AI's Facial Expressions: A Mixed Bag of Success with Titan-g1
- 8 minutes read - 1683 wordsTable of Contents
Facial expressions are a powerful tool for conveying emotions and intentions in visual storytelling. Dramatic facial expressions, in particular, can add depth and impact to a scene. Generative AI models are increasingly being used to create images with realistic facial expressions, but how well do they capture the nuances of human emotion? This blog post delves into the performance of a generative AI model in creating images with facial expressions across a range of scenes, exploring its strengths and weaknesses in capturing camera position, shot composition, and aesthetic style. We’ll examine examples where the model excels and where it needs improvement, providing insights into the current state of AI’s ability to generate expressive imagery.
Created with: titan-g1
Lost in the City Lights
A solitary figure stands amidst the urban blur, her gaze lost in the distance. The shallow depth of field emphasizes her isolation, creating a mood of pensive introspection.
Prompt
facial-expressions Agreement: melancholy, contemplative ; A lone figure; eye-level; Single Person; a bustling city street at night; cinematic
Characteristic
Shot : A woman stands on a city street at night, looking into the distance. The street lights blur into bokeh.
Aesthetic Score : 0.7
Mood : melancholy, introspective, urban
Quality
Entropy : 6.75
Noise : 101
Prompt Clip Score : 0.22
AI Evaluation
Likelihood of AI : 0.20
Image errors : No noticeable artifacts or errors.
Reaching for the Top: Ambition and Confidence in the City
A man in a sharp suit stands confidently before a towering skyscraper, his gaze fixed upwards. His crossed arms and determined expression convey a sense of ambition and professional drive, capturing the essence of urban aspiration.
Prompt
facial-expressions Agreement: determined, resolute ; A superhero standing tall; eye-level; Hero; a cityscape with a burning building in the background; cinematic
Characteristic
Shot : A man in a suit standing in front of a tall building, looking up
Aesthetic Score : 0.6
Mood : determined, confident, professional
Quality
Entropy : 6.87
Noise : 95
Prompt Clip Score : 0.18
AI Evaluation
Likelihood of AI : 0.20
Image errors : No visible errors
Laughter and Love Fill the Dinner Table
A heartwarming scene of a woman sharing laughter and joy with her family at the dinner table. The intimate focus on her face captures the warmth and happiness of the moment.
Prompt
facial-expressions Agreement: peaceful, content ; A family gathered around a dinner table; eye-level; Normal People; a cozy kitchen with warm lighting; cinematic
Characteristic
Shot : A woman is laughing at a dinner table, the scene is warm and intimate.
Aesthetic Score : 0.7
Mood : happy, warm, inviting
Quality
Entropy : 6.87
Noise : 102
Prompt Clip Score : 0.29
AI Evaluation
Likelihood of AI : 0.30
Image errors : Slight blurriness around the edges of the image.
Joyful Victory: Gamer Celebrates with Enthusiasm
A young woman beams with joy, headphones on, as she waves her hand in front of her computer. The vibrant colors and her energetic expression capture the excitement of a gaming triumph or a positive online interaction.
Prompt
facial-expressions Agreement: excited, engaged ; A gamer intensely focused on a screen; eye-level; Gamer; a dimly lit room with neon lights reflecting on the screen; cinematic
Characteristic
Shot : A young woman is sitting in front of a computer, wearing headphones and a denim jacket. She is smiling and waving her hand, as if she is excited about something. The background is blurred, and the scene is lit by bright blue and purple lights. A keyboard and a mouse are visible in the foreground.
Aesthetic Score : 0.6
Mood : excited, playful, joyful
Quality
Entropy : 6.86
Noise : 104
Prompt Clip Score : 0.25
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image is a little bit blurry, and the colors are a bit oversaturated.
Lost in Thought on the City Streets
A woman in a black leather jacket stands alone on a city street, her gaze fixed on something beyond the frame. The blurred background and her pensive expression create a sense of isolation and mystery, capturing the edgy mood of urban life.
Prompt
facial-expressions Agreement: reflective, introspective ; A woman walking down a quiet street; eye-level; Single Person; a row of old, brick buildings with faded paint; cinematic
Characteristic
Shot : A young woman with short, dark hair is standing in an urban setting, looking off to the side. She is wearing a black leather jacket, and the background is a blurred cityscape.
Aesthetic Score : 0.7
Mood : confident, stylish, urban
Quality
Entropy : 6.93
Noise : 95
Prompt Clip Score : 0.24
AI Evaluation
Likelihood of AI : 0.10
Image errors : No visible artifacts or errors.
Defiance in the Storm’s Eye
A woman stands resolute against a backdrop of raging thunder and lightning, her clenched fist a symbol of defiance and unwavering determination. The dramatic scene captures a moment of intense emotion, leaving the viewer to ponder the story behind her fierce spirit.
Prompt
facial-expressions Agreement: powerful, defiant ; A hero raising their fist in defiance; eye-level; Hero; a dark, stormy sky with lightning flashing in the background; cinematic
Characteristic
Shot : A woman with a determined expression stands in front of a dark stormy sky. Lightning strikes in the background.
Aesthetic Score : 0.4
Mood : intense, dramatic, powerful
Quality
Entropy : 6.89
Noise : 106
Prompt Clip Score : 0.23
AI Evaluation
Likelihood of AI : 0.30
Image errors : There are some minor artifacts and noise in the image.
Laughter Under the Blossoms: A Moment of Pure Joy
Three friends share a moment of genuine laughter under a blooming tree, bathed in soft natural light. Their carefree joy is infectious, capturing the essence of friendship and happiness.
Prompt
facial-expressions Agreement: joyful, carefree ; A group of friends laughing together; eye-level; Normal People; a sunny park with trees and flowers; cinematic
Characteristic
Shot : Three young women are laughing together in front of a flowering tree.
Aesthetic Score : 0.8
Mood : joyful, carefree, friendly
Quality
Entropy : 6.94
Noise : 107
Prompt Clip Score : 0.26
AI Evaluation
Likelihood of AI : 0.20
Image errors : No noticeable errors
Confetti Celebration: Young Man’s Joyful Victory
Capture the energy of a triumphant moment as a young man, adorned with headphones, basks in the glow of victory amidst a flurry of confetti. Vibrant colors and his ecstatic expression paint a picture of pure joy and celebration.
Prompt
facial-expressions Agreement: triumphant, ecstatic ; A gamer celebrating a victory; eye-level; Gamer; a brightly lit room with confetti and streamers; cinematic
Characteristic
Shot : A young man wearing headphones is celebrating with confetti falling around him. He is laughing and has his arms raised in the air. There is a shelf in the background.
Aesthetic Score : 0.7
Mood : joyful, energetic, celebratory
Quality
Entropy : 6.88
Noise : 94
Prompt Clip Score : 0.30
AI Evaluation
Likelihood of AI : 0.10
Image errors : no visible errors
Lost in Thought: A Moment of Melancholy in the Park
A young man, cloaked in black, sits alone on a park bench, his gaze fixed on the viewer. The blurred background and scattered leaves create a sense of quiet contemplation, hinting at a moment of introspection and perhaps even loneliness. The image evokes a mood of melancholy, leaving the viewer to ponder the man’s thoughts and emotions.
Prompt
facial-expressions Agreement: lonely, melancholic ; A man sitting alone on a bench; eye-level; Single Person; a deserted park with fallen leaves; cinematic
Characteristic
Shot : A man in a dark jacket is sitting in a park, looking thoughtfully off-camera. The background is blurred, suggesting a shallow depth of field, and the leaves on the ground indicate a fall setting.
Aesthetic Score : 0.7
Mood : pensive, introspective, contemplative
Quality
Entropy : 6.93
Noise : 96
Prompt Clip Score : 0.19
AI Evaluation
Likelihood of AI : 0.20
Image errors : No visible artifacts or errors.
A City of Dreams at Dusk
A young woman in a polka dot dress gazes out at the city skyline, bathed in the soft light of dusk. Her expression is a mix of hope, contemplation, and wistful longing, capturing the aspirations and dreams that lie within the urban landscape.
Prompt
facial-expressions Agreement: determined, hopeful ; A hero standing on a rooftop overlooking the city; eye-level; Hero; a panoramic view of a city skyline at night; cinematic
Characteristic
Shot : A woman is standing in front of a cityscape at dusk. She is looking out over the cityscape and has a slight smile on her face.
Aesthetic Score : 0.7
Mood : pensive, hopeful, romantic
Quality
Entropy : 6.72
Noise : 104
Prompt Clip Score : 0.20
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image has a slight amount of blurriness, especially in the background. The lighting is a bit flat, but overall the image is technically sound.
Conclusion
The results of the analysis 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 0.2, 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 0.54, which is considered good. This indicates that the model was able to understand the scene described in the prompt and create a shot that aligns with it.
- Aesthetic Analysis: The model scored 0.09, which is considered very good. This means that the generated image closely matched the expected aesthetic style.
Overall, the model demonstrates a good understanding of the scene and shot composition, but needs improvement in accurately capturing the intended camera position. The aesthetic quality of the generated image is very good.
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