AI's Facial Expressions: A Step Forward, But Still Room for Growth with Titan-g1
- 9 minutes read - 1901 wordsTable of Contents
The ability to generate realistic and expressive facial expressions is a crucial aspect of AI image generation. It allows for the creation of images that are not only visually appealing but also emotionally engaging. In this blog post, we explore the results of a generative AI model tasked with creating images based on detailed scene descriptions, focusing on the model’s performance in capturing facial expressions. We’ll delve into the model’s strengths and weaknesses, highlighting the areas where it excels and where it needs improvement. By understanding the current state of AI image generation, we can gain insights into the future of this exciting technology.
Created with: titan-g1
Lost in Thought: A Moment of Contemplation in the Park
A young man, cloaked in a black jacket, sits alone on a park bench, his gaze fixed on the distance. The image evokes a sense of pensive reflection, as he seems lost in his own thoughts, creating a mood of quiet contemplation and isolation.
Prompt
facial-expressions Attentiveness: Melancholy, yet observant ; A lone figure sitting on a park bench; eye-level; Single Person; bustling city park in the background; cinematic
Characteristic
Shot : A young man in a black jacket is sitting on a bench in a park. He is looking off into the distance, and his expression is thoughtful.
Aesthetic Score : 0.6
Mood : thoughtful, contemplative, calm
Quality
Entropy : 6.91
Noise : 98
Prompt Clip Score : 0.23
AI Evaluation
Likelihood of AI : 0.10
Image errors : The image has some noise and grain, particularly in the background.
City Lights, City Dreams
A young woman in a blue dress stands on a rooftop, gazing out at the city lights. The bokeh effect creates a dreamy atmosphere, hinting at a melancholic yet hopeful mood. Her gaze, directed off-camera, adds a touch of mystery and intrigue to the scene.
Prompt
facial-expressions Attentiveness: Determined, vigilant ; A superhero standing on a rooftop, looking out over the city; eye-level; Hero; cityscape with twinkling lights; cinematic
Characteristic
Shot : A young woman in a dark blue polka dot dress is looking out over a city at night. The city is blurred out in the background, and the woman’s face is sharp and in focus. There are lights in the distance.
Aesthetic Score : 0.6
Mood : melancholy, contemplative, romantic
Quality
Entropy : 6.91
Noise : 101
Prompt Clip Score : 0.21
AI Evaluation
Likelihood of AI : 0.10
Image errors : The image has some slight blurriness in the background, particularly around the city lights. This could be due to camera shake or a long exposure.
Lost in the Pages, Bathed in Soft Light
A woman finds solace in a book, the gentle glow of natural light illuminating her peaceful contemplation as she journeys by train. The scene evokes a sense of calm and quiet reflection, capturing the beauty of a simple moment.
Prompt
facial-expressions Attentiveness: Focused, absorbed ; A woman reading a book on a train; eye-level; Normal Person; blurred passengers and train windows; cinematic
Characteristic
Shot : A young woman is sitting on a train reading a book. She has long brown hair, a grey shirt, and a dark blue cardigan. The train window shows a blurry view of the landscape outside.
Aesthetic Score : 0.6
Mood : calm, contemplative, pensive
Quality
Entropy : 6.85
Noise : 102
Prompt Clip Score : 0.32
AI Evaluation
Likelihood of AI : 0.20
Image errors : There is some noise and blur in the image, especially in the background.
Gamer’s Paradise: Blue and Red Lights Fuel the Excitement
Capture the thrill of victory! This image showcases a young man immersed in a video game, his excitement palpable under the dynamic blue and red lighting. The scene is bursting with energy and playful spirit, making it a perfect representation of the joy of gaming.
Prompt
facial-expressions Attentiveness: Thrilled, competitive ; A gamer intensely focused on a screen, fingers flying across the keyboard; close-up; Gamer; dimly lit room with glowing monitor; cinematic
Characteristic
Shot : A young man wearing a headset is in a dimly lit room, looking towards the viewer. He is using a keyboard, and his hand is raised as if he is shouting or exclaiming something.
Aesthetic Score : 0.6
Mood : intense, engaged, excited
Quality
Entropy : 6.86
Noise : 101
Prompt Clip Score : 0.27
AI Evaluation
Likelihood of AI : 0.10
Image errors : Some artifacts are visible in the background, especially on the monitor screen. These could be removed with post-processing.
Lost in the City: A Moment of Contemplation
A young man strolls through a bustling city, his gaze fixed on the towering buildings. The blurred background and natural light create a sense of isolation and introspection, capturing a fleeting moment of contemplation in the urban landscape.
Prompt
facial-expressions Attentiveness: Lost in thought, introspective ; A man walking down a crowded street, seemingly oblivious to the chaos around him; eye-level; Single Person; bustling city street with people and traffic; cinematic
Characteristic
Shot : A man is standing on a city street, looking off into the distance. He is surrounded by other people, cars, and buildings. The overall impression is of a quiet, reflective moment in the midst of a busy city.
Aesthetic Score : 0.6
Mood : pensive, urban, contemplative
Quality
Entropy : 6.89
Noise : 97
Prompt Clip Score : 0.22
AI Evaluation
Likelihood of AI : 0.20
Image errors : There are no noticeable artifacts or errors in the image.
Lost in the Mist: A Moment of Contemplation on the Edge
A lone woman, backpack in tow, stands at the precipice of a misty valley. The scene evokes a sense of serenity and adventure, with the swirling mist adding an element of mystery to her contemplative pose.
Prompt
facial-expressions Attentiveness: fearless ; An adventurer stands at the precipice of a colossal, shimmering canyon, gazing up at a swirling vortex of vibrant mist in the sky. The air vibrates with an ancient energy, and the ground beneath their feet is covered in the remnants of forgotten, crystalline structures.; cinematic
Characteristic
Shot : A woman with a backpack is standing on a cliff overlooking a canyon with mist flowing through it.
Aesthetic Score : 0.7
Mood : serene, adventurous, contemplative
Quality
Entropy : 6.87
Noise : 103
Prompt Clip Score : 0.22
AI Evaluation
Likelihood of AI : 0.20
Image errors : No significant errors, but the mist might be slightly over-processed. Some slight color banding in the sky.
A Moment of Shared Joy: Grandmother and Granddaughter Connect
This heartwarming image captures a grandmother and granddaughter sharing a special moment together. The close-up shot highlights their genuine connection, with warm smiles and affectionate gestures. The scene radiates warmth and intimacy, showcasing the enduring bond between generations.
Prompt
facial-expressions Attentiveness: Curious, engaged ; A young girl listening intently to her grandmother tell a story; eye-level; Normal Person; cozy living room with warm lighting; cinematic
Characteristic
Shot : A grandmother and granddaughter are sitting on a couch together, talking and smiling. The grandmother is wearing a blue sweater and the granddaughter is wearing a white sweater.
Aesthetic Score : 0.6
Mood : warm, happy, intimate
Quality
Entropy : 6.92
Noise : 103
Prompt Clip Score : 0.30
AI Evaluation
Likelihood of AI : 0.20
Image errors : No noticeable errors.
Victory Dance! Gamer Reacts with Pure Joy
This image captures the pure joy of a gamer experiencing a triumphant moment. The young man’s enthusiastic fist pump and beaming smile radiate excitement, while the dynamic lighting adds to the energetic atmosphere. The presence of another person in the background suggests a shared experience and adds to the sense of camaraderie.
Prompt
facial-expressions Attentiveness: Joyful, triumphant ; A gamer celebrating a victory, eyes wide with excitement; close-up; Gamer; brightly lit room with cheering friends; cinematic
Characteristic
Shot : A young man is wearing headphones and cheering with his arms raised in the air. He is in a brightly lit room, likely a gaming room, with another person in the background.
Aesthetic Score : 0.6
Mood : joyful, excited, celebratory
Quality
Entropy : 6.94
Noise : 100
Prompt Clip Score : 0.29
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image has some noise and grain, especially in the darker areas. There is also some blurring in the background.
Lost in Thought: A Moment of Quiet Contemplation
A woman, dressed in black, sits in a cafe, her gaze fixed on the world outside. The soft lighting and her pensive expression create a sense of quiet contemplation, as if she’s lost in thought, perhaps reflecting on the beauty of the flowers in the background.
Prompt
facial-expressions Attentiveness: Observant, introspective ; A woman sitting alone in a cafe, observing the people around her; eye-level; Single Person; bustling cafe with tables and chairs; cinematic
Characteristic
Shot : A young woman sitting in a cafe, looking out of a window. There is a bouquet of flowers and a cup of coffee on the table in front of her.
Aesthetic Score : 0.7
Mood : pensive, contemplative, cozy
Quality
Entropy : 6.84
Noise : 100
Prompt Clip Score : 0.27
AI Evaluation
Likelihood of AI : 0.10
Image errors : The background is slightly blurry, and there are some distracting elements in the image, such as the flowers and the person in the window.
Solitude on the Edge: A Woman Finds Tranquility Amidst the Mountains
A woman stands on a cliff, dwarfed by the vastness of the mountain range. The muted colors and overcast sky create a sense of tranquility and solitude, inviting contemplation and a sense of awe at the natural world.
Prompt
facial-expressions Attentiveness: Reflective, contemplative ; A hero standing on a cliff, looking out at the vast landscape; eye-level; Hero; dramatic mountain range with clouds and sunlight; cinematic
Characteristic
Shot : A woman is standing on a mountain top looking out at the view. She is wearing a dark jacket and her hair is pulled back.
Aesthetic Score : 0.7
Mood : thoughtful, contemplative, serene
Quality
Entropy : 6.86
Noise : 98
Prompt Clip Score : 0.24
AI Evaluation
Likelihood of AI : 0.20
Image errors : There are no visible errors in the image.
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 0.15, which is below the “good” range of 0.5 to 0.75. This indicates that the model didn’t accurately capture the intended camera position described in the prompt.
- Shot Analysis: The model scored 0.57, which falls within the “good” range. This means the model was able to understand the scene described in the prompt and create an image that reflects it reasonably well.
- Aesthetic Analysis: The model scored 0.19, which is significantly higher than the “very good” range of -0.2 to 0.1. This suggests that the generated image’s aesthetic deviated significantly from the expected aesthetic described in the prompt.
Overall, the model shows promise in understanding the scene and camera position, but needs improvement in capturing the desired aesthetic.
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