instructions.
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