AI's Artistic Eye: Capturing Emotion, Missing the Mark on Aesthetics with Titan-g1
- 9 minutes read - 1804 wordsTable of Contents
In the realm of artificial intelligence, the ability to generate realistic and emotionally evocative images is a coveted goal. This case study examines the performance of a generative AI model in capturing facial expressions within various scenes. While the model demonstrates a strong understanding of shot composition, it struggles to accurately portray the subtle nuances of human emotion and meet the aesthetic expectations set by the prompts. This analysis highlights the challenges and opportunities in developing AI models that can truly capture the essence of human expression.
Created with: titan-g1
Lost in Thought: A Moment of Quiet Contemplation
A young man walks through an urban landscape, his back to the camera, lost in thought. The blurred background suggests movement, while his pensive gaze draws the viewer into his world of quiet contemplation.
Prompt
facial-expressions Daydreaming: Melancholy, lost in thought ; A lone figure; eye-level; Single Person; bustling city street; cinematic
Characteristic
Shot : A young man is walking down the street in an urban setting. The background is blurred, and the focus is on the man’s face.
Aesthetic Score : 0.6
Mood : pensive, introspective, thoughtful
Quality
Entropy : 6.93
Noise : 94
Prompt Clip Score : 0.20
AI Evaluation
Likelihood of AI : 0.20
Image errors : No significant errors
Silhouetted Against the Sunset: A Moment of Solitude on the Mountaintop
A lone figure stands on a snow-covered peak, bathed in the warm glow of the setting sun. The scene evokes a sense of serenity and contemplation, with the man’s silhouette against the sky creating a powerful image of isolation and introspection.
Prompt
facial-expressions Daydreaming: Confident, determined ; A lone figure stands on a mountain peak, silhouetted against the rising sun, gazing out at a vast, snow-capped landscape.; cinematic
Characteristic
Shot : A man stands on a snowy mountain peak, looking out at a vast snowy valley and distant mountains. The sun is setting, casting a golden glow over the landscape.
Aesthetic Score : 0.7
Mood : tranquil, serene, contemplative
Quality
Entropy : 6.84
Noise : 99
Prompt Clip Score : 0.24
AI Evaluation
Likelihood of AI : 0.20
Image errors : Some minor artifacts are visible in the sky, and the image appears slightly grainy. This is likely due to compression or post-processing.
A Moment of Quiet Contemplation
A woman finds solace in a warm cup of coffee, gazing out the window with a pensive expression. The soft lighting and cozy atmosphere create a sense of calm and reflection.
Prompt
facial-expressions Daydreaming: Peaceful, content ; A woman sipping coffee in a cafe; eye-level; Normal People; warm, inviting cafe interior; cinematic
Characteristic
Shot : A young woman is sitting at a cafe, looking out the window, holding a cup of coffee. A coffee pot is visible on the table in front of her.
Aesthetic Score : 0.7
Mood : calm, contemplative, cozy
Quality
Entropy : 6.77
Noise : 104
Prompt Clip Score : 0.28
AI Evaluation
Likelihood of AI : 0.40
Image errors : The image is slightly blurry, and there are some artifacts around the edges of the woman’s hair. There is a slightly noticeable graininess to the image. The background blur also appears somewhat artificial.
The Moment He Knew He Was In For a Wild Ride
A young man, headphones on, sits glued to his computer screen, his expression a mix of surprise and intense focus. The image captures the thrill of the game, the anticipation of the next move, and the pure joy of being fully immersed in the digital world.
Prompt
facial-expressions Daydreaming: Engrossed, excited ; A gamer intensely focused on a screen; close-up; Gamer; dimly lit room with gaming peripherals; cinematic
Characteristic
Shot : A young man wearing headphones is playing a game on his computer. He is looking intensely at the screen. The lighting is blue and purple, and the scene is set in a dimly lit room.
Aesthetic Score : 0.6
Mood : intense, focused, excited
Quality
Entropy : 6.72
Noise : 104
Prompt Clip Score : 0.25
AI Evaluation
Likelihood of AI : 0.10
Image errors : There are no obvious errors in the image.
A Moment of Reflection: A Young Girl Gazes into the Distance
A young girl stands by a window, her gaze lost in the distance. The soft focus of the background creates a sense of longing and isolation, hinting at a pensive and wistful mood. The partially obscured window frame adds a touch of mystery to the scene, leaving the viewer to wonder what thoughts are passing through the girl’s mind.
Prompt
facial-expressions Daydreaming: Curious, imaginative ; A child staring out a window; eye-level; Single Person; lush green garden; cinematic
Characteristic
Shot : A young girl looks out of a window, with a blurry background of green foliage and a building.
Aesthetic Score : 0.6
Mood : pensive, wistful, curious
Quality
Entropy : 6.87
Noise : 103
Prompt Clip Score : 0.28
AI Evaluation
Likelihood of AI : 0.10
Image errors : Some minor blurriness in the background. The girl’s hair seems slightly pixelated.
Witnessing the Magic: A Woman Gazes in Awe at the Aurora Borealis
A solitary figure stands in the heart of a winter wonderland, captivated by the celestial spectacle of the aurora borealis. The vibrant green and purple hues of the northern lights dance across the night sky, creating a breathtaking contrast against the snow-covered mountains and the darkness of the night. This serene scene evokes a sense of wonder and awe, capturing the beauty and majesty of nature’s most spectacular displays.
Prompt
facial-expressions Daydreaming: adventurous ; A explorer standing on the edge of a vast, snow-covered plateau; wide shot; Hero; towering ice mountains with shimmering auroras; cinematic
Characteristic
Shot : A woman in a winter coat and hat stands in front of a snowy mountain range with the aurora borealis in the sky.
Aesthetic Score : 0.75
Mood : serene, adventurous, magical
Quality
Entropy : 6.87
Noise : 102
Prompt Clip Score : 0.26
AI Evaluation
Likelihood of AI : 0.20
Image errors : There are some minor image artifacts, particularly in the snowy areas.
Laughter and Sunshine: Friends Enjoy a Perfect Picnic Day
Capture the joy of friendship with this heartwarming image. Three friends share laughter and good times on a sunny picnic, surrounded by lush greenery. The composition highlights their happiness, creating a warm and inviting atmosphere.
Prompt
facial-expressions Daydreaming: Joyful, carefree ; A group of friends laughing together at a picnic; eye-level; Normal People; sunny park with picnic blanket; cinematic
Characteristic
Shot : Three friends are laughing while sitting on a blanket in a park
Aesthetic Score : 0.7
Mood : joyful, carefree, happy
Quality
Entropy : 6.83
Noise : 98
Prompt Clip Score : 0.26
AI Evaluation
Likelihood of AI : 0.10
Image errors : No visible artifacts or errors
The Hacker’s Hands: A Close-Up Look at Digital Intrigue
A dimly lit room, a focused figure, and the rhythmic click of keys. This image captures the essence of digital mystery, with the close-up shot on the hands emphasizing the intensity of the moment. The lighting adds a layer of intrigue, leaving you wondering what secrets are being typed.
Prompt
facial-expressions Daydreaming: Thrilled, competitive ; A gamer’s hands rapidly moving across a keyboard; close-up; Gamer; brightly lit gaming setup with glowing screen; cinematic
Characteristic
Shot : A close-up of a person’s hands typing on a backlit keyboard in a dimly lit room. A computer monitor and mouse are visible in the background.
Aesthetic Score : 0.6
Mood : focused, techy, intense
Quality
Entropy : 6.88
Noise : 99
Prompt Clip Score : 0.27
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image is slightly overexposed, with some parts of the image being too bright. There is also some noise in the image, particularly in the shadows.
Finding Serenity on the Shores
A solitary figure stands on a tranquil beach, gazing out at the endless expanse of the ocean. The gentle crashing of waves and the vastness of the horizon evoke a sense of calm and contemplation. This image captures the essence of serenity, inviting viewers to find peace in the beauty of nature.
Prompt
facial-expressions Daydreaming: Reflective, introspective ; A woman walking alone on a beach; eye-level; Single Person; vast, empty beach with crashing waves; cinematic
Characteristic
Shot : A person is standing on a sandy beach, looking out at the ocean. The waves are crashing on the shore, and the sky is a muted gray. There are some small trees and bushes in the background.
Aesthetic Score : 0.6
Mood : peaceful, contemplative, serene
Quality
Entropy : 6.48
Noise : 95
Prompt Clip Score : 0.21
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image has a slight graininess. Some minor noise can be seen in the darker areas of the image.
Superhero Soaring Above the City
A powerful image captures a superhero in flight, his cape billowing behind him as he races over a bustling cityscape. The blur of the city below emphasizes his speed and strength, creating a sense of heroic optimism and hope.
Prompt
facial-expressions Daydreaming: Empowered, triumphant ; A superhero soaring through the sky; high angle; Hero; dramatic cloudscape with city skyline in the distance; cinematic
Characteristic
Shot : A superhero in a red cape flies over a city. He looks happy and confident, with a bright smile and the sky is bright with clouds.
Aesthetic Score : 0.6
Mood : happy, hopeful, confident
Quality
Entropy : 6.81
Noise : 99
Prompt Clip Score : 0.23
AI Evaluation
Likelihood of AI : 0.50
Image errors : No visible errors, but the image has a slight unnatural sheen, as if it was digitally enhanced, making it look a bit fake
Conclusion
The results show that the generative AI model performed well in understanding the camera position and shot composition, but struggled with the aesthetic expectations. Here’s a breakdown:
- Camera Position: The model scored 0.31, which is considered below average. This suggests that the model didn’t accurately capture the intended camera position described in the prompt.
- Shot Analysis: The model scored 0.53, which is considered good. This indicates that the model was able to understand and translate the scene description from the prompt into a visually coherent shot.
- Aesthetic Analysis: The model scored 0.14, which is considered okay. This means that the generated image’s aesthetic deviated slightly from the expected aesthetic described in the prompt.
Overall, the model demonstrated a good understanding of shot composition but struggled with camera positioning and aesthetic expectations.
Sources:
- https://dramaresource.com/storytelling/
- https://seedsoftellers.eu/resources/the-body-language-for-young-tellers/
- https://digitalcollections.sit.edu/cgi/viewcontent.cgi?article=1288&context=sandanona&filename=1&type=additional
- https://citeseerx.ist.psu.edu/document?doi=7f842882e9bb1fa2c0e96939bc8d2c37e34e17c0&repid=rep1&type=pdf
- https://www.twinkl.co.uk/search?q=drama+facial+expression
- https://docs.aws.amazon.com/bedrock/latest/userguide/titan-image-models.html