AI's Artistic Journey: Capturing Poses, But Missing the Mood with Freepik
- 9 minutes read - 1871 words
Table of Contents
In the realm of artificial intelligence, the ability to generate realistic and visually appealing images has become a fascinating area of exploration. One key aspect of image generation is the ability to capture the essence of a pose, conveying the mood and emotion of the subject. This blog post delves into an experiment that tested the capabilities of a generative AI model in creating images based on specific poses and scenes. While the model demonstrated impressive capabilities in understanding camera angles and shot composition, it fell short in capturing the intended aesthetic. We will explore the model’s strengths and weaknesses, analyzing its performance in different scenarios and discussing the potential for future improvements.
Created with: freepik
Silhouetted Against the Setting Sun: A Moment of Freedom in the Desert
A man leaps into the air, his silhouette a stark contrast against the fiery sunset over the vast desert landscape. This image captures the essence of adventure, freedom, and joy, with the dramatic lighting adding a touch of wonder and awe.
Prompt
poses jumping: Excitement, freedom ; A lone adventurer; wide shot; Adventure; a vast, sun-drenched desert landscape; cinematic
Characteristic
Shot : A man is jumping in the air, mid-leap, in a desert landscape at sunset. The sun is behind him and slightly out of frame. He is wearing a backpack. The sand is a warm color and there are hills in the distance.
Aesthetic Score : 0.7
Mood : joyful, adventurous, free
Quality
Entropy : 6.30
Noise : 39
Prompt Clip Score : 0.28
AI Evaluation
Likelihood of AI : 0.20
Image errors : No errors found.
Superhero Soars Over Dreamlike New York City
A heroic figure in a vibrant blue and red costume takes flight over a hazy cityscape, the iconic Empire State Building looming in the background. The dramatic pose and billowing cape evoke a sense of power and epic adventure, capturing the essence of a superhero’s heroic journey.
Prompt
poses jumping: Triumphant, powerful ; A superhero; close-up; Heroism; a cityscape with towering skyscrapers; cinematic
Characteristic
Shot : A superhero, perhaps Superman, in a dynamic pose, leaping from a rooftop with the city skyline in the background. The light is soft and warm, giving a heroic and hopeful feel.
Aesthetic Score : 0.7
Mood : heroic, hopeful, dramatic
Quality
Entropy : 6.88
Noise : 53
Prompt Clip Score : 0.27
AI Evaluation
Likelihood of AI : 0.80
Image errors : The image appears to be AI-generated, with some artifacts and inconsistencies in the textures and details. The shadows and highlights are not quite natural.
Friends Soaring High Against Majestic Peaks
Capture the joy and adventure of friendship with this vibrant photo. Four friends leap into the air, their smiles radiating pure happiness against the backdrop of a breathtaking mountain range. The low angle shot emphasizes their carefree spirit and the vastness of the natural world, creating a truly inspiring image.
Prompt
poses jumping: Joyful, carefree ; A group of friends; medium shot; Tourism; a scenic mountain vista with a breathtaking view; cinematic
Characteristic
Shot : Four friends are jumping in mid-air against the backdrop of a mountain range with a valley in the distance. The sky is bright and clear with some clouds. The mountain range is covered in snow.
Aesthetic Score : 0.7
Mood : joyful, carefree, adventurous
Quality
Entropy : 6.66
Noise : 58
Prompt Clip Score : 0.31
AI Evaluation
Likelihood of AI : 0.20
Image errors : No obvious artifacts or errors in the image.
Leap of Faith: A Futuristic Cityscape in Motion
A young man defies gravity, leaping through a bustling futuristic city street. The dynamic composition and blurred background create a sense of action and speed, capturing the energy of this vibrant urban landscape.
Prompt
poses jumping: Energetic, playful ; A video game character; close-up; Gaming; a vibrant, pixelated world; cinematic
Characteristic
Shot : A young man in casual clothing is jumping in mid-air, with a city background, the city has a futuristic feel with neon lights and towering buildings.
Aesthetic Score : 0.8
Mood : dynamic, action, futuristic
Quality
Entropy : 6.65
Noise : 57
Prompt Clip Score : 0.25
AI Evaluation
Likelihood of AI : 0.90
Image errors : The lighting seems a bit artificial, especially on the character. There is a slight blurring effect around the character that can be a bit distracting.
Taking Flight: A Moment of Joy in the Airport
A woman leaps into the air, capturing the essence of freedom and excitement against the backdrop of a bustling airport. The blurred background emphasizes her joyful energy, creating a dynamic contrast that speaks volumes about the moment.
Prompt
poses jumping: Anticipation, excitement ; A traveler; long shot; Travel; a bustling airport terminal with people rushing around; cinematic
Characteristic
Shot : A woman in a blue jacket and jeans jumps in an airport terminal, facing away from the camera, with her hair flowing behind her. There are other people in the background, but they are blurry and out of focus.
Aesthetic Score : 0.6
Mood : joyful, free, adventurous
Quality
Entropy : 6.71
Noise : 63
Prompt Clip Score : 0.33
AI Evaluation
Likelihood of AI : 0.10
Image errors : Some slight blurriness and graininess throughout the image, most noticeable in the background.
Capturing the Energy: Dancers Take Flight on Stage
A vibrant performance bursts with joy and energy, captured in this image. The dancer in the foreground, suspended in mid-air, embodies the dynamic movement and theatrical spirit of the show.
Prompt
poses jumping: Energetic, vibrant ; A group of dancers; medium shot; Groups; a brightly lit stage with a cheering audience; cinematic
Characteristic
Shot : A group of dancers performing on stage, one dancer is in the foreground, mid-air jump, other dancers are in the background. The stage is lit with warm lights. The background audience is blurry.
Aesthetic Score : 0.7
Mood : joyful, energetic, theatrical
Quality
Entropy : 6.85
Noise : 63
Prompt Clip Score : 0.25
AI Evaluation
Likelihood of AI : 0.20
Image errors : Some slight artifacts and noise on the dancer’s clothing and in the background.
Man Defies the Storm in a Dramatic Leap
A muscular man, clad in blue, leaps across a rain-soaked road, defying the fury of a raging thunderstorm. Lightning illuminates the sky, adding to the intensity of the moment. The image captures a powerful sense of drama and strength.
Prompt
poses jumping: Determined, courageous ; A lone figure; close-up; Heroism; a dark, stormy night with lightning flashing; cinematic
Characteristic
Shot : A muscular man in a blue jacket and pants jumps over a wet road with a bolt of lighting striking beneath his feet.
Aesthetic Score : 0.6
Mood : intense, dramatic, powerful
Quality
Entropy : 6.86
Noise : 52
Prompt Clip Score : 0.27
AI Evaluation
Likelihood of AI : 0.80
Image errors : The lighting looks artificial and the composition is a little cluttered. The man’s pose looks slightly unnatural.
Uncharted Territory: Explorers Brave the Jungle’s Mysteries
A group of young adventurers embark on a thrilling expedition through a dense jungle, their path leading towards an ancient stone structure shrouded in mist. The image captures the excitement and mystery of their journey, with dynamic movement and a sense of wonder.
Prompt
poses jumping: Curious, adventurous ; A group of explorers; wide shot; Adventure; a dense jungle with ancient ruins; cinematic
Characteristic
Shot : A group of young adventurers are walking through a lush, green jungle. The group consists of four boys and one girl. They are all dressed in explorer gear. The image is set in front of an ancient temple. The jungle is thick and misty, giving the scene a sense of mystery and adventure.
Aesthetic Score : 0.7
Mood : adventurous, mysterious, hopeful
Quality
Entropy : 6.77
Noise : 85
Prompt Clip Score : 0.29
AI Evaluation
Likelihood of AI : 0.20
Image errors : No significant errors detected. The image is well-composed and the lighting is good. The colors are vibrant and there is good contrast.
Empowered in the Digital Realm
A young woman, bathed in the glow of a futuristic interface, stands confidently in a darkened room. Her outstretched arm and intense focus suggest a moment of control and power within a technologically advanced world.
Prompt
poses jumping: Focused, intense ; A gamer; close-up; Gaming; a dimly lit room with a computer screen glowing; cinematic
Characteristic
Shot : A young woman in a casual outfit and headphones is standing in a dimly lit room with multiple computer monitors displaying digital information. She is reaching out with her right hand towards one of the monitors, as if manipulating the data on it.
Aesthetic Score : 0.6
Mood : futuristic, determined, focused
Quality
Entropy : 6.56
Noise : 54
Prompt Clip Score : 0.26
AI Evaluation
Likelihood of AI : 0.20
Image errors : There is some slight noise in the image, particularly in the shadows.
Silhouettes of Love: A Sunset Jump on the Beach
Capture the joy and romance of a couple’s playful moment as they jump in the air, silhouetted against a breathtaking sunset on a sandy beach. The wet sand and crashing waves add to the scene’s beauty and create a sense of carefree happiness.
Prompt
poses jumping: Romantic, carefree ; A couple; medium shot; Travel; a romantic sunset over a beach; cinematic
Characteristic
Shot : A couple jumps in the air on a beach at sunset, holding hands and looking at each other with smiles. The background is a golden sunset over the ocean, and the sand is soft and golden.
Aesthetic Score : 0.8
Mood : romantic, happy, carefree
Quality
Entropy : 6.69
Noise : 47
Prompt Clip Score : 0.29
AI Evaluation
Likelihood of AI : 0.30
Image errors : The image is slightly overexposed, which causes the sky to be washed out and the colors to be less vibrant. The couple’s limbs are slightly unnatural in pose.
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 0.48, which is considered okay. This means the generated image’s camera position was somewhat different from what was requested in the prompt.
- Shot Analysis: The model scored 0.595, which is considered good. This indicates the generated image’s shot composition was fairly close to what was requested in the prompt.
- Aesthetic Analysis: The model scored 0.05, which is considered okay. This means the generated image’s aesthetic was somewhat different from what was expected based on the prompt.
Overall, the model seems to be better at understanding the scene and shot composition than 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