AI Captures the Essence of Poses, But Struggles with Aesthetics with Imagen-v3-fast
- 9 minutes read - 1773 wordsTable of Contents
Dramatic style poses are a powerful tool in visual storytelling, used to convey emotion, action, and character. From the iconic superhero stance to the contemplative pose of a lone traveler, these poses have the ability to capture the essence of a scene and evoke a specific feeling in the viewer. In this blog post, we explore the capabilities of a generative AI model in creating images based on dramatic poses, analyzing its performance in terms of camera position, shot analysis, and aesthetic interpretation.
Created with: imagen-v3-fast
Leap of Joy: Man Embraces the Desert Sun
A man soars through the air, arms outstretched, against a backdrop of endless desert and a brilliant sun. His joyous leap captures the spirit of adventure and freedom, creating a dramatic and inspiring image.
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 with his arms outstretched in front of a desert landscape and a bright sun.
Aesthetic Score : 0.7
Mood : joyful, adventurous, free
Quality
Entropy : 6.59
Noise : 53
Prompt Clip Score : 0.30
AI Evaluation
Likelihood of AI : 0.20
Image errors : There is some blurring around the edges of the image and in the background, likely due to over-sharpening or lens distortions. There are some noticeable artifacts in the sand, especially around the man’s feet, that could be a result of noise reduction.
Superheroes Take Flight in Epic Showdown
Two costumed heroes, one in red and gold, the other in blue and gold, soar through the city in a dynamic display of power. The dramatic lighting and composition capture the intensity of the moment, leaving viewers eager to see what unfolds next.
Prompt
poses jumping: Triumphant, powerful ; A superhero; close-up; Heroism; a cityscape with towering skyscrapers; cinematic
Characteristic
Shot : Two superheroes, one in a red and gold suit and one in a blue and gold suit, are flying over a city.
Aesthetic Score : 0.6
Mood : heroic, dynamic, action
Quality
Entropy : 6.48
Noise : 67
Prompt Clip Score : 0.31
AI Evaluation
Likelihood of AI : 0.80
Image errors : The image appears to be generated by AI. The characters have a slightly uncanny valley effect, and the background looks somewhat artificial and lacking in detail.
Friends Leap for Joy Against Majestic Mountains
Capture the spirit of adventure and friendship with this vibrant image. Four friends, beaming with happiness, jump in unison against a breathtaking backdrop of towering mountains. The scene exudes joy, carefree abandon, and a sense of exploration, making it a perfect reminder of the simple pleasures in life.
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 the air in front of a mountain range. They are all smiling and look happy.
Aesthetic Score : 0.7
Mood : joyful, carefree, adventurous
Quality
Entropy : 6.78
Noise : 79
Prompt Clip Score : 0.31
AI Evaluation
Likelihood of AI : 0.20
Image errors : No visible artifacts or errors.
Youthful Energy in Motion
A vibrant image capturing the dynamic energy of a young man in a yellow jacket, leaping against a purple backdrop with pink sparkles. The dynamic pose and lighting create a sense of action and excitement, perfectly embodying a youthful and energetic mood.
Prompt
poses jumping: Energetic, playful ; A video game character; close-up; Gaming; a vibrant, pixelated world; cinematic
Characteristic
Shot : A young man in a yellow jacket and blue jeans is jumping in mid-air, against a purple background with some pink sparkles.
Aesthetic Score : 0.8
Mood : dynamic, youthful, energetic
Quality
Entropy : 6.11
Noise : 37
Prompt Clip Score : 0.27
AI Evaluation
Likelihood of AI : 0.90
Image errors : No noticeable errors.
Taking Flight: A Whimsical Moment at the Airport
A man in a plaid shirt embraces the joy of travel with a playful jump in an airport terminal. Shot from a low angle, the image captures his mid-air leap, creating a sense of dynamic energy and whimsical excitement. The blurred background figures add to the lively atmosphere, making this a moment of pure travel joy.
Prompt
poses jumping: Anticipation, excitement ; A traveler; long shot; Travel; a bustling airport terminal with people rushing around; cinematic
Characteristic
Shot : A man in a plaid shirt and white t-shirt is jumping in mid-air in an airport terminal. The image is shot from a low angle, making the man appear larger than life.
Aesthetic Score : 0.6
Mood : playful, whimsical, dynamic
Quality
Entropy : 6.58
Noise : 66
Prompt Clip Score : 0.31
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image has some blurring and noise, particularly in the background, which detracts from the overall sharpness. The subject’s face also appears slightly blurred.
Five Young Men Soar Through the Air in a High-Energy Performance
This captivating image captures the raw energy and joy of a live performance. Five young men, dressed in casual clothing, leap through the air with wide smiles and raised arms, showcasing their athleticism and infectious enthusiasm. The stage is bathed in spotlights, highlighting the dancers against a backdrop of a large wooden structure. The image evokes a sense of excitement and playfulness, capturing a moment of pure exhilaration.
Prompt
poses jumping: Energetic, vibrant ; A group of dancers; medium shot; Groups; a brightly lit stage with a cheering audience; cinematic
Characteristic
Shot : Five young men in casual clothing are leaping in the air during a performance on a stage in front of a large audience. The stage is lit with spotlights and there is a large wooden structure behind the dancers, perhaps a stage backdrop.
Aesthetic Score : 0.7
Mood : energetic, lively, playful
Quality
Entropy : 6.30
Noise : 83
Prompt Clip Score : 0.26
AI Evaluation
Likelihood of AI : 0.10
Image errors : No noticeable errors or artifacts in the image.
Man Soars Through a Storm of Lightning
A dramatic scene unfolds as a man flies towards the viewer, bathed in the glow of lightning bolts against a dark, stormy sky. The intensity of the moment is palpable, heightened by the man’s determined expression and the dynamic camera angle.
Prompt
poses jumping: Determined, courageous ; A lone figure; close-up; Heroism; a dark, stormy night with lightning flashing; cinematic
Characteristic
Shot : A man is flying towards the viewer with lightning bolts in the background, dark cloudy sky
Aesthetic Score : 0.6
Mood : intense, dramatic, action
Quality
Entropy : 6.55
Noise : 65
Prompt Clip Score : 0.29
AI Evaluation
Likelihood of AI : 0.80
Image errors : Some artifacts are visible, especially in the background, and the lightning bolts look somewhat artificial. The subject’s head is slightly distorted.
Jungle Chase: Adrenaline-Fueled Escape!
A low-angle shot captures the heart-pounding action as a group of adventurers leaps through the dense jungle, their expressions a mix of determination and fear. The dynamic composition and mid-air poses create a sense of thrilling adventure, leaving you wondering what they’re running from or towards.
Prompt
poses jumping: Curious, adventurous ; A group of explorers; wide shot; Adventure; a dense jungle with ancient ruins; cinematic
Characteristic
Shot : A group of adventurers are jumping in mid-air, running through a jungle path, seemingly escaping or pursuing something
Aesthetic Score : 0.7
Mood : adventure, action, exciting
Quality
Entropy : 6.68
Noise : 104
Prompt Clip Score : 0.31
AI Evaluation
Likelihood of AI : 0.80
Image errors : No noticeable image errors. The characters are slightly blurry, which could be a stylistic choice or a slight artifact of the image processing
The Intensity of the Game: A Gamer’s Focused Moment
A young man, immersed in his gaming world, sits in a gaming chair, headset on, eyes glued to the computer screen. The lighting and his focused expression create a palpable sense of intensity and anticipation, capturing the competitive spirit of gaming.
Prompt
poses jumping: Focused, intense ; A gamer; close-up; Gaming; a dimly lit room with a computer screen glowing; cinematic
Characteristic
Shot : A young man wearing a headset is sitting in a gaming chair, looking intently at a computer screen, likely playing a game.
Aesthetic Score : 0.6
Mood : focused, intense, competitive
Quality
Entropy : 6.11
Noise : 35
Prompt Clip Score : 0.31
AI Evaluation
Likelihood of AI : 0.20
Image errors : No visible errors in the image.
Silhouettes of Love: A Sunset Romance
Capture the joy and romance of a couple’s playful moment against a breathtaking sunset. The silhouette of the woman jumping in the air, while the man watches with adoration, creates a dramatic and heartwarming scene. This image evokes feelings of love, happiness, and the magic of a perfect evening.
Prompt
poses jumping: Romantic, carefree ; A couple; medium shot; Travel; a romantic sunset over a beach; cinematic
Characteristic
Shot : A couple silhouetted against a sunset on a beach. The woman is jumping in the air and the man is standing still, they are looking at each other.
Aesthetic Score : 0.7
Mood : romantic, joyful, playful
Quality
Entropy : 6.55
Noise : 76
Prompt Clip Score : 0.34
AI Evaluation
Likelihood of AI : 0.10
Image errors : The image has some noise and grain, particularly in the shadows. There is a slight blurriness in the woman’s hair.
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 a 0.5, which falls within the “good” range. This indicates that the model was able to reasonably interpret and implement the camera positions described in the prompt.
- Shot Analysis: The model scored a 0.6, also within the “good” range. This suggests that the model understood the scene described in the prompt and was able to create a shot that reflected that understanding.
- Aesthetic Analysis: The model scored a 0.1, which is considered “very good”. This means that the generated image’s aesthetic closely matched the expected aesthetic described in the prompt.
Overall, the model demonstrates a good understanding of camera positions and scene composition, but it excels in capturing 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://deepmind.google/technologies/imagen-3/