AI's Artistic Eye: Capturing Poses, But Missing the Shot with Titan-g1
- 8 minutes read - 1696 wordsTable of Contents
In the realm of AI-generated art, capturing the essence of a scene goes beyond simply depicting objects. It involves understanding the nuances of composition, camera angles, and the overall aesthetic. This blog post delves into the results of an experiment where an AI model was tasked with generating images based on specific poses and scene descriptions. The results reveal a fascinating insight into the AI’s artistic capabilities, highlighting its strengths and weaknesses in capturing the desired visual style.
Created with: titan-g1
Silhouetted Against the Vastness: A Moment of Contemplation
A solitary figure stands on a mountain peak, their silhouette stark against the rolling landscape and cloudy sky. The scene evokes a sense of serenity, contemplation, and a touch of loneliness, highlighting the vastness of the world and the smallness of the individual within it.
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 lone man stands on a grassy hilltop overlooking a vast, rolling landscape. The sky is overcast with clouds and a sense of mystery.
Aesthetic Score : 0.6
Mood : serene, contemplative, adventurous
Quality
Entropy : 6.49
Noise : 103
Prompt Clip Score : 0.23
AI Evaluation
Likelihood of AI : 0.20
Image errors : No visible artifacts or errors.
Lost in Time: A Woman’s Silhouette Against an Ancient Temple
A woman stands silhouetted against the backdrop of an ancient temple, overgrown with lush foliage. The scene evokes a sense of mystery, adventure, and contemplation, leaving the viewer to wonder about her story and the secrets held within the temple’s walls.
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 woman in a blue tank top and khaki pants stands on a path leading up to an ancient stone temple overgrown with greenery.
Aesthetic Score : 0.6
Mood : mysterious, adventurous, tranquil
Quality
Entropy : 6.86
Noise : 112
Prompt Clip Score : 0.30
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image has some noise and compression artifacts, particularly in the shadows. The contrast is a bit flat, and the colors are slightly muted.
The Glow of Competition: A Gamer’s Focus in the Dimly Lit Room
A close-up shot captures the intensity of a gamer’s focus as they navigate a virtual world. The dimly lit room adds to the sense of immersion, highlighting the player’s hands gripping the controller with determination.
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 person is playing a video game on a computer, holding a gamepad. The scene is lit by blue and purple light, giving it a futuristic and dramatic feeling. The image is well-composed and focused on the gamer’s hands, which adds to the sense of action and tension.
Aesthetic Score : 0.5
Mood : intense, futuristic, focused
Quality
Entropy : 6.90
Noise : 96
Prompt Clip Score : 0.26
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image has a slight blurriness, particularly in the background, which is likely due to the low-light conditions. There are also some minor artifacts around the edges of the objects, especially in the background.
Awe-Inspiring Notre Dame: A Tourist’s Joyful Moment
A young man beams with happiness as he stands before the majestic Notre Dame Cathedral in Paris. The Gothic architecture, with its soaring spires and intricate details, evokes a sense of wonder and awe. This image captures the joy of travel and the beauty of iconic landmarks.
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 man, wearing a blue denim shirt and a beige t-shirt, is standing in front of the Notre Dame Cathedral in Paris. He is looking up and smiling, and the cathedral is in the background. The image has a soft, warm color palette.
Aesthetic Score : 0.7
Mood : happy, joyful, touristy
Quality
Entropy : 6.79
Noise : 95
Prompt Clip Score : 0.21
AI Evaluation
Likelihood of AI : 0.20
Image errors : No notable errors in the image.
A Solitary Journey Through Tranquil Hills
A lone figure, backpack in tow, traverses a winding road through a grassy hillside. The vast landscape evokes a sense of peace and contemplation, suggesting a journey of self-discovery.
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 woman with a backpack walks on a winding road through a grassy field. The road leads into the distance and is surrounded by rolling hills.
Aesthetic Score : 0.6
Mood : tranquil, adventurous, hopeful
Quality
Entropy : 6.78
Noise : 107
Prompt Clip Score : 0.24
AI Evaluation
Likelihood of AI : 0.30
Image errors : The image is slightly blurry, especially in the background.
Sunset Silhouettes: A Moment of Joy on the Beach
Four friends bask in the golden glow of a sunset on the beach, their silhouettes painted against the vibrant sky. The scene exudes a sense of relaxed happiness and carefree joy, capturing the essence of a perfect summer evening.
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 : Four friends are walking on a sandy beach, facing away from the camera towards the sunset, holding hands.
Aesthetic Score : 0.6
Mood : happy, carefree, playful
Quality
Entropy : 6.73
Noise : 97
Prompt Clip Score : 0.27
AI Evaluation
Likelihood of AI : 0.10
Image errors : The image is slightly blurry, especially in the background.
Firefighter’s Determined Gaze: A Symbol of Courage and Hope
A powerful image captures a firefighter in full gear, standing before a building and gazing upwards with unwavering determination. The scene evokes a sense of seriousness, courage, and hope, highlighting the bravery of those who face danger to protect others.
Prompt
poses hands-in-pockets: determined ; firefighter, standing in front of a building; medium shot; heroism; cinematic
Characteristic
Shot : A firefighter stands in front of a building, looking up.
Aesthetic Score : 0.6
Mood : serious, focused, determined
Quality
Entropy : 6.88
Noise : 103
Prompt Clip Score : 0.29
AI Evaluation
Likelihood of AI : 0.10
Image errors : No visible errors.
Lost in the Depths: Exploring a Cave of Wonder
Three adventurers venture into a breathtaking cave, its intricate rock formations illuminated by the faint glow of their headlamps. The low light and cavernous space create a sense of mystery and awe, hinting at the secrets hidden within.
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 men exploring a cave with beautiful rock formations. The cave is lit with artificial light sources.
Aesthetic Score : 0.6
Mood : adventurous, mysterious, explorative
Quality
Entropy : 6.49
Noise : 115
Prompt Clip Score : 0.28
AI Evaluation
Likelihood of AI : 0.10
Image errors : The image is slightly underexposed, especially in the foreground. This makes the figures difficult to see clearly. The shadows are a bit harsh and the lighting is a bit uneven.
Confetti Celebration: Friends Capture Joy in a Burst of Color
Three friends share a moment of pure joy, surrounded by falling confetti. The high-contrast lighting and vibrant colors create a visually stunning and celebratory atmosphere. This image captures the essence of friendship and the excitement of a special occasion.
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 : Three people celebrating with confetti falling around them. They are all laughing and seem to be enjoying themselves.
Aesthetic Score : 0.7
Mood : joyful, celebratory, vibrant
Quality
Entropy : 6.89
Noise : 105
Prompt Clip Score : 0.25
AI Evaluation
Likelihood of AI : 0.20
Image errors : No visible errors.
Family Joy Under a Grand Sky
A heartwarming scene of a family of four standing before a majestic building, bathed in the glow of a bright blue sky. The architecture evokes a sense of history and grandeur, while the family’s presence adds a touch of warmth and joy to the composition.
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 four posing in front of a large stone building in a sunny day. There is a clear blue sky.
Aesthetic Score : 0.6
Mood : happy, cheerful, family
Quality
Entropy : 6.57
Noise : 102
Prompt Clip Score : 0.27
AI Evaluation
Likelihood of AI : 0.10
Image errors : No major errors.
Conclusion
The results show that the generative AI model performed well in terms of camera position and shot analysis, but struggled with aesthetic analysis. Here’s a breakdown:
- Camera Position: The model scored 0.4, which is considered below average. This suggests that the model didn’t accurately capture the intended camera positions described in the prompt.
- Shot Analysis: The model scored 0.54, which is considered average. This indicates that the model was able to understand the scene in the prompt to a reasonable degree, but not exceptionally well.
- Aesthetic Analysis: The model scored 0.1, which is considered very good. This means that the generated image closely matched the expected aesthetic style described in the prompt.
Overall, the model seems to be better at understanding the aesthetic style of the prompt than it is at accurately capturing 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://docs.aws.amazon.com/bedrock/latest/userguide/titan-image-models.html