AI's Artistic Journey: Capturing Poses, But Missing the Essence with Scenario
- 9 minutes read - 1888 wordsTable of Contents
In the realm of artificial intelligence, the ability to generate images from text prompts has become increasingly sophisticated. However, while AI models can effectively capture the technical aspects of a scene, such as camera position and shot composition, they often struggle to replicate the desired aesthetic. This is particularly evident in the generation of poses, where the model’s output may lack the emotional depth and visual appeal intended by the prompt. This blog post delves into the challenges of generating aesthetically pleasing poses using AI, exploring the model’s strengths and weaknesses, and highlighting the importance of human artistic input in achieving truly compelling imagery.
Created with: scenario
Contemplating the Peaks: A Moment of Serenity in the Mountains
A lone hiker stands on a rocky outcrop, gazing out at a majestic mountain range. The cloudy sky above adds to the sense of awe and wonder, while the woman’s contemplative pose evokes a feeling of peace and adventure.
Prompt
poses hands-in-pockets: determined, confident ; A lone adventurer, standing on a mountain peak; wide shot; heroism; dramatic sky with clouds; cinematic
Characteristic
Shot : A woman in hiking gear stands on a rocky cliff, looking out at a vast mountain range with snow-capped peaks and a cloudy sky. The sun is setting, casting a warm glow on the scene.
Aesthetic Score : 0.75
Mood : serene, adventurous, contemplative
Quality
Entropy : 6.67
Noise : 74
Prompt Clip Score : 0.25
AI Evaluation
Likelihood of AI : 0.10
Image errors : No noticeable artifacts or errors
Lost in Wonder: A Young Explorer Among Ancient Ruins
A young girl stands poised before ancient ruins, swallowed by lush jungle growth. Her expression speaks of both anticipation and wonder, hinting at a journey of discovery and adventure. The scene evokes a sense of mystery and hope, inviting viewers to imagine the secrets hidden within the overgrown stones.
Prompt
poses hands-in-pockets: curious, excited ; A young explorer, gazing at a vast jungle; medium shot; adventure; lush green foliage and ancient ruins; cinematic
Characteristic
Shot : A young girl in explorer gear stands in front of an overgrown ancient temple in a jungle setting. The lighting is soft and warm, suggesting a late afternoon or early evening time of day.
Aesthetic Score : 0.7
Mood : adventurous, mysterious, hopeful
Quality
Entropy : 6.71
Noise : 102
Prompt Clip Score : 0.29
AI Evaluation
Likelihood of AI : 0.80
Image errors : The image has a slight blurring effect, particularly in the background, which may be intended as an artistic choice, but it also makes the image appear somewhat generic. There are some subtle artifacts around the edges of the girl’s hair, especially noticeable near the temples and the ears.
Gamer Girl: Focused and Ready to Conquer
A young woman, radiating confidence, sits immersed in a video game. The vibrant lighting and her determined expression create a captivating scene of intensity and focus.
Prompt
poses hands-in-pockets: focused, intense ; A gamer, sitting at a desk with a controller in hand; close-up; gaming; neon lights and computer screens; cinematic
Characteristic
Shot : A young woman in a pink jacket sits in front of a computer, wearing headphones and looking at the camera. The background is a dimly lit gaming room with colorful lights.
Aesthetic Score : 0.7
Mood : confident, focused, edgy
Quality
Entropy : 6.83
Noise : 83
Prompt Clip Score : 0.31
AI Evaluation
Likelihood of AI : 0.20
Image errors : No visible errors.
A Moment of Joy in a European City
A young woman, radiating happiness, strolls down a charming cobblestone street in a European city. Her gaze is fixed on a majestic building in the distance, hinting at a sense of wonder and adventure. The shallow depth of field emphasizes her joyful expression, capturing the carefree spirit of exploration.
Prompt
poses hands-in-pockets: amazed, happy ; A tourist, admiring a famous landmark; medium shot; tourism; bustling city streets and iconic architecture; cinematic
Characteristic
Shot : A young woman with long brown hair, wearing a white t-shirt and a blue denim vest, is walking down a cobblestone street in a European city. She is looking up at a tall building with a spire in the background. The sun is shining and the sky is blue.
Aesthetic Score : 0.7
Mood : happy, carefree, adventurous
Quality
Entropy : 6.69
Noise : 89
Prompt Clip Score : 0.22
AI Evaluation
Likelihood of AI : 0.20
Image errors : There are no visible errors in the image.
Hopeful Journey Through a Field of Wildflowers
A young woman, filled with adventure, walks a path through a vibrant field of wildflowers towards rolling green hills under a clear, bright sky. The soft lighting and her gaze towards the horizon evoke a sense of peace, hope, and wonder.
Prompt
poses hands-in-pockets: free, adventurous ; A backpacker, walking along a scenic road; medium shot; travel; rolling hills and vibrant wildflowers; cinematic
Characteristic
Shot : A young woman in a white shirt and jeans walks along a path through a field of wildflowers in a mountain valley. The sun is setting, casting a warm glow on the scene.
Aesthetic Score : 0.8
Mood : serene, happy, adventurous
Quality
Entropy : 6.73
Noise : 84
Prompt Clip Score : 0.28
AI Evaluation
Likelihood of AI : 0.20
Image errors : No obvious artifacts or errors. Some minor blurriness in the background.
Golden Hour Friendships on the Beach
Capture the joy of a perfect summer evening with this heartwarming image. A group of friends bask in the golden glow of the setting sun, their smiles radiating happiness and carefree fun. The serene beach setting and the warm, romantic atmosphere create a lasting memory of friendship and joy.
Prompt
poses hands-in-pockets: relaxed, joyful ; A group of friends, standing on a beach at sunset; wide shot; groups; golden sand and crashing waves; cinematic
Characteristic
Shot : A group of friends pose on a beach at sunset. They are all smiling and looking at the camera. The beach is sandy with waves crashing in the background.
Aesthetic Score : 0.7
Mood : happy, relaxed, friendly
Quality
Entropy : 6.64
Noise : 86
Prompt Clip Score : 0.28
AI Evaluation
Likelihood of AI : 0.20
Image errors : No visible errors
Firefighter Stands Tall Amidst Blazing Inferno
A firefighter in full gear faces a burning building, the smoke and flames creating a dramatic backdrop. The image captures the intensity, heroism, and danger of their work, highlighting the contrast between the firefighter’s calm stance and the fiery chaos.
Prompt
poses hands-in-pockets: brave, determined ; A firefighter, standing in front of a burning building; medium shot; heroism; smoke and flames; cinematic
Characteristic
Shot : A female firefighter in full gear standing in front of a burning building, there is smoke and flames in the background, a burnt car in the foreground
Aesthetic Score : 0.7
Mood : dramatic, tense, heroic
Quality
Entropy : 6.81
Noise : 88
Prompt Clip Score : 0.30
AI Evaluation
Likelihood of AI : 0.20
Image errors : No visible errors.
Adventure Awaits: A Glimpse of Discovery in the Desert Canyon
Three hikers, their faces alight with curiosity, stand at the edge of a desert canyon, their gaze fixed on something beyond the frame. The dramatic composition and the light filtering through the cave opening create a sense of anticipation and mystery, hinting at the wonders that lie ahead on their journey.
Prompt
poses hands-in-pockets: cautious, curious ; A group of explorers, navigating a dark cave; medium shot; adventure; stalactites and stalagmites; cinematic
Characteristic
Shot : Three people, a man and two women, are standing in a cave, looking out into a desert landscape.
Aesthetic Score : 0.7
Mood : mysterious, adventurous, hopeful
Quality
Entropy : 6.68
Noise : 109
Prompt Clip Score : 0.26
AI Evaluation
Likelihood of AI : 0.80
Image errors : The image is slightly blurry in some areas, particularly the background. The lighting is also a bit uneven. The figure of the man at the left has a slightly out of place pose and feels not well integrated in the composition.
Joyful Celebration: A Night Filled with Laughter and Confetti
Capture the spirit of a vibrant party with this image. A young woman beams with happiness, surrounded by friends amidst a flurry of colorful confetti. The blurry background adds a sense of movement and excitement, perfectly encapsulating the joyful atmosphere of the event.
Prompt
poses hands-in-pockets: excited, triumphant ; A gamer, celebrating a victory with friends; close-up; gaming; celebratory confetti and flashing lights; cinematic
Characteristic
Shot : A young woman with a big smile is dancing in a crowded place, confetti falling around her. She is dressed in a white hoodie. The background is blurry with other people and lights.
Aesthetic Score : 0.7
Mood : joyful, vibrant, celebratory
Quality
Entropy : 6.84
Noise : 88
Prompt Clip Score : 0.23
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image is slightly overexposed, especially in the background. The confetti looks artificial.
Family Fun Against a Majestic Backdrop
A heartwarming scene unfolds as a family of three enjoys a day out in front of a grand architectural masterpiece. The father carries his son on his shoulders, capturing the joy and love shared between them. The imposing structure adds a sense of grandeur and history to the moment, creating a beautiful contrast with the playful family dynamic.
Prompt
poses hands-in-pockets: happy, united ; A family, standing in front of a famous monument; wide shot; tourism; historical landmark and sunny sky; cinematic
Characteristic
Shot : A family of three is standing in front of a large, ornate building, likely a monument or a government building. The building has columns and statues, and the family is smiling and looking at the camera.
Aesthetic Score : 0.7
Mood : happy, joyful, family
Quality
Entropy : 6.38
Noise : 90
Prompt Clip Score : 0.31
AI Evaluation
Likelihood of AI : 0.10
Image errors : The image seems to be slightly overexposed and some details in the background appear a bit blurry.
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 0.45, which falls slightly below the “good” range of 0.5 to 0.75. This suggests that while the model generally understood the camera position described in the prompt, there were some discrepancies between the intended and generated image.
- Shot Analysis: The model scored 0.525, which is within the “good” range. This indicates that the model was able to successfully translate the prompt’s description of the scene into a visually coherent shot.
- Aesthetic Analysis: The model scored 0.05, which is significantly lower than the “very good” range of -0.2 to 0.1. This suggests that the generated image’s aesthetic deviated considerably from the expected aesthetic based on the prompt.
Overall, the model demonstrates a good understanding of camera position and shot composition, but needs improvement in generating images that match 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.scenario.com