AI Captures the Mood, But Struggles with the Details with Titan-g1
- 9 minutes read - 1725 wordsTable of Contents
Facial expressions are a powerful tool in storytelling, conveying emotions and intentions without words. Dramatic facial expressions, in particular, can heighten the impact of a scene, drawing the viewer in and amplifying the emotional resonance. This is often seen in film and television, where actors use their faces to convey a wide range of emotions, from joy and love to anger and despair. In this blog post, we’ll explore how a generative AI model is being used to create images with dramatic facial expressions, and we’ll examine its strengths and weaknesses in capturing the nuances of human emotion.
Created with: titan-g1
Lost in the Rain: A Moment of Melancholy
A woman sits alone in a cafe, her gaze fixed on the rain outside. The somber atmosphere and her contemplative expression evoke a sense of wistful loneliness, amplified by the isolating effect of the downpour.
Prompt
facial-expressions Worry: melancholy, lonely ; Single woman; eye-level; Single Persons; dimly lit coffee shop with rain outside; cinematic
Characteristic
Shot : A woman sits by a window in a cafe, looking out at the rainy street. There is a cup of coffee in front of her.
Aesthetic Score : 0.7
Mood : pensive, melancholic, contemplative
Quality
Entropy : 6.75
Noise : 107
Prompt Clip Score : 0.25
AI Evaluation
Likelihood of AI : 0.10
Image errors : There are some slight artifacts in the image, particularly in the background. The lighting is a bit flat and uneven.
Superhero Stands Tall, Ready for Action
A determined superhero, bathed in dramatic lighting, gazes upwards, ready to face whatever challenge awaits. The scene evokes a sense of heroism and intensity, leaving the viewer eager to know what lies ahead.
Prompt
facial-expressions Worry: intense, burdened ; Man in a superhero costume; medium shot; Heroes; cityscape at night with flashing sirens; cinematic
Characteristic
Shot : A man dressed as a superhero is standing on a city street at night, he is looking up with a dramatic expression on his face.
Aesthetic Score : 0.5
Mood : dramatic, intense, hopeful
Quality
Entropy : 6.87
Noise : 107
Prompt Clip Score : 0.26
AI Evaluation
Likelihood of AI : 0.10
Image errors : The image has some slight blurriness, particularly in the background.
Lost in the Crowd: A Woman’s Silent Struggle
A close-up shot captures the anxious face of a young woman amidst the blur of a crowded subway car. Her isolation and unease are palpable, leaving the viewer wondering what secrets lie beneath the surface.
Prompt
facial-expressions Worry: anxious, overwhelmed ; Young woman in a crowded subway; eye-level; Normal People; blurred faces of commuters; cinematic
Characteristic
Shot : A young woman is standing in a crowded subway car. Her expression is concerned and she is looking off to the side.
Aesthetic Score : 0.6
Mood : tense, anxious, unsettling
Quality
Entropy : 6.92
Noise : 100
Prompt Clip Score : 0.29
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image is slightly blurry and there are some artifacts in the background.
Lost in the Code: A Moment of Intense Focus
A young man, headphones on, stares intently at his computer screen in a dimly lit room. The atmosphere is one of focused concentration, hinting at a project demanding his full attention. The scene evokes a sense of quiet intensity and the thrill of a challenge.
Prompt
facial-expressions Worry: intense, focused ; Gamer with headphones on; close-up; Gamer; dimly lit room with glowing computer screen; cinematic
Characteristic
Shot : A young man wearing headphones is looking intently at a screen, likely playing a video game. The background is blurred, suggesting a focused, intimate atmosphere.
Aesthetic Score : 0.6
Mood : focused, intense, serious
Quality
Entropy : 6.65
Noise : 104
Prompt Clip Score : 0.31
AI Evaluation
Likelihood of AI : 0.10
Image errors : Some slight noise and compression artifacts are visible, particularly in the background.
Lost in Autumn’s Embrace
A solitary figure sits amidst fallen leaves, lost in thought. The muted colors and the man’s pensive posture evoke a sense of melancholy and introspection, highlighting the beauty and solitude of autumn.
Prompt
facial-expressions Worry: sad, reflective ; Man sitting alone on a park bench; long shot; Single Persons; empty park with falling leaves; cinematic
Characteristic
Shot : A man is sitting on a bench in a park, lost in thought. The leaves are falling around him and the background is blurred.
Aesthetic Score : 0.6
Mood : melancholy, contemplative, introspective
Quality
Entropy : 6.91
Noise : 98
Prompt Clip Score : 0.27
AI Evaluation
Likelihood of AI : 0.20
Image errors : No major errors, but the image appears slightly soft and lacks sharpness. The background also appears somewhat muted.
City in Flames: A Woman on the Edge
A solitary figure silhouetted against a fiery cityscape. A woman in a black leather jacket stands on a rooftop, her gaze fixed on the inferno below. The scene is both dramatic and ominous, hinting at a story of loss, danger, and perhaps even hope.
Prompt
facial-expressions Worry: determined, resolute ; Heroine standing on a rooftop; medium shot; Heroes; cityscape with smoke and fire in the distance; cinematic
Characteristic
Shot : A woman in a black leather jacket stands on a rooftop looking out at a city with a fire in the distance. The smoke is billowing in the background.
Aesthetic Score : 0.6
Mood : dramatic, tense, somber
Quality
Entropy : 6.77
Noise : 93
Prompt Clip Score : 0.26
AI Evaluation
Likelihood of AI : 0.20
Image errors : None
Kitchen Confrontation: A Couple’s Heated Argument
A tense moment unfolds in a kitchen as a couple engages in a heated argument. Their expressions and gestures reveal the intensity of their disagreement, capturing a raw and emotional scene.
Prompt
facial-expressions Worry: tense, frustrated ; Couple arguing in a kitchen; eye-level; Normal People; cluttered kitchen with dirty dishes; cinematic
Characteristic
Shot : A couple is arguing in the kitchen, the woman is facing the camera and the man is facing away, the kitchen is cluttered with dishes and cooking supplies.
Aesthetic Score : 0.3
Mood : tense, conflict, unhappy
Quality
Entropy : 6.85
Noise : 104
Prompt Clip Score : 0.30
AI Evaluation
Likelihood of AI : 0.20
Image errors : No significant errors, the image is somewhat blurry but this is likely due to the action in the scene.
Caught in the Moment: A Face of Surprise and Focus
A close-up shot captures the intense surprise of a person wearing a headset, seated in front of a computer. Their focused expression and the cropped framing create a sense of drama and immediacy, leaving the viewer wondering what sparked this reaction.
Prompt
facial-expressions Worry: intense, focused ; Gamer’s hands on a keyboard; close-up; Gamer; flashing lights and sounds from the game; cinematic
Characteristic
Shot : A young man wearing headphones, is looking at a computer screen. He seems shocked or surprised by something he sees. He is sitting at a desk and his hands are on a keyboard. The scene is lit by blue and purple lighting.
Aesthetic Score : 0.6
Mood : intense, surprised, focused
Quality
Entropy : 6.68
Noise : 103
Prompt Clip Score : 0.27
AI Evaluation
Likelihood of AI : 0.20
Image errors : There are no obvious artifacts or errors in the image.
Lost in the Shadows: A Moment of Melancholy
A woman stands alone on a deserted sidewalk, bathed in the soft glow of streetlights. Her gaze is fixed on the distance, reflecting a sense of loneliness and introspection. The blurred background emphasizes her isolation, creating a poignant image of melancholy.
Prompt
facial-expressions Worry: lonely, vulnerable ; Woman walking alone at night; long shot; Single Persons; deserted street with streetlights; cinematic
Characteristic
Shot : A young woman is walking on a street at night, with a street lamp illuminating her face. The street is empty and there are buildings in the background.
Aesthetic Score : 0.6
Mood : melancholy, lonely, contemplative
Quality
Entropy : 6.82
Noise : 98
Prompt Clip Score : 0.25
AI Evaluation
Likelihood of AI : 0.10
Image errors : The image is slightly blurry and the colors are a bit muted.
Two Soldiers in a Desolate Landscape: A Moment of Uncertainty
A stark, rocky landscape serves as the backdrop for two soldiers, their expressions reflecting the weight of their situation. One studies a map, while the other sits in the background, both seemingly lost in contemplation. The scene evokes a sense of tension and uncertainty, hinting at the harsh realities of war.
Prompt
facial-expressions Worry: serious, strategic ; Hero looking at a map; medium shot; Heroes; war-torn battlefield with smoke and debris; cinematic
Characteristic
Shot : Two men in military clothing are standing in a post-apocalyptic setting. One is looking at a map and the other is looking at him.
Aesthetic Score : 0.6
Mood : serious, contemplative, desolate
Quality
Entropy : 6.94
Noise : 107
Prompt Clip Score : 0.28
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image is slightly blurry and the colors are a bit muted.
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 0.3, indicating a moderate understanding of the camera position specified in the prompt. This is considered average, as a score between 0.5 and 0.75 is considered good, and above 0.75 is very good.
- Shot Analysis: The model scored 0.45, also indicating a moderate understanding of the scene described in the prompt. This is considered average, as a score between 0.5 and 0.75 is considered good, and above 0.75 is very good.
- Aesthetic Analysis: The model scored 0.2, which is considered very good. This means the generated image’s aesthetic closely matched the expected aesthetic based on the prompt. A score between -0.2 and 0.1 is considered very good.
Overall, the model demonstrates a decent ability to interpret the scene and camera position, but it excels at 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