AI's Artistic Struggle: Capturing the Essence of Poses with Titan-g1
- 9 minutes read - 1859 wordsTable of Contents
In the realm of artificial intelligence, the ability to generate images based on textual prompts is a rapidly evolving field. This blog post delves into an experiment where an AI model was tasked with creating images based on specific poses and scenes. While the model demonstrated a decent understanding of camera positions and shot composition, it struggled to capture the desired aesthetic, highlighting the ongoing challenges in AI’s artistic capabilities. This exploration delves into the nuances of AI-generated imagery, examining the strengths and limitations of current models in capturing the essence of dramatic poses and conveying the intended mood and atmosphere.
Created with: titan-g1
A Moment of Solitude Amidst Majestic Peaks
A lone hiker, dwarfed by the grandeur of snow-capped mountains, finds peace and perspective on a serene mountaintop. The vast landscape evokes a sense of adventure and contemplation, highlighting the beauty and power of nature.
Prompt
poses crossed-arms: determined, confident ; A lone explorer, standing atop a windswept mountain peak; wide shot; Adventure; a vast, breathtaking panorama of snow-capped peaks and swirling clouds; cinematic
Characteristic
Shot : A lone hiker stands on a mountaintop overlooking a vast, snow-capped mountain range. The sky is a clear blue, with fluffy clouds scattered across the horizon. The hiker is wearing a red jacket and black pants, and is looking out at the breathtaking view.
Aesthetic Score : 0.8
Mood : serene, contemplative, inspiring
Quality
Entropy : 6.47
Noise : 101
Prompt Clip Score : 0.24
AI Evaluation
Likelihood of AI : 0.20
Image errors : There is some slight noise in the image, particularly in the sky.
Silhouetted Against the Sunset, a Man Contemplates the City
A solitary figure in a suit stands with his back to the camera, gazing out at a sprawling cityscape as the sun dips below the horizon. The warm glow of the setting sun casts a dramatic silhouette, highlighting the man’s contemplative mood against the backdrop of towering skyscrapers.
Prompt
poses crossed-arms: powerful, stoic ; silhouetted against a blazing sunset; medium shot; Heroism; a cityscape with towering skyscrapers and a fiery sky; cinematic
Characteristic
Shot : A man in a suit is standing on a rooftop with his back to the camera, looking out at a city skyline during a sunset.
Aesthetic Score : 0.6
Mood : thoughtful, contemplative, urban
Quality
Entropy : 6.73
Noise : 95
Prompt Clip Score : 0.23
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image has some minor artifacts, particularly around the edges of the subject.
The Glow of Competition: Young Gamers Immersed in the Heat of the Game
A vibrant scene captures the intensity of a gaming session. Colorful lighting illuminates a group of young people focused on their computer screens, their expressions revealing a mix of concentration and competitive spirit. The atmosphere is electric with anticipation, highlighting the thrill of the game.
Prompt
poses crossed-arms: focused, intense ; A group of gamers, huddled around a glowing computer screen; close-up; Gaming; a dimly lit room with neon lights and gaming peripherals; cinematic
Characteristic
Shot : Three young people are sitting in front of a computer, focused on the screen. The room is lit with vibrant blue and pink lights, giving it a gamer aesthetic.
Aesthetic Score : 0.6
Mood : focused, intense, competitive
Quality
Entropy : 6.88
Noise : 104
Prompt Clip Score : 0.29
AI Evaluation
Likelihood of AI : 0.20
Image errors : No noticeable errors
Parisian Mystery: A Woman’s Silhouette Against the Eiffel Tower
A young woman in a flowing blue dress stands thoughtfully in front of a Parisian building, the iconic Eiffel Tower casting a long shadow in the background. The scene evokes a sense of Parisian elegance and mystery, leaving the viewer to wonder about her story.
Prompt
poses crossed-arms: awe-struck, contemplative ; A young woman, gazing out at the Eiffel Tower; medium shot; Tourism; a bustling Parisian street with charming cafes and cobblestone streets; cinematic
Characteristic
Shot : A young woman in a blue dress is standing on a street in Paris with the Eiffel Tower in the background.
Aesthetic Score : 0.7
Mood : dreamy, romantic, Parisian
Quality
Entropy : 6.95
Noise : 95
Prompt Clip Score : 0.29
AI Evaluation
Likelihood of AI : 0.20
Image errors : No noticeable image errors.
Embracing the Open Road: A Woman Finds Freedom on the Beach
A woman, arms outstretched, stands on a sandy beach, her gaze fixed on the endless horizon. The blue sky and vast ocean create a sense of boundless possibility, reflecting a mood of happiness, adventure, and carefree abandon. This image captures the essence of a journey, a moment of pure joy and liberation.
Prompt
poses crossed-arms: free-spirited, adventurous ; A backpacker, standing on a deserted beach; long shot; Travel; a pristine beach with turquoise waters and palm trees swaying in the breeze; cinematic
Characteristic
Shot : A woman with her arms outstretched, wearing a hat and a backpack, standing on a beach with a tropical island in the background.
Aesthetic Score : 0.7
Mood : happy, carefree, adventurous
Quality
Entropy : 6.65
Noise : 98
Prompt Clip Score : 0.25
AI Evaluation
Likelihood of AI : 0.30
Image errors : The image has a slight color cast and a grainy texture, possibly due to over-editing or a low-resolution source image.
Space Explorers: A New Dawn Awaits
Three astronauts, clad in futuristic spacesuits, stand poised before a colossal spaceship, bathed in the golden light of a distant sun. Their determined expressions and the warm glow of the scene evoke a sense of anticipation and hope, hinting at an exciting mission on the horizon.
Prompt
poses crossed-arms: determined, united ; A team of astronauts, standing in the shadow of a colossal spaceship; medium shot; Heroism; a futuristic spaceport with gleaming metal and swirling nebulae; cinematic
Characteristic
Shot : Three astronauts standing in a space station, wearing space suits, looking into the distance, with a spaceship in the background
Aesthetic Score : 0.7
Mood : futuristic, serious, hopeful
Quality
Entropy : 6.77
Noise : 111
Prompt Clip Score : 0.28
AI Evaluation
Likelihood of AI : 0.30
Image errors : No notable errors or artifacts.
VR Joyride: Friends Celebrate a Virtual Adventure
Three friends, immersed in a vibrant virtual world, share laughter and excitement as they celebrate their shared experience. The blurry neon background adds to the sense of energy and movement, capturing the joy of their virtual journey.
Prompt
poses crossed-arms: excited, triumphant ; A group of friends, celebrating a victory in a virtual reality game; close-up; Gaming; a brightly lit arcade with flashing lights and immersive VR headsets; cinematic
Characteristic
Shot : Three people are wearing VR headsets and are having fun, jumping in the air with their arms raised. The scene appears to be set in a futuristic environment.
Aesthetic Score : 0.7
Mood : joyful, energetic, excited
Quality
Entropy : 6.85
Noise : 108
Prompt Clip Score : 0.32
AI Evaluation
Likelihood of AI : 0.10
Image errors : The image has slight noise and artifacts, especially visible in the background.
Contemplating the City: A Moment of Peace on the Bridge
A woman stands on a bridge, bathed in sunlight, gazing out at a picturesque European city. The scene evokes a sense of reflection and tranquility, with the city’s classic architecture and the shimmering river adding to the peaceful atmosphere. The dramatic lighting and the woman’s pose create a captivating image that invites viewers to share in her contemplative moment.
Prompt
poses crossed-arms: reflective, introspective ; A lone traveler, standing on a bridge overlooking a bustling city; medium shot; Travel; a vibrant cityscape with towering buildings and a river flowing below; cinematic
Characteristic
Shot : A woman stands on a bridge overlooking a city with a river flowing below. The city is in the background, with a few cars driving on the roads. There is a tower in the distance.
Aesthetic Score : 0.7
Mood : calm, contemplative, melancholic
Quality
Entropy : 6.79
Noise : 102
Prompt Clip Score : 0.23
AI Evaluation
Likelihood of AI : 0.20
Image errors : No noticeable artifacts or errors
Conquering Peaks, Embracing Freedom
Two adventurers stand triumphant atop a mountain, arms raised in joyous celebration. The breathtaking vista and dramatic lighting capture the essence of their adventurous spirit and the thrill of reaching new heights.
Prompt
poses crossed-arms: accomplished, exhilarated ; A group of hikers, standing at the summit of a mountain; wide shot; Adventure; a panoramic view of rolling hills and lush forests; cinematic
Characteristic
Shot : Two men standing on a mountain with a beautiful view of the valley below. They are both wearing backpacks and are looking out at the view. One of the men has his arms raised in the air.
Aesthetic Score : 0.6
Mood : joyful, adventurous, triumphant
Quality
Entropy : 6.70
Noise : 105
Prompt Clip Score : 0.26
AI Evaluation
Likelihood of AI : 0.10
Image errors : No noticeable image artifacts or errors
Friends Capture Joyful Memories in Front of Historic Cathedral
Four friends radiate happiness as they take a selfie in front of a majestic cathedral, bathed in the warm glow of a sunny day. The blue sky and the historic architecture create a picturesque backdrop for their carefree moment, capturing the essence of travel and friendship.
Prompt
poses crossed-arms: happy, excited ; A group of tourists, posing for a photo in front of a famous landmark; medium shot; Tourism; a historic landmark with intricate architecture and vibrant colors; cinematic
Characteristic
Shot : A group of four young adults are taking a selfie in front of Notre Dame Cathedral in Paris. The cathedral is in the background, and the group is in the foreground.
Aesthetic Score : 0.7
Mood : happy, fun, touristy
Quality
Entropy : 6.83
Noise : 104
Prompt Clip Score : 0.27
AI Evaluation
Likelihood of AI : 0.20
Image errors : There are no noticeable errors in the image.
Conclusion
The results show that the generative AI model performed well in understanding and executing camera positions and shot composition, but struggled with achieving the desired aesthetic. Here’s a breakdown:
- Camera Position: The model scored a 0.4, which falls below the “good” range of 0.5 to 0.75. This suggests that the model didn’t perfectly capture the intended camera positions described in the prompt.
- Shot Analysis: The model scored a 0.53, which is within the “good” range. This indicates that the model was able to understand and translate the scene description in the prompt into a visually coherent shot.
- Aesthetic Analysis: The model scored a 0.07, which is significantly below the “very good” range of -0.2 to 0.1. This suggests that the generated image’s aesthetic deviated considerably from the expected aesthetic described in the prompt.
Overall, the model demonstrates a decent understanding of camera positions and shot composition, but needs improvement 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://docs.aws.amazon.com/bedrock/latest/userguide/titan-image-models.html