AI's Facial Expressions: A Mixed Bag of Success with Dall-e-3
- 9 minutes read - 1867 wordsTable of Contents
Facial expressions are a powerful tool for conveying emotions and intentions in visual storytelling. 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 angles, shot composition, and aesthetic quality. We’ll examine examples where the model excels in capturing dramatic facial expressions, highlighting its potential for creating compelling visual narratives.
Created with: dall-e-3
Lost in Thought: A Moment of Melancholy in the City
A young woman, shrouded in a gray sweater, sits alone at a cafe table, her gaze lost in the distance. The bustling city life outside blurs into the background, mirroring the quiet contemplation in her eyes. The scene evokes a sense of loneliness and introspection, capturing a fleeting moment of melancholy in the urban landscape.
Prompt
facial-expressions Daydreaming: Melancholy, lost in thought ; A lone figure; eye-level; Single Person; bustling city street; cinematic
Characteristic
Shot : A woman is sitting at a table outside, with a city street behind her. The camera is looking at her from a low angle.
Aesthetic Score : 0.7
Mood : mysterious, pensive, urban
Quality
Entropy : 6.72
Noise : 89
Prompt Clip Score : 0.17
AI Evaluation
Likelihood of AI : 0.10
Image errors : Some minor artifacts and blurriness in the background, particularly around the car and the camera.
A Hero Stands Watch Over the City
A powerful superhero, cloaked in darkness and hope, surveys the twinkling cityscape. The dramatic scene evokes a sense of awe and wonder, highlighting the hero’s strength and the promise of a brighter future.
Prompt
facial-expressions Daydreaming: Confident, determined ; A superhero standing on a rooftop; high angle; Hero; cityscape at night; cinematic
Characteristic
Shot : A superhero stands on a rooftop overlooking a cityscape at night. The city lights shimmer in the distance, and the sky is filled with stars.
Aesthetic Score : 0.7
Mood : dramatic, heroic, hopeful
Quality
Entropy : 6.31
Noise : 110
Prompt Clip Score : 0.24
AI Evaluation
Likelihood of AI : 0.90
Image errors : The superhero’s costume appears a bit blurry and lacks sharpness. The city skyline in the background appears somewhat artificial, like a painted backdrop, lacking depth.
Lost in Thought: A Moment of Tranquility in a Cozy Cafe
A young woman finds peace amidst the gentle hum of a dimly lit cafe. With a warm cup of coffee in hand and her eyes closed, she appears lost in contemplation, her thoughts taking flight in a whimsical thought bubble. The scene evokes a sense of relaxation, dreaminess, and quiet introspection.
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 at a table in a cafe, enjoying a cup of coffee. She has her eyes closed and is smiling, as if lost in thought. There’s a thought bubble above her head.
Aesthetic Score : 0.7
Mood : relaxed, contemplative, dreamy
Quality
Entropy : 6.77
Noise : 81
Prompt Clip Score : 0.30
AI Evaluation
Likelihood of AI : 0.20
Image errors : There are no visible artifacts or errors in the image.
Lost in the Game: A Moment of Focused Intensity
A young woman, bathed in the glow of her screen, is completely absorbed in her video game. The dramatic lighting highlights her determined expression as she navigates the virtual world with focus and energy.
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 woman is playing a video game in a dimly lit room. She is wearing a headset and a sweater. The room is dark, but there is a soft glow from the computer screen and the lights in the room.
Aesthetic Score : 0.7
Mood : focused, determined, confident
Quality
Entropy : 6.21
Noise : 77
Prompt Clip Score : 0.25
AI Evaluation
Likelihood of AI : 0.20
Image errors : Slight blurriness around the edges of the image. No other major artifacts or errors
A Window to Wonder: A Boy’s Dream of Adventure
This whimsical scene captures a young boy gazing out a window at a lush jungle teeming with life. A hidden civilization beckons from the distance, while a vibrant red bird perches in the foreground, adding a touch of magic. The image evokes a sense of wonder and mystery, inviting you to imagine the adventures that await beyond the window.
Prompt
facial-expressions Daydreaming: Curious, imaginative ; A child staring out a window; eye-level; Single Person; lush green garden; cinematic
Characteristic
Shot : A young boy is looking out of a window at a lush, green jungle. The jungle is full of plants, animals, and a path leading into the distance. The scene has a whimsical and fantastical feel.
Aesthetic Score : 0.7
Mood : whimsical, fantastical, hopeful
Quality
Entropy : 6.72
Noise : 113
Prompt Clip Score : 0.28
AI Evaluation
Likelihood of AI : 0.80
Image errors : There are some minor artifacts in the image, particularly around the edges of the window frame.
A Knight’s Journey Through the Ethereal Portal
A silver-armored knight rides a white steed into a swirling, mystical portal. The scene is framed by a dark blue circular border, creating a sense of depth and movement. The knight’s determined expression and the ethereal mists evoke a dreamlike, adventurous mood, leaving you wondering what awaits on the other side.
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 knight on horseback rides through a swirling, dreamy portal, emerging from a woodland scene into a starlit sky. A face emerges from the trees, suggesting a connection between the knight and the otherworldly realm.
Aesthetic Score : 0.7
Mood : mystical, ethereal, adventurous
Quality
Entropy : 6.78
Noise : 97
Prompt Clip Score : 0.25
AI Evaluation
Likelihood of AI : 0.80
Image errors : The knight’s armor appears somewhat blurry and lacking in detail. The face in the trees is partially obscured and lacking in definition.
Sun-Kissed Laughter: Friends Share Joy at a Park Picnic
A group of friends bask in the warm sunlight, their laughter echoing through the park as they enjoy a carefree picnic. The scene radiates joy and playfulness, capturing the essence of a perfect summer day.
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 : A group of friends laughing together on a picnic blanket in a park during a sunny day.
Aesthetic Score : 0.7
Mood : joyful, carefree, happy
Quality
Entropy : 6.66
Noise : 100
Prompt Clip Score : 0.28
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image has some slight artifacts in the background, especially around the trees.
The Face of Immersion: One Man, Two Worlds
A split-screen image captures the raw emotion of gaming. On one side, calm focus. On the other, explosive excitement. This powerful visual embodies the transformative nature of intense gameplay.
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 gamer is playing a video game, the image is split in two to show the player’s two emotional states: calm and focused, and intense and passionate, the player’s emotions are projected on the game screen in the background.
Aesthetic Score : 0.6
Mood : intense, passionate, focused
Quality
Entropy : 6.61
Noise : 102
Prompt Clip Score : 0.29
AI Evaluation
Likelihood of AI : 0.70
Image errors : The image has some artifacts, particularly around the edges of the split-screen and the game screen in the background. There is also some noise in the image, especially in the darker areas.
Lost in Thought by the Sea
A young woman with long black hair gazes into the distance, her contemplative expression mirrored in the blurred backdrop of the ocean and sand. The soft focus draws the viewer’s attention to her solitary figure, capturing a moment of quiet melancholy and serene reflection.
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 young woman with long black hair looks out over a wide beach with a stormy ocean in the background.
Aesthetic Score : 0.8
Mood : melancholy, contemplative, peaceful
Quality
Entropy : 6.23
Noise : 88
Prompt Clip Score : 0.24
AI Evaluation
Likelihood of AI : 0.80
Image errors : The background appears somewhat blurry and a bit too simplistic, like a painted backdrop.
Soaring Towards Hope: A Superhero’s Journey Begins
This image captures the essence of hope and empowerment as a superhero takes flight, her cape billowing in the dramatic sky. The strong lighting and hopeful expression create a sense of awe and wonder, hinting at an adventurous journey ahead.
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 woman dressed as a superhero flies in the sky above a city. A cloud in the shape of a thought bubble floats above her.
Aesthetic Score : 0.6
Mood : empowered, hopeful, whimsical
Quality
Entropy : 6.89
Noise : 103
Prompt Clip Score : 0.26
AI Evaluation
Likelihood of AI : 0.80
Image errors : The clouds look somewhat artificial, particularly the one in the shape of a thought bubble. The city below is also somewhat blurry and lacking detail.
Conclusion
The results of the analysis show that the generative AI model performed well in terms of understanding the scene and camera position, but struggled with the aesthetic aspect. Here’s a breakdown:
- Camera Position: The model scored 0.25, 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 0.545, 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 0.12, which is considered very good. This means that the generated image’s aesthetic closely matched the expected aesthetic described in the prompt.
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, indicating the model’s ability to create visually appealing results.
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://openai.com/index/dall-e-3/