AI's Artistic Struggle: Capturing the Essence of Poses with Freepik
- 9 minutes read - 1906 wordsTable of Contents
In the realm of artificial intelligence, the ability to generate images based on textual prompts is a rapidly evolving field. This blog post delves into the results of an experiment where an AI model was tasked with creating images based on specific poses and scenes. While the model demonstrated proficiency in understanding camera positions and shot types, it fell short in capturing the intended aesthetic, highlighting the ongoing challenges in AI’s artistic capabilities. This exploration sheds light on the nuances of AI-generated imagery and the importance of human artistic intuition in achieving truly compelling visual narratives.
Created with: freepik
Contemplating the Vastness: A Man Finds Solitude on a Mountain Peak
A solitary figure sits on a rocky mountain edge, gazing out at a winding road snaking through a valley. The scene evokes a sense of serenity and adventure, highlighting the man’s connection with the powerful and vast mountain landscape.
Prompt
poses crossed-legs: determined, contemplative ; A lone adventurer, sitting on a cliff edge; wide shot; Adventure; a vast, breathtaking mountain range; cinematic
Characteristic
Shot : A man is sitting on a cliff overlooking a valley with winding roads. The mountains are in the background and the sky is clear.
Aesthetic Score : 0.75
Mood : tranquil, contemplative, serene
Quality
Entropy : 6.74
Noise : 62
Prompt Clip Score : 0.25
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image appears slightly soft, especially in the subject. The background is a little blurry.
One Warrior Stands Against the Flames
A lone warrior, clad in golden armor, stands defiant amidst a scene of fiery destruction. The epic mood and dramatic juxtaposition of the warrior and the flames create a powerful and intense image.
Prompt
poses crossed-legs: triumphant, confident ; A victorious warrior, standing tall on a battlefield; medium shot; Heroism; fallen enemies and a burning city in the background; cinematic
Characteristic
Shot : A lone warrior in golden armor stands amidst a fiery battlefield, his sword drawn. The background shows a city in ruins with smoke billowing in the sky.
Aesthetic Score : 0.7
Mood : epic, dramatic, heroic
Quality
Entropy : 6.84
Noise : 57
Prompt Clip Score : 0.26
AI Evaluation
Likelihood of AI : 0.80
Image errors : There are some minor artifacts in the smoke and flames, suggesting it may be digitally created. The warrior’s armor also appears a bit too perfect and smooth, lacking the texture and wear one would expect from a battle-hardened soldier.
Lost in the Game: A Gamer’s Intense Focus Under Dim Lights
A young man, headphones on, is completely immersed in his video game. The dimly lit room adds to the dramatic effect, highlighting his intense concentration and the thrill of the game.
Prompt
poses crossed-legs: intense, focused ; A gamer, intensely focused on a screen; close-up; Gaming; a dimly lit room with glowing monitors and gaming peripherals; cinematic
Characteristic
Shot : A young man is sitting at a desk in a dimly lit room, wearing a headset and looking intently at a computer screen. He is playing a video game. There is a keyboard and mouse in front of him, and a large computer monitor is behind him. The room is decorated with gaming-related items.
Aesthetic Score : 0.6
Mood : focused, intense, competitive
Quality
Entropy : 6.48
Noise : 46
Prompt Clip Score : 0.26
AI Evaluation
Likelihood of AI : 0.10
Image errors : The image has some noise in the shadows, particularly in the upper left corner. There is also some blurring in the background, which is likely due to the low light.
Sunset Cityscape: Friends Embrace the View
A group of friends bask in the golden hour on a rooftop, their laughter echoing against the backdrop of a sprawling cityscape. The scene captures the joy of friendship, the thrill of adventure, and the awe-inspiring beauty of urban life at sunset.
Prompt
poses crossed-legs: excited, awe-struck ; A group of tourists, admiring a breathtaking view; medium shot; Tourism; a panoramic vista of a bustling city skyline; cinematic
Characteristic
Shot : A group of young adults are sitting on a rooftop overlooking a city skyline at sunset. The image is focused on the people, but the cityscape is also prominent in the background.
Aesthetic Score : 0.7
Mood : youthful, carefree, adventurous
Quality
Entropy : 6.77
Noise : 69
Prompt Clip Score : 0.29
AI Evaluation
Likelihood of AI : 0.10
Image errors : The image is slightly blurry, especially in the background. Some of the subjects are not in focus. There is a bit of noise in the image. There is a bit of chromatic aberration.
Lost in Thought: A Moment of Contemplation on a Moving Train
A young woman sits by the window of a train, her gaze fixed on a passing train and the blurry landscape beyond. The contrast between her focused expression and the fleeting scenery evokes a sense of melancholy and contemplation, capturing a moment of quiet introspection amidst the rush of travel.
Prompt
poses crossed-legs: reflective, nostalgic ; A traveler, gazing out of a train window; close-up; Travel; a blur of passing landscapes and towns; cinematic
Characteristic
Shot : A young woman sits by the window of a train looking out at the passing scenery.
Aesthetic Score : 0.6
Mood : melancholy, thoughtful, nostalgic
Quality
Entropy : 6.83
Noise : 60
Prompt Clip Score : 0.29
AI Evaluation
Likelihood of AI : 0.10
Image errors : There are no visible errors in the image.
Campfire Nights: Laughter, Light, and Cozy Vibes
A group of friends gather around a crackling campfire, bathed in the warm glow of the flames and twinkling string lights. The scene exudes a sense of cozy festivity and happiness, with the darkness of the forest adding a touch of mystery.
Prompt
poses crossed-legs: joyful, relaxed ; A group of friends, laughing and sharing stories around a campfire; medium shot; Groups; a serene forest setting with twinkling stars above; cinematic
Characteristic
Shot : A group of friends are sitting around a campfire in a forest at night. There are fairy lights strung up in the trees, creating a warm and inviting atmosphere. The fire is crackling and the friends are laughing and talking.
Aesthetic Score : 0.7
Mood : warm, inviting, happy
Quality
Entropy : 6.44
Noise : 68
Prompt Clip Score : 0.28
AI Evaluation
Likelihood of AI : 0.10
Image errors : No noticeable errors
A Moment of Awe: An Astronaut Gazes at Earth from Space
This breathtaking image captures the profound solitude and wonder experienced by an astronaut looking out at our planet from the vast expanse of space. The astronaut’s perspective highlights the fragility and beauty of Earth, leaving viewers with a sense of awe and a renewed appreciation for our home.
Prompt
poses crossed-legs: awe-inspired, contemplative ; A lone astronaut, gazing at Earth from a spaceship window; close-up; Heroism; a vast, blue planet against the backdrop of space; cinematic
Characteristic
Shot : An astronaut is looking out a porthole at Earth. The Earth appears as a blue sphere with white clouds, with the sun shining brightly in the upper right corner of the image.
Aesthetic Score : 0.8
Mood : awe, wonder, solitude
Quality
Entropy : 6.69
Noise : 69
Prompt Clip Score : 0.27
AI Evaluation
Likelihood of AI : 0.80
Image errors : The Earth’s surface appears somewhat unrealistic, and the astronaut’s face is not very detailed. The reflection in the helmet is not realistic, appears very blurry.
Shadows Dance in the Cave: A Gathering of Adventurers
Four figures huddle in the flickering light of torches, their faces etched with determination. The air crackles with suspense as they face an unknown challenge in the depths of a mysterious cave. Will they find glory or succumb to the darkness?
Prompt
poses crossed-legs: suspenseful, cautious ; A group of explorers, huddled together in a dark cave; medium shot; Adventure; flickering torches illuminating the rough stone walls; cinematic
Characteristic
Shot : Four people are huddled together inside a cave, illuminated by flickering torches, creating an atmosphere of suspense and exploration.
Aesthetic Score : 0.6
Mood : mysterious, suspenseful, adventurous
Quality
Entropy : 6.54
Noise : 75
Prompt Clip Score : 0.32
AI Evaluation
Likelihood of AI : 0.30
Image errors : There are no visible errors or artifacts in the image.
Confetti Shower of Joy
A young man, radiating pure happiness, sits amidst a flurry of confetti, his arms raised in victory. The scene captures the essence of celebration and excitement, with the man’s infectious smile reflecting the joy of the moment.
Prompt
poses crossed-legs: exuberant, joyful ; A gamer, celebrating a victory with a triumphant fist pump; close-up; Gaming; a brightly lit room with a celebratory confetti explosion; cinematic
Characteristic
Shot : A young man is sitting on the floor, surrounded by confetti, with a joyful expression on his face, celebrating a victory.
Aesthetic Score : 0.7
Mood : joyful, celebratory, ecstatic
Quality
Entropy : 6.85
Noise : 62
Prompt Clip Score : 0.31
AI Evaluation
Likelihood of AI : 0.10
Image errors : The image is slightly blurry, especially in the background.
Street Food Feast: A Vibrant Scene of Friends and Flavors
Capture the energy of a bustling Asian street food market with this vibrant image. A group of friends enjoys a meal, surrounded by the sights and sounds of the city. The warm lighting and dynamic perspective create a sense of adventure and excitement.
Prompt
poses crossed-legs: lively, adventurous ; A group of travelers, sharing a meal at a bustling street market; medium shot; Travel; vibrant colors and aromas of exotic food stalls; cinematic
Characteristic
Shot : A group of people are eating at a street food market in a city. The image captures the energy and excitement of the market, with the people enjoying their food and the food itself looking delicious. There are lots of food stalls and vendors in the background.
Aesthetic Score : 0.7
Mood : vibrant, lively, social
Quality
Entropy : 6.87
Noise : 83
Prompt Clip Score : 0.29
AI Evaluation
Likelihood of AI : 0.10
Image errors : No visible errors, maybe some minor noise in the background.
Conclusion
The results show that the generative AI model performed well in terms of camera position and shot analysis, but struggled with aesthetic analysis. Here’s a breakdown:
- Camera Position: The model scored 0.45, which is slightly below the “good” range of 0.5 to 0.75. This suggests that the model’s ability to accurately interpret and reproduce camera positions in the prompt is decent, but could be improved.
- Shot Analysis: The model scored 0.51, which falls within the “good” range. This indicates that the model is generally able to understand the scene described in the prompt and create images that reflect the intended shot type.
- Aesthetic Analysis: The model scored 0.06, which is significantly lower than the “very good” range of -0.2 to 0.1. This suggests that the generated image’s aesthetic deviated significantly from the expected aesthetic based on the prompt.
Overall, the model demonstrates a good understanding of camera positions and shot types, but needs improvement in generating images that match 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