AI Captures Scenes, But Struggles with Emotions with Imagen-v2
- 10 minutes read - 1935 wordsTable of Contents
In the realm of artificial intelligence, the ability to generate realistic and emotionally evocative images is a coveted goal. This blog post examines the performance of a generative AI model in capturing facial expressions within various scenes. While the model demonstrates proficiency in understanding the scene and camera position, it struggles to accurately portray the intended emotional nuances through facial expressions. This exploration delves into the model’s strengths and weaknesses, highlighting the challenges and opportunities in achieving a more nuanced understanding of human emotions in AI-generated imagery.
Created with: imagen-v2
Lost in the Crowd: A Moment of Melancholy at the Party
A young woman, her face etched with sadness and confusion, stands alone at a bustling party. The blurred background emphasizes her isolation, capturing a moment of introspection and longing.
Prompt
facial-expressions Jealousy: Lonely and envious ; A single woman; eye-level; Single Persons; A crowded party with couples dancing and laughing; cinematic
Characteristic
Shot : A woman with short curly hair stands in a brightly lit room, looking off to the side with a concerned expression. There are other people in the background, blurred and out of focus, suggesting a party or social gathering.
Aesthetic Score : 0.6
Mood : melancholy, pensive, introspective
Quality
Entropy : 6.78
Noise : 78
Prompt Clip Score : 0.27
AI Evaluation
Likelihood of AI : 0.70
Image errors : The image has some slight artifacts in the woman’s hair and skin, particularly around the edges of her face and neck. The lighting also appears to be a bit harsh and uneven, creating a slightly unnatural look.
The Man of Steel, Brooding Over the City
A dramatic image of a superhero, possibly Superman, standing on a rooftop, gazing over a cityscape. The cloudy sky and his contemplative pose create a sense of mystery and heroic brooding.
Prompt
facial-expressions Jealousy: Bitter and isolated ; A superhero standing alone on a rooftop; eye-level; Heroes; A city skyline with a couple holding hands in the distance; cinematic
Characteristic
Shot : A superhero standing on a rooftop, overlooking a city skyline. The scene is set in a dramatic and gritty style.
Aesthetic Score : 0.6
Mood : dark, heroic, mysterious
Quality
Entropy : 6.63
Noise : 102
Prompt Clip Score : 0.24
AI Evaluation
Likelihood of AI : 0.70
Image errors : There are some noticeable artifacts in the image, particularly in the background cityscape.
Lost in the Laughter: A Moment of Solitude in a Bustling Cafe
A solitary figure sits at a cafe table, his gaze lost in the distance, while a lively group enjoys conversation behind him. The scene evokes a sense of melancholy and loneliness, highlighting the contrast between the man’s isolation and the vibrant energy of the surrounding crowd.
Prompt
facial-expressions Jealousy: Heartbroken and resentful ; A man watching his ex-girlfriend laughing with another man; eye-level; Normal People; A bustling cafe with people chatting and enjoying coffee; cinematic
Characteristic
Shot : A man sits at a table in a cafe, looking dejected. There are other people in the cafe, but they are out of focus. The man has a cup of coffee in front of him.
Aesthetic Score : 0.7
Mood : sad, lonely, contemplative
Quality
Entropy : 6.67
Noise : 57
Prompt Clip Score : 0.28
AI Evaluation
Likelihood of AI : 0.30
Image errors : The man’s left arm appears to be a bit too thick. The blur in the background seems somewhat unnatural, particularly around the rightmost figure.
Caught in the Crossfire: A Portrait of Anxiety
A close-up portrait captures the raw emotion of a young man, his face illuminated by contrasting blue and orange lights. The dramatic lighting accentuates his worried expression, creating a sense of intensity and unease. The blurred background adds to the feeling of isolation and the weight of his anxieties.
Prompt
facial-expressions Jealousy: Obsessive and competitive ; A gamer staring intently at his computer screen; eye-level; Gamer; A dimly lit room with posters of video game characters on the walls; cinematic
Characteristic
Shot : A close-up portrait of a young man with a blue light on his face, looking up with an intense expression, possibly in thought or fear. The background is blurred and out of focus, with a hint of warm light in the distance.
Aesthetic Score : 0.6
Mood : intense, contemplative, mysterious
Quality
Entropy : 6.53
Noise : 67
Prompt Clip Score : 0.21
AI Evaluation
Likelihood of AI : 0.60
Image errors : The image appears to be slightly blurry and soft in some areas, particularly around the edges. The skin tones are also slightly unnatural and may have been smoothed or retouched digitally.
A Look of Intrigue: Woman’s Gaze Holds a Mystery
A woman stands in a park, her stern expression and focused gaze drawing the viewer’s attention to something unseen. The blurred figures in the background add to the sense of mystery and intrigue, leaving the viewer wondering what secrets lie beyond the frame.
Prompt
facial-expressions Jealousy: Yearning and wistful ; A woman looking at a couple holding hands in the park; eye-level; Single Persons; A sunny park with children playing and couples strolling; cinematic
Characteristic
Shot : A woman is looking off to the side with a thoughtful expression, she is in an outdoor setting with blurred people in the background.
Aesthetic Score : 0.7
Mood : pensive, mysterious, introspective
Quality
Entropy : 6.87
Noise : 75
Prompt Clip Score : 0.27
AI Evaluation
Likelihood of AI : 0.10
Image errors : The background appears slightly blurry and out of focus, especially the figures in the distance.
Captain America Stands Tall, Ready for Action
A dramatic close-up captures Captain America in a stadium, his gaze locked on the viewer. The intense lighting and heroic pose create a sense of anticipation and power, leaving the audience wondering what challenge lies ahead.
Prompt
facial-expressions Jealousy: Disgruntled and envious ; A hero watching another hero receive accolades; eye-level; Heroes; A crowded stadium with cheering fans and flashing lights; cinematic
Characteristic
Shot : A superhero, most likely Captain America, stands in a stadium with a crowd behind him.
Aesthetic Score : 0.6
Mood : dramatic, powerful, heroic
Quality
Entropy : 6.73
Noise : 56
Prompt Clip Score : 0.20
AI Evaluation
Likelihood of AI : 0.80
Image errors : The image appears to have been generated by AI, with some slight blurriness and lack of detail in the background and skin textures.
A Shadow of Suspense: A Woman’s Worried Glance in a Dimly Lit Room
A captivating image with a strong aesthetic score (0.7) depicts a woman in a red dress and gold necklace, bathed in soft light. Her concerned expression and the mysterious, dimly lit setting create a palpable sense of suspense and drama. The mood is both intriguing and unsettling, leaving the viewer wondering what secrets lie hidden in the shadows.
Prompt
facial-expressions Jealousy: Angry and betrayed ; A man watching his wife dancing with another man at a party; eye-level; Normal People; A brightly lit party with people dancing and laughing; cinematic
Characteristic
Shot : A woman with a worried expression is in a dimly lit room with other people in the background. The lighting is dramatic and there is a strong use of color.
Aesthetic Score : 0.7
Mood : suspenseful, dramatic, mysterious
Quality
Entropy : 6.59
Noise : 51
Prompt Clip Score : 0.24
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image appears to have some slight noise and artifacts.
Lost in the Music: A Portrait of Focus
A close-up portrait captures the intensity of a young man immersed in his music. The dramatic lighting and serious expression convey a sense of deep concentration and emotional engagement.
Prompt
facial-expressions Jealousy: Frustrated and envious ; A gamer watching a livestream of another player achieving a high score; eye-level; Gamer; A dimly lit room with a computer screen displaying the livestream; cinematic
Characteristic
Shot : Close-up portrait of a young man wearing headphones, looking serious and intense. The background is blurred and out of focus.
Aesthetic Score : 0.7
Mood : intense, focused, serious
Quality
Entropy : 6.05
Noise : 85
Prompt Clip Score : 0.27
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image has some minor artifacts and noise, particularly in the background. The lighting is a bit harsh, creating some shadows.
A Mysterious Love: A Tale of Intensity and Romance
In this captivating scene, a couple stands close together, their love palpable amidst a fantastical, slightly blurred background. The man, clad in a dark coat with red accents, and the woman, with her long red hair, create a sense of mystery and intensity. The close-up shot and dramatic background emphasize their emotions, drawing viewers into their intimate world.
Prompt
facial-expressions Jealousy: Melancholy and longing ; looking at a couple kissing in the rain; eye-level; Single Persons; A rainy street with puddles reflecting the city lights; cinematic
Characteristic
Shot : A young man and woman are standing close together, looking at each other. The image is set in a post-apocalyptic or futuristic world.
Aesthetic Score : 0.7
Mood : romantic, dramatic, melancholic
Quality
Entropy : 6.62
Noise : 105
Prompt Clip Score : 0.28
AI Evaluation
Likelihood of AI : 0.80
Image errors : The image has some minor artifacts, particularly in the hair. There are some areas where the image is slightly blurry.
The Eye of the Storm: A Man’s Determined Gaze Amidst Chaos
A close-up shot captures a man in a vibrant red and blue suit, his intense gaze locked on the viewer. The background blurs into a chaotic scene of figures and fire, hinting at a moment of conflict or crisis. The image evokes a sense of urgency and tension, leaving the viewer questioning the man’s role in the unfolding drama.
Prompt
facial-expressions Jealousy: Frustrated and envious ; A hero watching another hero save the day; eye-level; Heroes; A chaotic scene with explosions and people running for safety; cinematic
Characteristic
Shot : A close-up shot of a man’s face in a superhero costume, with a blurred background of a crowd and explosions. He has a determined expression on his face, and his eyes are wide open.
Aesthetic Score : 0.7
Mood : intense, determined, dramatic
Quality
Entropy : 6.77
Noise : 66
Prompt Clip Score : 0.25
AI Evaluation
Likelihood of AI : 0.90
Image errors : The background appears somewhat blurry, and the overall image feels a bit over-saturated.
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 0.38, which is below the “good” range of 0.5 to 0.75. This suggests the model didn’t fully capture the intended camera position described in the prompt.
- Shot Analysis: The model scored 0.77, which falls within the “good” range. This indicates the model successfully understood the scene described in the prompt and created an image that reflects it.
- Aesthetic Analysis: The model scored 0.09, which is significantly higher than the “very good” range of -0.2 to 0.1. This means 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://deepmind.google/technologies/imagen-2/