AI's Artistic Struggle: Capturing the Essence of Poses with Freepik
- 10 minutes read - 1952 wordsTable of Contents
In the realm of artificial intelligence, the ability to generate images based on textual descriptions is a rapidly evolving field. One intriguing challenge is capturing the essence of poses, conveying not just the physical arrangement of limbs but also the emotions, actions, and overall aesthetic intended. This blog post delves into the results of an AI model tasked with generating images based on pose descriptions, exploring its strengths and weaknesses in understanding camera angles, scene composition, and aesthetic.
Created with: freepik
Contemplating the Vastness: A Hiker Finds Serenity on a Misty Mountain Peak
A lone hiker stands on a mountain summit, gazing out at a sprawling, misty valley. Dramatic clouds fill the sky, creating a breathtaking contrast with the bright expanse above. The scene evokes a sense of serenity, contemplation, and adventure, capturing the essence of a solitary journey amidst nature’s grandeur.
Prompt
poses ankle-cross: Determined, confident, facing the unknown ; A lone adventurer, standing atop a windswept mountain peak; wide shot; Adventure; Dramatic sky with swirling clouds; cinematic
Characteristic
Shot : A lone hiker stands on a mountain peak, looking out at a vast panorama of misty mountains.
Aesthetic Score : 0.7
Mood : serene, contemplative, adventurous
Quality
Entropy : 6.65
Noise : 69
Prompt Clip Score : 0.26
AI Evaluation
Likelihood of AI : 0.60
Image errors : The clouds and mountains have a slightly artificial look, as if they were rendered in a 3D program. There is some minor noise in the sky, which could be reduced with some post-processing.
Heroic Silhouette: A Sunset of Hope
A powerful superhero stands tall on a rooftop, bathed in the golden light of a setting sun. The city skyline stretches out below, a canvas for their heroic presence. This image captures a moment of anticipation and hope, as the hero prepares to face whatever challenges lie ahead.
Prompt
poses ankle-cross: Powerful, heroic, standing tall ; A superhero, silhouetted against a blazing sunset; medium shot; Heroism; City skyline with towering buildings; cinematic
Characteristic
Shot : Superman, standing on a rooftop with a cityscape in the background, at sunset.
Aesthetic Score : 0.7
Mood : heroic, dramatic, powerful
Quality
Entropy : 6.81
Noise : 41
Prompt Clip Score : 0.28
AI Evaluation
Likelihood of AI : 0.90
Image errors : The image has some minor artifacts around the edges of Superman’s suit and the cityscape. The city lights in the background are also a bit too uniform.
Lost in the Neon Glow: A Cyberpunk Gamer’s Paradise
A young woman, captivated by the virtual world, sits amidst a vibrant cyberpunk gaming room bathed in neon light. Her expression speaks of wonder and curiosity, hinting at the playful adventures that await within the digital realm.
Prompt
poses ankle-cross: Immersed, concentrated, in the zone ; A gamer, intensely focused on a virtual reality headset; close-up; Gaming; Futuristic, neon-lit gaming room; cinematic
Characteristic
Shot : A young woman wearing a VR headset sits on the floor of a brightly lit gaming room. The room is decorated with neon lights and graffiti, and the woman looks focused on the virtual world.
Aesthetic Score : 0.7
Mood : futuristic, cyberpunk, immersive
Quality
Entropy : 6.58
Noise : 56
Prompt Clip Score : 0.28
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image is slightly blurry, especially in the background. There is some noise in the image, particularly in the shadows.
Lost in Time: A Moment of Serenity Amidst Ancient Ruins
A young woman finds peace and contemplation as she gazes upon an ancient city, its ruins whispering tales of a bygone era. The serene landscape and her solitary pose evoke a sense of nostalgia and tranquility.
Prompt
poses ankle-cross: Awe-struck, contemplative, taking in the beauty ; A tourist, gazing out at a breathtaking vista; medium shot; Tourism; Ancient ruins with a panoramic view; cinematic
Characteristic
Shot : A young woman sits on stone steps in front of ancient ruins, gazing out at a scenic landscape. The image captures a sense of peace and tranquility.
Aesthetic Score : 0.7
Mood : serene, contemplative, nostalgic
Quality
Entropy : 6.66
Noise : 73
Prompt Clip Score : 0.31
AI Evaluation
Likelihood of AI : 0.20
Image errors : No visible errors
Lost in the Desert’s Embrace
A solitary figure traverses the endless expanse of sand, leaving behind a trail of footprints that whisper tales of adventure and contemplation. The vastness of the desert evokes a sense of isolation and wonder, inviting the viewer to ponder the journey ahead.
Prompt
poses ankle-cross: Free-spirited, adventurous, embracing the unknown ; A backpacker, standing at the edge of a vast desert; wide shot; Travel; Endless sand dunes stretching into the horizon; cinematic
Characteristic
Shot : A lone woman walks on a sand dune in a desert. The dune stretches out ahead of her, leading to a horizon with distant mountains.
Aesthetic Score : 0.7
Mood : tranquil, adventurous, hopeful
Quality
Entropy : 5.56
Noise : 52
Prompt Clip Score : 0.26
AI Evaluation
Likelihood of AI : 0.20
Image errors : No obvious errors or artifacts detected.
Friends’ Night Out: Laughter and Light on a Cobblestone Street
A group of friends stroll down a charming cobblestone street, their laughter echoing under the warm glow of string lights and streetlamps. The scene captures the joy and camaraderie of a night out with friends, evoking a sense of nostalgia and happiness.
Prompt
poses ankle-cross: Joyful, carefree, enjoying each other’s company ; A group of friends, laughing and celebrating; medium shot; Groups; Vibrant, bustling street scene with colorful lights; cinematic
Characteristic
Shot : A group of young people laughing and walking down a city street at night. The street is lit up with string lights.
Aesthetic Score : 0.7
Mood : happy, carefree, youthful
Quality
Entropy : 6.82
Noise : 82
Prompt Clip Score : 0.28
AI Evaluation
Likelihood of AI : 0.20
Image errors : There are no significant image errors in the image. There are a few very small artifacts in the shadows around the feet, but these are minor and do not affect the overall quality of the image.
A Knight’s Solitary Journey to the Castle
A mysterious and epic scene unfolds as a knight in full armor stands on a stone pathway leading to a medieval castle. Backlit and isolated, he gazes towards the castle, leaving the viewer to wonder what awaits him within its walls. The perspective from the rear adds to the intrigue, creating a sense of anticipation and mystery.
Prompt
poses ankle-cross: Stoic, vigilant, protecting the realm ; A lone warrior, standing guard at a castle gate; medium shot; Heroism; Majestic castle with a moat and drawbridge; cinematic
Characteristic
Shot : A knight in full armor stands on a stone path leading up to a medieval castle, looking back at the viewer.
Aesthetic Score : 0.7
Mood : dramatic, epic, mysterious
Quality
Entropy : 6.83
Noise : 81
Prompt Clip Score : 0.33
AI Evaluation
Likelihood of AI : 0.80
Image errors : The stone path is a bit too perfectly symmetrical and the textures on the castle are a bit flat and unrealistic.
Whispers in the Mist: A Campfire Under a Mysterious Sky
A group of young adventurers gather around a crackling campfire, their faces illuminated by the dancing flames. The surrounding forest is shrouded in a thick mist, adding an air of mystery and contemplation to the scene. The dramatic contrast between the firelight and the dark background creates a sense of wonder and anticipation.
Prompt
poses ankle-cross: Intrigued, curious, sharing stories ; A group of explorers, huddled around a campfire; close-up; Adventure; Dense forest with flickering flames; cinematic
Characteristic
Shot : A group of young adults are gathered around a campfire in a forest, sitting on the ground and looking at the flames. The scene is dimly lit by the fire, and the trees are silhouetted in the background. The atmosphere is peaceful and contemplative.
Aesthetic Score : 0.7
Mood : mysterious, intimate, contemplative
Quality
Entropy : 6.80
Noise : 73
Prompt Clip Score : 0.30
AI Evaluation
Likelihood of AI : 0.30
Image errors : The image appears to be slightly over-exposed, and there is a slight amount of noise in the shadows.
Immersed in the Game: Joyful Gamer Lit by String Lights
A young man, radiating pure joy, sits on the floor in a dimly lit living room, string lights casting a warm glow. Headphones on, he excitedly raises his hands in front of the television, fully immersed in the thrill of his video game. The scene captures the energy and excitement of gaming, creating a sense of playful immersion.
Prompt
poses ankle-cross: Excited, victorious, celebrating success ; A gamer, triumphantly raising their hands after winning a game; close-up; Gaming; Brightly lit gaming console with flashing lights; cinematic
Characteristic
Shot : A man wearing headphones is sitting on the floor in front of a TV screen, he is cheering with his hands in the air, it looks like he is playing a video game. There are gaming controllers and a cushion on the floor next to him.
Aesthetic Score : 0.6
Mood : excited, joyful, playful
Quality
Entropy : 6.78
Noise : 55
Prompt Clip Score : 0.29
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image is slightly blurry in areas. There are some artifacts visible on the TV screen and on the floor.
A Night of Enchantment: A Couple’s Romantic Moment Overlooking the City
In this dreamy scene, a couple shares an intimate moment on a balcony overlooking a city at night. The twinkling city lights create a romantic ambiance, while the use of light and shadow adds a dramatic effect. The mood is set for a truly enchanting experience.
Prompt
poses ankle-cross: Intimate, romantic, enjoying the view together ; A couple, standing on a balcony overlooking a bustling city; medium shot; Travel; Romantic cityscape with twinkling lights; cinematic
Characteristic
Shot : A couple is standing on a balcony overlooking a city at night. They are looking at each other and seem to be in love. The city lights are twinkling in the background.
Aesthetic Score : 0.7
Mood : romantic, cozy, hopeful
Quality
Entropy : 6.79
Noise : 63
Prompt Clip Score : 0.32
AI Evaluation
Likelihood of AI : 0.60
Image errors : The background is a bit blurry, and the city lights appear slightly pixelated. The image overall lacks detail.
Conclusion
The results show that the generative AI model performed well in terms of understanding camera positions and scene composition, but struggled with achieving the desired aesthetic. Here’s a breakdown:
- Camera Position: The model scored 0.43, which is considered below average. This suggests that the model didn’t accurately translate the camera positions described in the prompt into the generated image.
- Shot Analysis: The model scored 0.5, which is considered average. This indicates that the model was able to understand the scene described in the prompt to a reasonable degree, but there’s room for improvement in accurately capturing the intended shot.
- Aesthetic Analysis: The model scored 0.08, which is considered poor. This means that the generated image’s aesthetic significantly deviated from the expected aesthetic described in the prompt.
Overall, the model needs improvement in accurately capturing the desired camera positions and aesthetic. While it shows some understanding of the scene, it needs to be trained further to better translate the prompt’s instructions into a visually appealing image.
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