Dramatic poses are a powerful tool in visual storytelling, conveying emotions and narratives through the way a subject positions their body. From the iconic ‘Thinker’ statue to the dynamic poses of superheroes in action, these poses have the ability to capture our attention and evoke strong feelings. However, replicating these poses accurately and aesthetically in AI-generated images presents a unique challenge. This blog post explores the results of an experiment where AI was tasked with generating images based on specific poses and scene descriptions, revealing both its strengths and limitations in this artistic endeavor.
Created with: scenario
Finding Wonder in the Snowy Peaks
A young woman, bathed in the soft glow of a snowy mountain landscape, gazes upwards with a sense of calm hope and adventure. The scene evokes a feeling of awe and wonder at the beauty of the natural world.
Prompt
poses leaning-in: determined, focused ; A lone adventurer; close-up; Adventure; a vast, snow-capped mountain range; cinematic
Characteristic
Shot : A young woman is standing in a snowy mountain landscape, looking off into the distance with a determined expression.
Aesthetic Score : 0.8
Mood : serene, adventurous, hopeful
Quality
Entropy : 6.70
Noise : 90
Prompt Clip Score : 0.27
AI Evaluation
Likelihood of AI : 0.20
Image errors : There are no obvious artifacts or errors in the image.
Captain Marvel Soars Through Chaos
A powerful image capturing Captain Marvel in flight, her heroic presence dominating a city engulfed in smoke and fire. The dynamic pose and dramatic backdrop evoke a sense of intense action and excitement.
Prompt
poses leaning-in: powerful, heroic ; A superhero in mid-flight; dynamic shot; Heroism; a cityscape with a burning building in the background; cinematic
Characteristic
Shot : A female superhero in a blue and gold costume is leaping through the air over a city. The city appears to be on fire, and there is a lot of smoke and debris in the air. The superhero is looking at the camera.
Aesthetic Score : 0.7
Mood : action, dramatic, heroic
Quality
Entropy : 6.92
Noise : 97
Prompt Clip Score : 0.30
AI Evaluation
Likelihood of AI : 0.80
Image errors : The fire in the background looks a little bit artificial. The lighting seems a little bit unnatural.
Focused Determination: A Tech-Savvy Woman at Work
This image captures a young woman immersed in her work, her focused expression and the dramatic lighting highlighting her determination. The scene evokes a sense of technological prowess and dedication, showcasing the power of focus in a digital age.
Prompt
poses leaning-in: intense, focused ; A gamer’s hands on a keyboard; close-up; Gaming; a brightly lit computer screen displaying a game; cinematic
Characteristic
Shot : A young woman is sitting at a desk, looking intently at a computer screen. She is typing on a keyboard and her hands are illuminated by the blue backlight.
Aesthetic Score : 0.7
Mood : focused, determined, concentrated
Quality
Entropy : 6.74
Noise : 85
Prompt Clip Score : 0.26
AI Evaluation
Likelihood of AI : 0.20
Image errors : No visible errors
Sunset Romance on the Beach
A couple stands hand-in-hand on a sandy beach, bathed in the warm glow of a setting sun. The scene evokes a sense of romantic intimacy and peaceful tranquility.
Prompt
poses leaning-in: romantic, awe-inspired ; A couple gazing at a breathtaking sunset; medium shot; Tourism; a panoramic view of a beach with the sun setting over the ocean; cinematic
Characteristic
Shot : A couple standing on a beach at sunset, looking at each other.
Aesthetic Score : 0.7
Mood : romantic, serene, warm
Quality
Entropy : 6.53
Noise : 87
Prompt Clip Score : 0.27
AI Evaluation
Likelihood of AI : 0.80
Image errors : There are some minor artifacts in the sky, especially near the palm tree leaves, and the colors seem a bit too saturated.
Lost in the Landscape: A Moment of Contemplation
A woman sits by a train window, her gaze fixed on the rolling hills and fields passing by. The scene evokes a sense of pensive longing, capturing a moment of quiet reflection amidst the journey.
Prompt
poses leaning-in: reflective, adventurous ; A backpacker looking out of a train window; close-up; Travel; a passing landscape of rolling hills and green fields; cinematic
Characteristic
Shot : A young woman is looking out of a train window at a rural landscape. The landscape is a blur of green and brown fields. The woman’s face is in focus, and she looks sad and contemplative.
Aesthetic Score : 0.7
Mood : melancholic, contemplative, wistful
Quality
Entropy : 6.77
Noise : 92
Prompt Clip Score : 0.28
AI Evaluation
Likelihood of AI : 0.80
Image errors : The image is slightly blurry, especially in the background.
Winter Wonderland: A Cozy Campfire Under a Setting Sun
Four friends gather around a crackling campfire in a snowy forest, bathed in the warm glow of the setting sun. The scene evokes a sense of peace and tranquility, with soft falling snow and bare trees adding to the cozy, nostalgic atmosphere.
Prompt
poses leaning-in: intimate, warm ; A group of friends huddled together around a campfire; medium shot; Groups; a dark forest with the firelight illuminating their faces; cinematic
Characteristic
Shot : Four young women are sitting around a campfire in a snowy forest, they are dressed in warm clothing and appear to be enjoying each other’s company.
Aesthetic Score : 0.8
Mood : cozy, friendship, winter
Quality
Entropy : 6.73
Noise : 100
Prompt Clip Score : 0.27
AI Evaluation
Likelihood of AI : 0.90
Image errors : The image seems to have been created digitally. The trees in the background seem to lack texture and are mostly symmetrical, the snow lacks any texture or variation in depth. The fire is too perfect and flat, lacking any variation of smoke and depth.
Soldier’s Focus Amidst Chaos
A female soldier, clad in military gear, stands resolute, aiming a sniper rifle. Behind her, a fiery explosion erupts, creating a sense of urgency and danger. The scene captures the intensity and focus of a soldier in the midst of a dramatic situation.
Prompt
poses leaning-in: intense, focused ; A soldier peering through a sniper scope; close-up; Heroism; a battlefield with smoke and explosions in the distance; cinematic
Characteristic
Shot : A woman in military fatigues is aiming a sniper rifle with a backdrop of a fiery explosion and smoke. She is kneeling on a hill, with a patch of the American flag on her arm.
Aesthetic Score : 0.6
Mood : intense, dramatic, action-packed
Quality
Entropy : 6.77
Noise : 85
Prompt Clip Score : 0.31
AI Evaluation
Likelihood of AI : 0.30
Image errors : Slight overexposure on the horizon. The image has a slightly blurred effect, possibly from motion blur or post-processing. The shadow of the sniper rifle on the ground seems to be a bit artificial.
Lost in the Jungle’s Embrace: A Serene Adventure Awaits
Three adventurers trek through a vibrant jungle, bathed in the golden glow of a hidden waterfall. The light filtering through the foliage creates a sense of mystery and wonder, inviting you to explore this serene and adventurous landscape.
Prompt
poses leaning-in: determined, adventurous ; A group of explorers navigating a dense jungle; wide shot; Adventure; lush green foliage and towering trees; cinematic
Characteristic
Shot : A group of three hikers are walking on a path in a dense jungle, heading towards a waterfall.
Aesthetic Score : 0.7
Mood : mysterious, adventurous, serene
Quality
Entropy : 6.64
Noise : 116
Prompt Clip Score : 0.27
AI Evaluation
Likelihood of AI : 0.80
Image errors : The image has some minor artifacts, such as a few blurred areas and some unnatural looking foliage.
Radiant Smile, Warm Glow: A Portrait of Joy
This close-up portrait captures a young woman’s infectious smile, bathed in soft lighting and warm colors. Her bright eyes and friendly expression create a charming and inviting atmosphere.
Prompt
poses leaning-in: excited, immersed ; A gamer’s face lit by the screen; close-up; Gaming; a vibrant, colorful game interface; cinematic
Characteristic
Shot : A close-up portrait of a young woman with blonde hair, wearing a pink cardigan and a silver necklace, smiling brightly at the camera.
Aesthetic Score : 0.8
Mood : happy, youthful, confident
Quality
Entropy : 6.68
Noise : 81
Prompt Clip Score : 0.22
AI Evaluation
Likelihood of AI : 0.80
Image errors : There are some minor artifacts and blurring in the hair, especially around the edges.
City Lights, Shared Dreams: A Rooftop Moment at Dusk
Three figures silhouetted against a breathtaking cityscape, bathed in the warm glow of twilight. This image captures the essence of romance, nostalgia, and peace, leaving you with a sense of wonder and awe at the beauty of the city.
Prompt
poses leaning-in: joyful, appreciative ; A family looking out at a cityscape from a rooftop; medium shot; Tourism; a sprawling city skyline with twinkling lights; cinematic
Characteristic
Shot : Three figures, two women and a young boy, are sitting on a rooftop overlooking a cityscape at sunset. The city skyline is in the background, with several skyscrapers visible. The scene is lit by the setting sun, casting a warm glow over the city.
Aesthetic Score : 0.75
Mood : romantic, melancholic, peaceful
Quality
Entropy : 6.74
Noise : 102
Prompt Clip Score : 0.28
AI Evaluation
Likelihood of AI : 0.80
Image errors : The image is slightly blurry, especially in the distance. There are some areas of aliasing, particularly around the edges of the figures and the buildings. The colors are slightly oversaturated, giving the image a slightly artificial look.
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 0.35, 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 0.55, which is considered good. This indicates that the model was able to understand and translate the scene description from the prompt into the generated image.
- Aesthetic Analysis: The model scored 0.07, which is considered average. This means that the generated image’s aesthetic was somewhat close to the expected aesthetic, but not particularly strong.
Overall, the model demonstrated a good understanding of the scene and shot composition, but needs improvement in accurately capturing the intended camera position and achieving the desired aesthetic.