AI's Facial Expressions: A Step Forward, But Still Room for Growth with Imagen-v2
- 9 minutes read - 1723 wordsTable of Contents
Facial expressions are a powerful tool in storytelling, conveying emotions and adding depth to characters. In the realm of AI-generated imagery, capturing these expressions accurately is crucial for creating compelling and engaging visuals. This analysis explores the capabilities of a generative AI model in understanding and depicting facial expressions within various scenes, highlighting its strengths and areas for improvement.
Created with: imagen-v2
Lost in Thought: A Portrait of Melancholy
A close-up portrait captures a woman’s pensive gaze, her green eyes reflecting a world of unspoken emotions. The shallow depth of field draws the viewer into her intimate world, while the muted colors and blurred city lights create a sense of melancholy and mystery.
Prompt
facial-expressions Daydreaming: Melancholy, lost in thought ; A lone figure; eye-level; Single Person; bustling city street; cinematic
Characteristic
Shot : A woman with brown hair is looking up in the middle of a blurry city background, she is wearing a brown jacket and a beige scarf.
Aesthetic Score : 0.7
Mood : thoughtful, pensive, mysterious
Quality
Entropy : 6.68
Noise : 46
Prompt Clip Score : 0.22
AI Evaluation
Likelihood of AI : 0.90
Image errors : There is some slight blurring in the background, and the subject’s skin appears a bit unnatural.
Superman at Dusk: A City Awaits
A dramatic silhouette of Superman, bathed in the golden hues of dusk, gazes out over a sprawling cityscape. The scene evokes a sense of heroic hope and anticipation, promising a story of courage and triumph.
Prompt
facial-expressions Daydreaming: Confident, determined ; A superhero standing on a rooftop; high angle; Hero; cityscape at night; cinematic
Characteristic
Shot : Superman looking out over a city at night, perhaps from a rooftop, with a blurry cityscape in the background.
Aesthetic Score : 0.7
Mood : heroic, contemplative, powerful
Quality
Entropy : 6.47
Noise : 51
Prompt Clip Score : 0.22
AI Evaluation
Likelihood of AI : 0.90
Image errors : The image appears to have some slight blurring, particularly in the background, which might be a result of the rendering process or post-processing.
Lost in Thought: A Moment of Quiet Contemplation
A woman finds solace in a warm cafe, her thoughtful gaze and the soft lighting creating a sense of introspection and quiet contemplation. The scene evokes a mood of pensive relaxation, capturing a moment of quiet reflection.
Prompt
facial-expressions Daydreaming: Peaceful, content ; A woman sipping coffee in a cafe; eye-level; Normal People; warm, inviting cafe interior; cinematic
Characteristic
Shot : A young woman is sitting in a cafe, sipping from a cup of coffee. The background is blurred, and she is looking off to the side.
Aesthetic Score : 0.8
Mood : pensive, warm, relaxed
Quality
Entropy : 6.78
Noise : 53
Prompt Clip Score : 0.26
AI Evaluation
Likelihood of AI : 0.70
Image errors : The image has no significant errors, except for some minor blurring and a slight oversaturation.
Lost in the Neon Glow: A Portrait of Mystery
A young man, bathed in vibrant, futuristic lighting, stares intently into the distance. His headphones amplify the intensity of the moment, creating a sense of intrigue and mystery. The dramatic lighting highlights his features, drawing the viewer into his world.
Prompt
facial-expressions Daydreaming: Engrossed, excited ; A gamer intensely focused on a screen; close-up; Gamer; dimly lit room with gaming peripherals; cinematic
Characteristic
Shot : A young man wearing headphones is illuminated by blue and red light, possibly a gamer or musician, he is looking up as if in thought or concentration.
Aesthetic Score : 0.7
Mood : intense, focused, mysterious
Quality
Entropy : 6.08
Noise : 64
Prompt Clip Score : 0.26
AI Evaluation
Likelihood of AI : 0.80
Image errors : The image suffers from some oversharpening, which gives the skin a slightly artificial texture, the hair also suffers from this same issue. There is a noticeable blurring of the background that doesn’t have enough depth.
Silhouettes of Solitude: A Sunset Story
A woman sits by a window, her silhouette a stark contrast against the fiery hues of a setting sun. The city skyline stretches out behind her, a backdrop to her contemplative mood. This image evokes a sense of melancholy and longing, capturing the quiet beauty of a solitary moment.
Prompt
facial-expressions Daydreaming: Curious, imaginative ; A lone figure gazing out from a high-rise window, overlooking a bustling city street below, bathed in the warm glow of the setting sun.; cinematic
Characteristic
Shot : A woman is looking out of a window at a cityscape during sunset. The sun is setting behind the cityscape, casting a warm glow on the scene.
Aesthetic Score : 0.7
Mood : melancholy, contemplative, peaceful
Quality
Entropy : 6.36
Noise : 91
Prompt Clip Score : 0.30
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image has some minor artifacts, such as the slight blurriness of the cityscape in the background.
A Knight’s Pensive Gaze in the Mysterious Forest
A lone knight, clad in armor, gazes upwards into the dense canopy of a forest. The dramatic lighting and his pensive expression create a sense of mystery and anticipation, leaving the viewer wondering what secrets lie ahead.
Prompt
facial-expressions Daydreaming: Brave, adventurous ; A knight in shining armor riding through a forest; wide shot; Hero; mystical forest with dappled sunlight; cinematic
Characteristic
Shot : A young man in knight armor looks up into the forest. He appears pensive.
Aesthetic Score : 0.7
Mood : dramatic, mysterious, thoughtful
Quality
Entropy : 6.77
Noise : 65
Prompt Clip Score : 0.27
AI Evaluation
Likelihood of AI : 0.30
Image errors : The background appears slightly blurred and out of focus. There is a slight halo effect around the subject’s head, which may be due to over-processing.
Golden Hour Laughter: Friends Embrace the Sunset’s Warmth
Three friends bask in the golden glow of a setting sun, their laughter echoing the joy of a carefree moment. The warm light paints the scene with nostalgia, capturing the essence of youthful happiness.
Prompt
facial-expressions Daydreaming: Joyful, carefree ; A group of friends laughing together at a picnic; eye-level; Normal People; sunny park with picnic blanket; cinematic
Characteristic
Shot : Three friends laughing and looking up at the sky, likely at sunset, while lying on a blanket in a park.
Aesthetic Score : 0.7
Mood : joyful, carefree, warm
Quality
Entropy : 6.63
Noise : 87
Prompt Clip Score : 0.27
AI Evaluation
Likelihood of AI : 0.10
Image errors : No visible errors.
Neon Dreams: A Moment of Hope and Serenity
A young woman, bathed in vibrant pink and blue neon lights, gazes upwards with a soft smile. The futuristic glow creates a dreamy and hopeful atmosphere, capturing a moment of peaceful reflection.
Prompt
facial-expressions Daydreaming: Thrilled, competitive ; A gamer’s hands rapidly moving across a keyboard; close-up; Gamer; brightly lit gaming setup with glowing screen; cinematic
Characteristic
Shot : A young woman with red hair is wearing headphones and looking off to the side in a dimly lit room with purple and blue neon lights.
Aesthetic Score : 0.7
Mood : dreamy, relaxed, contemplative
Quality
Entropy : 6.33
Noise : 68
Prompt Clip Score : 0.28
AI Evaluation
Likelihood of AI : 0.10
Image errors : The image is slightly blurry and the lighting is uneven. There are some artifacts in the background.
Lost in the Waves: A Moment of Melancholy by the Sea
A solitary figure stands on a windswept beach, her gaze lost in the turbulent ocean. The cloudy sky and choppy water mirror the introspective mood, while the dramatic lighting emphasizes a sense of isolation and longing. This evocative image captures a moment of quiet contemplation, inviting viewers to share in the woman’s unspoken emotions.
Prompt
facial-expressions Daydreaming: Reflective, introspective ; A woman walking alone on a beach; eye-level; Single Person; vast, empty beach with crashing waves; cinematic
Characteristic
Shot : A woman stands on a beach, her back to the camera, looking out at the ocean. The sky is overcast and the beach is empty.
Aesthetic Score : 0.7
Mood : melancholy, contemplative, introspective
Quality
Entropy : 6.88
Noise : 119
Prompt Clip Score : 0.22
AI Evaluation
Likelihood of AI : 0.10
Image errors : Some slight graininess in the sky. The lighting is a bit uneven. The color balance is slightly off, making the image look a bit cold.
A Hero’s Gaze: Superman Contemplates the City
A close-up portrait captures the determined gaze of a middle-aged Superman, his eyes fixed on the cloudy sky above a blurry cityscape. The image evokes a sense of power, responsibility, and the weight of heroism.
Prompt
facial-expressions Daydreaming: Empowered, triumphant ; A superhero soaring through the sky; high angle; Hero; dramatic cloudscape with city skyline in the distance; cinematic
Characteristic
Shot : A close-up portrait of a man looking up, presumably Superman, with a city skyline in the background.
Aesthetic Score : 0.7
Mood : serious, hopeful, determined
Quality
Entropy : 6.59
Noise : 52
Prompt Clip Score : 0.25
AI Evaluation
Likelihood of AI : 0.80
Image errors : The image has some visible artifacts, particularly in the hair and the background. The lighting appears overly saturated and unnatural.
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 0.33, which is below average. This suggests that the model didn’t accurately capture the intended camera position described in the prompt.
- Shot Analysis: The model scored 0.62, which is considered good. This indicates that the model was able to understand the scene and create a shot that was relatively close to what was described in the prompt.
- Aesthetic Analysis: The model scored 0.12, which is considered very good. This means that the generated image’s aesthetic was very close to the expected aesthetic described in the prompt.
Overall: While the model performed well in understanding the scene and achieving the desired aesthetic, it struggled with accurately capturing the intended 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://deepmind.google/technologies/imagen-2/