AI-Generated Poses: A Study in Aesthetics and Accuracy with Dall-e-3
- 9 minutes read - 1743 wordsTable of Contents
Dramatic poses are a powerful tool in visual storytelling, conveying emotion, action, and character. AI is increasingly being used to generate these poses, offering a new avenue for creative expression. This analysis explores the strengths and weaknesses of AI in capturing the essence of dramatic poses, examining how well it translates scene descriptions into compelling visuals.
Created with: dall-e-3
One Against Many: A Warrior’s Stand at Sunset
A lone female warrior, clad in blue, stands defiant against a line of silhouetted horsemen at sunset. The scene is charged with tension and anticipation, as she prepares to face an overwhelming force. The dramatic lighting and use of silhouettes create a powerful and evocative image.
Prompt
poses fighting: epic, determined ; A lone warrior; wide shot; heroism; a desolate battlefield with the setting sun in the background; cinematic
Characteristic
Shot : A lone female warrior, clad in traditional garb, faces a charging army of horsemen at sunset.
Aesthetic Score : 0.7
Mood : epic, dramatic, resolute
Quality
Entropy : 6.68
Noise : 96
Prompt Clip Score : 0.23
AI Evaluation
Likelihood of AI : 0.60
Image errors : Some slight blurring in the background and on the warrior’s clothing, especially around the edges.
Escape Through the Jungle: A Race Against Time
Four adventurers navigate a dense jungle, their faces etched with determination as they race towards ancient stone structures. The scene evokes a sense of urgency and adventure, leaving viewers eager to discover their destination and the mysteries that await.
Prompt
poses fighting: intense, adventurous ; A group of adventurers; medium shot; adventure; a dense jungle with ancient ruins in the distance; cinematic
Characteristic
Shot : Four adventurers running through a lush jungle with ancient ruins in the background.
Aesthetic Score : 0.6
Mood : adventurous, mysterious, action-packed
Quality
Entropy : 6.80
Noise : 119
Prompt Clip Score : 0.27
AI Evaluation
Likelihood of AI : 0.80
Image errors : The image has some noticeable artifacts, particularly in the foliage and shadows. The characters’ faces are somewhat blurry, and the lighting is uneven.
Cyberpunk Runner: A Neon-Drenched Chase Through the Future
A masked figure bursts through the neon-lit streets of a futuristic city, the low angle and forward motion capturing the intensity and urgency of the chase. This cyberpunk-style image evokes a sense of stylish danger and thrilling adventure.
Prompt
poses fighting: dynamic, futuristic ; A player character; close-up; gaming; a neon-lit cityscape with holographic projections; cinematic
Characteristic
Shot : A futuristic cyberpunk scene with a lone masked figure running through a city bathed in neon lights and digital streaks.
Aesthetic Score : 0.7
Mood : intense, futuristic, cyberpunk
Quality
Entropy : 6.91
Noise : 107
Prompt Clip Score : 0.23
AI Evaluation
Likelihood of AI : 1.00
Image errors : No significant errors, however the edges of the figure are slightly blurry, and the city lights in the background are a little too repetitive.
Chaos in the Marketplace: A Fight Erupts Amidst the Bustle
Two figures clash in a dynamic fight, their movements blurring as they grapple in the heart of a crowded marketplace. The scene is alive with energy and chaos, capturing the raw intensity of the moment.
Prompt
poses fighting: chaotic, humorous ; Two tourists; medium shot; tourism; a bustling marketplace with colorful stalls and vibrant crowds; cinematic
Characteristic
Shot : Two people are fighting in a crowded marketplace. They are both in a fighting stance and are about to strike each other.
Aesthetic Score : 0.7
Mood : intense, action-packed, dramatic
Quality
Entropy : 6.82
Noise : 118
Prompt Clip Score : 0.34
AI Evaluation
Likelihood of AI : 0.10
Image errors : Some blurriness in the background, particularly on the people in the far distance, suggests motion blur. This could be intentional or a slight processing artifact.
A Solitary Figure Walks into the Setting Sun
A lone traveler traverses a vast, undulating desert landscape as the sun dips below the horizon. The scene evokes a sense of serenity, loneliness, and contemplation, with the figure’s journey symbolizing isolation, hope, and a yearning for the unknown.
Prompt
poses fighting: isolated, desperate ; A lone traveler; long shot; travel; a vast desert landscape with a lone sand dune in the foreground; cinematic
Characteristic
Shot : A lone figure walks across vast desert dunes, the setting sun casting a warm glow.
Aesthetic Score : 0.8
Mood : serene, contemplative, adventurous
Quality
Entropy : 6.68
Noise : 109
Prompt Clip Score : 0.25
AI Evaluation
Likelihood of AI : 0.80
Image errors : Some pixelation is visible in the distance, and the figure’s shadow appears slightly unrealistic.
Urban Warriors: Silhouetted Against the City Lights
A group of young adults strike powerful poses on a rooftop, bathed in dramatic light against a vibrant cityscape. The intense energy and dynamic silhouettes capture the thrill of urban life.
Prompt
poses fighting: energetic, playful ; A group of friends; medium shot; groups; a rooftop overlooking a city skyline at night; cinematic
Characteristic
Shot : A group of young adults are posed in fighting stances on a rooftop overlooking a city at night. There is a dramatic lighting effect with the main focus on the man in the center mid-air, delivering a kick.
Aesthetic Score : 0.6
Mood : action, intense, dynamic
Quality
Entropy : 6.80
Noise : 107
Prompt Clip Score : 0.31
AI Evaluation
Likelihood of AI : 0.30
Image errors : The lighting is slightly artificial and some of the details on the figures are slightly blurred.
A Face of War: Isolation and Tension in the Midst of Chaos
A close-up shot captures the intense emotions of a man amidst a raging war. The blurred background of flames and destruction emphasizes his isolation and the dramatic tension of the moment.
Prompt
poses fighting: tragic, determined ; A lone warrior; close-up; heroism; a burning village with smoke billowing in the air; cinematic
Characteristic
Shot : A close-up portrait of a man with a beard and blood on his face, in the background there is a fire and silhouettes of other people in the distance
Aesthetic Score : 0.7
Mood : dramatic, intense, war-like
Quality
Entropy : 6.77
Noise : 104
Prompt Clip Score : 0.22
AI Evaluation
Likelihood of AI : 0.80
Image errors : Minor noise and artifacting in the background. Slightly blurry.
Shadows and Secrets: Explorers Venture into the Unknown
A group of intrepid explorers, silhouetted against a brilliant light, navigate the depths of a mysterious cave. Stalactites and stalagmites cast eerie shadows, while flickering torches and candles create an atmosphere of suspense and adventure. The interplay of light and darkness adds a layer of intrigue, hinting at the secrets that lie hidden within the cave’s depths.
Prompt
poses fighting: suspenseful, adventurous ; A group of explorers; wide shot; adventure; a dark cave with flickering torches and mysterious shadows; cinematic
Characteristic
Shot : A group of adventurers are walking through a dark cave lit by torches and lanterns. The cave ceiling is high and there are stalactites hanging down. The adventurers are dressed in explorer gear and carrying equipment.
Aesthetic Score : 0.6
Mood : mysterious, suspenseful, adventurous
Quality
Entropy : 6.57
Noise : 88
Prompt Clip Score : 0.27
AI Evaluation
Likelihood of AI : 0.30
Image errors : The image appears to be somewhat over-sharpened, with some haloing around the edges of objects. The lighting is also a bit uneven, with some areas being overexposed and others being too dark.
Pixelated Future: Woman in VR Battles the Unknown
A woman, immersed in a virtual reality world, grips a rifle with intensity. The pixelated background hints at a digital battlefield, creating a sense of futuristic action and suspense. This gritty scene captures the thrill and danger of a virtual reality combat experience.
Prompt
poses fighting: immersive, intense ; A gamer; close-up; gaming; a virtual reality headset with a pixelated world projected in the background; cinematic
Characteristic
Shot : A woman is wearing a VR headset and holding a rifle. She is standing in front of a digital background.
Aesthetic Score : 0.6
Mood : intense, focused, futuristic
Quality
Entropy : 6.93
Noise : 97
Prompt Clip Score : 0.23
AI Evaluation
Likelihood of AI : 0.80
Image errors : The digital background is somewhat distracting and doesn’t blend well with the woman. The VR headset is also a bit blurry in some areas.
Love in Motion: A Couple’s Whimsical Dance Amidst the Train Station Rush
A captivating scene unfolds as a couple dances with joy and abandon in a bustling train station. Their romantic waltz stands out against the backdrop of hurried commuters and the majestic presence of a train, creating a sense of nostalgic whimsy and a powerful testament to the enduring power of love.
Prompt
poses fighting: fast-paced, chaotic ; Two travelers; medium shot; travel; a crowded train station with people rushing in all directions; cinematic
Characteristic
Shot : A couple dances in a crowded train station, with a steam locomotive in the background
Aesthetic Score : 0.8
Mood : romantic, whimsical, nostalgic
Quality
Entropy : 6.92
Noise : 117
Prompt Clip Score : 0.21
AI Evaluation
Likelihood of AI : 0.80
Image errors : Slight blurriness and lack of sharpness in certain areas of the image, especially in the background crowd.
Conclusion
The results show that the generative AI model performed okay in terms of camera position and shot analysis, but very well in terms of aesthetic analysis. Here’s a breakdown:
- Camera Position: The model scored 0.4, which is below the “good” range of 0.5 to 0.75. This suggests that the model didn’t quite capture the intended camera positions as described in the prompt.
- Shot Analysis: The model scored 0.63, which falls within the “good” range. This indicates that the model was able to understand the scene in the prompt reasonably well, but could be better at accurately representing the intended shot.
- Aesthetic Analysis: The model scored 0.02, which is within the “very good” range of -0.2 to 0.1. This means the generated image closely matched the expected aesthetic style.
Overall, the model seems to be better at capturing the desired aesthetic than accurately representing the camera positions and shot composition.
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://openai.com/index/dall-e-3/