AI's Struggle with Camera Angles: A Look at Facial Expressions in Storytelling with Titan-g1
- 9 minutes read - 1888 wordsTable of Contents
Facial expressions are a powerful tool in storytelling, conveying emotions and adding depth to characters. The way a character’s face is captured, through camera angles and framing, can significantly impact the audience’s perception. This blog post explores the capabilities of AI in generating scenes with specific camera angles and facial expressions, analyzing the results of a test and discussing the implications for the future of AI-generated content.
Created with: titan-g1
A Solitary Figure Against the Vastness
A woman stands alone on a hill, her small form dwarfed by the expansive landscape. The muted blue sky and the mix of browns and greens create a sense of melancholy and contemplation, highlighting the woman’s isolation and the serenity of the scene.
Prompt
facial-expressions Determination: Solitude and resilience ; A lone figure; eye-level; Single Person; A vast, desolate landscape; cinematic
Characteristic
Shot : A woman with long blonde hair is standing on a hilltop, looking out at a vast, empty landscape. The sky is overcast, and the ground is covered in a mixture of dirt, grass, and rocks.
Aesthetic Score : 0.7
Mood : melancholy, solitude, contemplative
Quality
Entropy : 6.54
Noise : 99
Prompt Clip Score : 0.17
AI Evaluation
Likelihood of AI : 0.10
Image errors : There is some noise in the image, especially in the background, and the color is slightly washed out.
Lost in the Sunset’s Embrace
A young woman with long blonde hair stands on a rooftop, her gaze lost in the distance as the city lights begin to twinkle below. The soft glow of the setting sun casts a melancholic hue over the scene, highlighting her pensive expression and the feeling of longing in her heart.
Prompt
facial-expressions Determination: Courage and unwavering resolve ; A hero standing tall; low-angle; Hero; A burning city in the background; cinematic
Characteristic
Shot : A young woman with long blonde hair is standing on a rooftop, looking out over a city skyline. The sun is setting, casting a warm glow over the scene.
Aesthetic Score : 0.8
Mood : dreamy, melancholic, thoughtful
Quality
Entropy : 6.84
Noise : 93
Prompt Clip Score : 0.16
AI Evaluation
Likelihood of AI : 0.20
Image errors : None
Industrial Work: A Glimpse into the Everyday
This image captures the essence of industrial work, showcasing three scenes featuring men engaged in various tasks. The warehouse setting, casual attire, and flat lighting create a sense of everyday routine and a working environment.
Prompt
facial-expressions Determination: Grit and perseverance ; A worker pushing a heavy cart; eye-level; Normal People; A bustling factory floor; cinematic
Characteristic
Shot : The image shows a collage of three scenes, all set in a warehouse environment. The top left image showcases a worker moving boxes on a hand truck, the top right features a worker in a yellow hard hat looking directly at the camera, and the bottom right depicts a worker wearing an orange vest smiling and looking towards the camera.
Aesthetic Score : 0.4
Mood : industrial, working, casual
Quality
Entropy : 6.91
Noise : 112
Prompt Clip Score : 0.26
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image appears to have slight compression artifacts, particularly noticeable in the top left and bottom right sections.
Lost in the Code: The Blue Light of Focus
A young man, bathed in the blue glow of his computer screen, is completely absorbed in his work. The intensity of his focus is palpable, as he navigates the digital world with unwavering determination.
Prompt
facial-expressions Determination: Concentration and drive ; A gamer intensely focused on a screen; close-up; Gamer; A dimly lit room with glowing monitors; cinematic
Characteristic
Shot : A young man wearing headphones is seated in front of a computer, likely playing a game. The lighting is blue and the scene is a bit dark, with a focus on the man’s face.
Aesthetic Score : 0.6
Mood : focused, intense, concentrated
Quality
Entropy : 6.54
Noise : 101
Prompt Clip Score : 0.27
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image has some slight blurriness and noise, especially in the background.
Lost in the Storm: A Moment of Contemplation
A young woman gazes out of a window, her face etched with sadness, as a stormy sky hangs over the city. The image captures a moment of quiet contemplation, tinged with melancholy and a sense of dramatic tension.
Prompt
facial-expressions Determination: Inner strength and hope ; A woman staring out a window; eye-level; Single Person; A stormy sky; cinematic
Characteristic
Shot : A young woman looks out of a window with a somber expression. The window frame is visible on the left side of the frame and a view of a cityscape and cloudy sky is in the background.
Aesthetic Score : 0.6
Mood : pensive, melancholic, contemplative
Quality
Entropy : 6.91
Noise : 96
Prompt Clip Score : 0.24
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image appears to be slightly overexposed and the focus is a bit soft. There is some noise in the background which may be due to the image being taken in low-light conditions.
A Hero’s Quest: Mystery and Drama in a Ruined World
A lone figure, clad in fantasy armor, stands amidst the ruins, a torch held high against a stormy sky. His gaze is fixed on a mysterious object floating above, hinting at a perilous journey and a hidden destiny. The dramatic lighting and his reaching pose create a sense of epic adventure and impending danger.
Prompt
facial-expressions Determination: Victory and unwavering resolve ; A lone adventurer raises a glowing staff, a triumphant pose against a backdrop of a fantastical, ancient city in ruins.; cinematic
Characteristic
Shot : A man in a fantasy-themed costume stands in a crumbling city, holding a staff with a flame at the top. A mysterious object hangs in the background.
Aesthetic Score : 0.7
Mood : dramatic, hopeful, epic
Quality
Entropy : 6.94
Noise : 98
Prompt Clip Score : 0.31
AI Evaluation
Likelihood of AI : 0.50
Image errors : The lighting is a bit unnatural and the colors are a bit too saturated. The background seems somewhat blurry.
Family Faces Fire in Heartbreaking Collage
A powerful collage captures the raw emotion of a family facing a devastating fire. The images depict a young girl comforting a toddler, a mother and child seeking refuge, a house engulfed in flames, and a woman’s worried expression. The somber mood and dramatic use of fire create a sense of urgency and heartbreak.
Prompt
facial-expressions Determination: Resilience and unity ; A family huddled together; eye-level; Normal People; A burning house in the background; cinematic
Characteristic
Shot : The image shows a family in front of a house that is on fire. There is a woman holding a young boy in her arms, and another woman and young boy are in the background. The image is split into four sections, with the top two sections showing the family and the bottom two sections showing the house and surrounding area. The image is blurry and the colors are muted, which creates a sense of sadness and uncertainty. The fire is not very bright, but it is enough to be a danger to the people in the image.
Aesthetic Score : 0.5
Mood : sad, anxious, uncertain
Quality
Entropy : 6.90
Noise : 103
Prompt Clip Score : 0.28
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image is slightly blurry and the colors are muted. This could be due to the fact that the image was taken in low light conditions or that it was edited to create a certain mood.
The Focused Hands of a Tech Wizard
A close-up shot captures the intensity of a person typing on a keyboard, their hands moving with purpose. The mouse in the foreground and the computer monitor in the background create a techy atmosphere, highlighting the focused energy of the moment.
Prompt
facial-expressions Determination: Excitement and focus ; A gamer’s hands furiously typing on a keyboard; close-up; Gamer; A brightly lit gaming room; cinematic
Characteristic
Shot : A person is typing on a keyboard in a dimly lit room with some colorful light from a nearby monitor.
Aesthetic Score : 0.6
Mood : focused, techy, mysterious
Quality
Entropy : 6.83
Noise : 97
Prompt Clip Score : 0.27
AI Evaluation
Likelihood of AI : 0.20
Image errors : The lighting is a bit uneven, and there is some noise in the image.
Lost in Thought, Found in the Desert
A young woman with dark hair gazes thoughtfully into the distance, her serene expression reflecting the peace of the soft, warm desert light. The scene evokes a sense of quiet contemplation and inner peace.
Prompt
facial-expressions Determination: Hope and perseverance ; A lone traveler walks towards a distant beacon of light, its warmth a promise in the vast, silent expanse of the desert.; cinematic
Characteristic
Shot : A woman with a determined look gazing into the distance against a backdrop of a desert landscape.
Aesthetic Score : 0.7
Mood : serious, contemplative, hopeful
Quality
Entropy : 6.88
Noise : 92
Prompt Clip Score : 0.21
AI Evaluation
Likelihood of AI : 0.20
Image errors : No significant errors or artifacts.
Sunrise Triumph on the Mountain Peak
A lone hiker stands victorious on a mountain summit, arms raised in celebration as the sun paints the snowy landscape with golden hues. This inspiring scene captures the serenity and accomplishment of reaching a challenging goal.
Prompt
facial-expressions Determination: Confidence and unwavering resolve ; A lone figure stands on a mountain peak, silhouetted against a breathtaking sunrise over a vast, snow-capped landscape.; cinematic
Characteristic
Shot : A person stands with arms raised on a mountain peak with a sunrise in the background.
Aesthetic Score : 0.7
Mood : serene, uplifting, inspirational
Quality
Entropy : 6.84
Noise : 103
Prompt Clip Score : 0.24
AI Evaluation
Likelihood of AI : 0.30
Image errors : Some minor noise and blur
Conclusion
The analysis shows 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, indicating it did not perform well in capturing the intended camera position. A score between 0.5 and 0.75 would be considered good, and above 0.75 very good.
- Shot Analysis: The model scored 0.49, indicating it performed moderately well in understanding the scene described in the prompt. A score between 0.5 and 0.75 would be considered good, and above 0.75 very good.
- Aesthetic Analysis: The model scored 0.21, indicating it performed very well in capturing the intended aesthetic. A score between -0.2 and 0.1 is considered very good.
Overall, the model seems to be better at understanding the scene and capturing the desired aesthetic than it is at accurately representing the camera position.
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