AI's Artistic Struggle: Capturing the Essence of Poses with Dall-e-3
- 10 minutes read - 1929 wordsTable of Contents
In the realm of artificial intelligence, the ability to generate realistic and expressive images is a constant pursuit. One key aspect of this pursuit is capturing the essence of poses, the way bodies are positioned and interact with their surroundings. This blog post delves into an experiment where a generative AI model was tasked with creating images based on scene descriptions, highlighting its strengths and weaknesses in capturing poses and aesthetics. We’ll explore how the model performed, analyzing its ability to understand camera position, shot analysis, and aesthetic interpretation, and discuss the challenges of AI in capturing the nuances of human expression and artistic intent.
Created with: dall-e-3
Soldiers Stand in Somber Formation, Silhouetted Against a Distant Conflict
A group of soldiers in military uniform stand in a tight formation, their faces etched with seriousness. The scene is bathed in a dramatic interplay of light and shadow, highlighting the weight of their duty. A smaller group of soldiers is silhouetted in the background, suggesting a distant conflict that casts a long shadow over the present moment.
Prompt
poses standing-in-a-row: determined, courageous, hopeful ; A group of soldiers; wide shot; heroism; a battlefield with smoke and explosions in the background; cinematic
Characteristic
Shot : A large group of soldiers standing in formation, with a smaller group of soldiers in silhouette in the background. The scene is lit by a spotlight from above, creating a dramatic effect.
Aesthetic Score : 0.6
Mood : intense, solemn, patriotic
Quality
Entropy : 6.81
Noise : 110
Prompt Clip Score : 0.25
AI Evaluation
Likelihood of AI : 0.70
Image errors : No errors, but the image is slightly blurry.
Uncharted Territory Awaits: Adventurers Embark on a Jungle Quest
Four intrepid explorers, their faces radiating confidence, stand poised at the edge of a verdant jungle path. The soft lighting casts a warm glow on their faces, highlighting their determination as they gaze towards a mysterious stone temple in the distance. This image captures the essence of adventure, exploration, and the thrill of the unknown.
Prompt
poses standing-in-a-row: excited, curious, adventurous ; A team of explorers; medium shot; adventure; a lush jungle with ancient ruins in the distance; cinematic
Characteristic
Shot : A group of four adventurers, dressed in safari gear, standing in front of a jungle path. The group includes two men and two women.
Aesthetic Score : 0.6
Mood : adventurous, determined, hopeful
Quality
Entropy : 6.85
Noise : 109
Prompt Clip Score : 0.30
AI Evaluation
Likelihood of AI : 0.40
Image errors : The image appears to have some slight blurring around the edges, and some artifacts in the background. The lighting is slightly uneven.
The Glow of Competition: Young Gamers Face Off Under the Spotlight
A group of diverse young people, their faces illuminated by vibrant spotlights, grip their gaming controllers with intensity. The close-up framing and dramatic lighting capture the competitive spirit and anticipation of the moment, creating a powerful visual of the passion and focus of competitive gaming.
Prompt
poses standing-in-a-row: focused, competitive, passionate ; A group of gamers; close-up shot; gaming; a brightly lit esports arena with cheering fans; cinematic
Characteristic
Shot : A group of diverse young adults stand in a row, focused on playing video games with controllers in their hands. The scene is lit with dramatic, colorful lighting, creating a vibrant and energetic atmosphere.
Aesthetic Score : 0.7
Mood : intense, focused, competitive
Quality
Entropy : 6.66
Noise : 89
Prompt Clip Score : 0.29
AI Evaluation
Likelihood of AI : 0.20
Image errors : No noticeable errors or artifacts present.
Capturing Joy Against a Majestic Backdrop
A group of friends, beaming with happiness, pose for a photo in front of a breathtaking mountain range. The towering peaks create a sense of awe and adventure, highlighting the shared joy of the moment.
Prompt
poses standing-in-a-row: happy, relaxed, joyful ; A family of tourists; long shot; tourism; a breathtaking view of a mountain range with a clear blue sky; cinematic
Characteristic
Shot : A group of people, mostly young adults, are posing for a photo on a mountaintop, with a view of a distant mountain range in the background.
Aesthetic Score : 0.6
Mood : happy, friendly, adventurous
Quality
Entropy : 6.73
Noise : 103
Prompt Clip Score : 0.32
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image appears to have been compressed or resized, which has resulted in some blurring and loss of detail. The lighting is also slightly uneven, with some faces appearing brighter than others.
Golden Hour Adventure: Backpackers Embark on a Journey into the Unknown
A group of backpackers sets off on a dirt road through a tropical paradise, bathed in the warm glow of a setting sun. The hazy atmosphere adds a touch of mystery and anticipation to their adventure, leaving their future uncertain but full of hope.
Prompt
poses standing-in-a-row: free-spirited, adventurous, optimistic ; A group of backpackers; medium shot; travel; a dusty road leading to a distant village with palm trees; cinematic
Characteristic
Shot : A group of eight young adults, carrying backpacks, are walking on a dusty road in a tropical setting. The road is lined with palm trees and the background shows mountains with a hazy atmosphere.
Aesthetic Score : 0.6
Mood : adventurous, determined, hopeful
Quality
Entropy : 6.49
Noise : 99
Prompt Clip Score : 0.34
AI Evaluation
Likelihood of AI : 0.20
Image errors : There are no noticeable artifacts or errors in the image.
Silhouettes of Hope: A Choir’s Dramatic Performance
A large choir stands in silhouette on stage, bathed in spotlights, creating a powerful and mysterious atmosphere. The scene evokes a sense of drama, hope, and solemnity, leaving a lasting impression.
Prompt
poses standing-in-a-row: harmonious, powerful, emotional ; A choir singing in harmony; close-up shot; groups; a dimly lit stage with spotlights; cinematic
Characteristic
Shot : A choir of people standing in a dark room, illuminated by bright spotlights, creating a dramatic silhouette effect.
Aesthetic Score : 0.6
Mood : dramatic, solemn, powerful
Quality
Entropy : 6.64
Noise : 98
Prompt Clip Score : 0.29
AI Evaluation
Likelihood of AI : 0.10
Image errors : There are slight artifacts in the shadows of the people. Some of the shadows are slightly pixelated.
Under the Spotlight: A Vibrant Dance Performance Captures the Crowd
A group of dancers in colorful attire electrifies the stage with their energetic moves, bathed in the glow of spotlights. The vibrant atmosphere is palpable, as a large crowd watches in awe, captivated by the spectacle.
Prompt
poses standing-in-a-row: energetic, synchronized, joyful ; A line of dancers; wide shot; groups; a brightly lit stage with colorful costumes; cinematic
Characteristic
Shot : A group of people are dancing on a stage, lit by bright spotlights. There is a second group of people standing on a platform above the stage.
Aesthetic Score : 0.7
Mood : energetic, vibrant, playful
Quality
Entropy : 6.93
Noise : 105
Prompt Clip Score : 0.25
AI Evaluation
Likelihood of AI : 0.60
Image errors : None, except that the dancers’ clothes could look a bit too sharp
Golden Hour Friendships: A Sunset Beach Moment
Capture the joy and warmth of a perfect summer evening with this image. A group of friends stand on a beach, bathed in the golden light of the setting sun, radiating happiness and carefree energy. The scene evokes a sense of relaxation and connection, making it a perfect reminder of cherished moments with loved ones.
Prompt
poses standing-in-a-row: relaxed, happy, nostalgic ; A group of friends; medium shot; groups; a sunset over a beach with waves crashing in the background; cinematic
Characteristic
Shot : A group of friends, 6 men and 3 women, are standing on a beach at sunset. They are all smiling and looking at the camera. The sun is setting behind them, casting a warm glow on the scene.
Aesthetic Score : 0.7
Mood : joyful, carefree, happy
Quality
Entropy : 6.45
Noise : 97
Prompt Clip Score : 0.31
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image is a bit overexposed, especially in the sky. The sun is also a bit too bright. There is some blurriness around the edges of the image, which may be due to lens distortion. The image has an overall warm and fuzzy filter applied, which may make the details look less sharp.
The Codebreakers: A Glimpse into a High-Stakes Tech Showdown
In the dimly lit confines of a server room, four figures huddle around a screen, their faces etched with intense focus. The air crackles with suspense as they decipher the secrets hidden within the code. What are they working on? And what stakes are at play?
Prompt
poses standing-in-a-row: focused, determined, innovative ; A team of scientists; close-up shot; groups; a laboratory with complex machinery and glowing screens; cinematic
Characteristic
Shot : Four people, possibly a team of programmers or IT professionals, are looking intently at a computer screen. They are in a dimly lit room, possibly a server room or data center. The screen is displaying some kind of code or data.
Aesthetic Score : 0.6
Mood : intense, focused, serious
Quality
Entropy : 6.82
Noise : 100
Prompt Clip Score : 0.26
AI Evaluation
Likelihood of AI : 0.90
Image errors : The image is slightly blurry, possibly due to the use of a long exposure time.
Young Protester’s Determination Amidst a Sea of Uprising
A close-up shot captures the intensity of a young man at the heart of a massive protest, his determined expression and raised fist reflecting the urgency and tension of the moment.
Prompt
poses standing-in-a-row: determined, passionate, hopeful ; A group of protesters; long shot; groups; a city street with banners and signs; cinematic
Characteristic
Shot : A crowd of people protesting in the streets of a city. They are holding signs and some are raising their fists in the air. The focus is on a young man with dark hair who looks concerned.
Aesthetic Score : 0.7
Mood : intense, serious, dramatic
Quality
Entropy : 6.92
Noise : 103
Prompt Clip Score : 0.25
AI Evaluation
Likelihood of AI : 0.30
Image errors : The image has a slight blurriness, which might be due to motion or a deliberate effect. The details of some signs are unclear.
Conclusion
The results show that the generative AI model performed well in understanding the scene and camera position, but struggled with the aesthetic aspect. Here’s a breakdown:
- Camera Position: The model scored 0.4, which is below the “good” range of 0.5 to 0.75. This indicates that the model didn’t quite capture the intended camera position as described in the prompt.
- Shot Analysis: The model scored 0.63, which falls within the “good” range. This means the model was able to understand the scene and create a shot that was relatively close to what was described in the prompt.
- Aesthetic Analysis: The model scored 0.11, which is slightly above the “very good” range of -0.2 to 0.1. This suggests that the generated image’s aesthetic deviated somewhat from the expected aesthetic described in the prompt.
Overall, the model demonstrated a good understanding of the scene and shot composition, but needs improvement in accurately capturing the intended camera position and 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://openai.com/index/dall-e-3/