AI's Facial Expressions: A Mixed Bag of Success with Freepik

Facial expressions are a powerful tool for conveying emotions and intentions in visual storytelling. In the realm of generative AI, the ability to create images with specific facial expressions is a crucial aspect of achieving realistic and engaging visuals. This blog post delves into the performance of a generative AI model in capturing facial expressions, camera position, and scene aesthetics. We analyze the model’s strengths and weaknesses based on various prompts and discuss the implications for future development.

Created with: freepik

Autumn Melancholy: A Moment of Contemplation

A young woman finds solace amidst the fallen leaves of autumn, bathed in the soft glow of streetlights. The composition evokes a sense of isolation and contemplation, capturing a moment of quiet reflection in the serene beauty of the park.

Prompt

facial-expressions Sadness: Melancholy, loneliness ; A lone figure; eye-level; Single Person; Empty park bench with fallen leaves; cinematic

Characteristic

Shot : A young woman sits on a bench in a park with fall foliage in the background.

Aesthetic Score : 0.7

Mood : melancholy, contemplative, autumnal

Quality

Entropy : 6.85

Noise : 67

Prompt Clip Score : 0.28

AI Evaluation

Likelihood of AI : 0.20

Image errors : The image is slightly blurry.

The Dark Knight Broods in the Rain

Affiliate Links

Stable Diffusion with Python

Master Stable Diffusion for AI image generation using Python. Control and customize your creations.

Stable Diffusion Web UI on AWS

Deploy Stable Diffusion Web UI on AWS with this comprehensive guide.

Mastering Midjourney: AI Art Guide

Unlock Midjourney V6 features and create exceptional AI art.

A brooding figure, likely Batman, stands amidst a downpour, his gaze fixed on the city below. The rain and dark lighting create a sense of mystery and suspense, hinting at the secrets hidden within the shadows.

Prompt

facial-expressions Sadness: Despair, disillusionment ; A superhero in their costume; eye-level; Hero; City skyline at night, rain falling; cinematic

Characteristic

Shot : A figure dressed as Batman, standing in the rain in front of a cityscape with blurred lights in the background.

Aesthetic Score : 0.7

Mood : dark, brooding, mysterious

Quality

Entropy : 6.71

Noise : 56

Prompt Clip Score : 0.27

AI Evaluation

Likelihood of AI : 0.80

Image errors : The image has some minor artifacts, particularly around the figure’s edges. The rain effect appears somewhat artificial.

A Moment of Quiet Desperation

A woman sits alone at a kitchen table, her face buried in her hands, a cup of coffee untouched before her. The image captures a sense of melancholy and isolation, highlighting the weight of her unspoken emotions.

Prompt

facial-expressions Sadness: Hopelessness, grief ; A woman sitting at a kitchen table; eye-level; Normal People; Empty coffee cup, unwashed dishes; cinematic

Characteristic

Shot : A woman is sitting at a kitchen table, looking down with a sad expression. There is a cup of coffee in front of her and a to-go cup behind her.

Aesthetic Score : 0.6

Mood : sad, contemplative, lonely

Quality

Entropy : 6.81

Noise : 47

Prompt Clip Score : 0.27

AI Evaluation

Likelihood of AI : 0.20

Image errors : There are no visible artifacts or errors in the image.

Lost in a Sea of Boxes: A Portrait of Discontent

A young man sits amidst a chaotic landscape of boxes and canned goods, his posture and expression conveying a palpable sense of weariness and disappointment. The cluttered surroundings amplify the feeling of being overwhelmed, leaving the viewer to ponder the weight of his circumstances.

Prompt

facial-expressions Sadness: Isolation, withdrawal ; A gamer hunched over their computer; close-up; Gamer; Empty pizza boxes, energy drink cans; cinematic

Characteristic

Shot : A young man is sitting among cardboard boxes. He looks bored and tired. There are also some cans of drinks on the floor.

Aesthetic Score : 0.4

Mood : melancholy, bored, frustrated

Quality

Entropy : 6.75

Noise : 49

Prompt Clip Score : 0.19

AI Evaluation

Likelihood of AI : 0.10

Image errors : The image has a slight blur in some areas, most likely caused by camera shake or lack of focus.

Lost in the Shadows: A Moment of Melancholy

A young girl stands alone in a dimly lit hallway, her gaze fixed on the camera with a hint of sadness. The soft lighting and narrow space create a sense of isolation and loneliness, leaving the viewer to ponder her unspoken emotions.

Prompt

facial-expressions Sadness: Loneliness, abandonment ; A child standing in a doorway; eye-level; Single Person; Empty hallway, dim lighting; cinematic

Characteristic

Shot : A young girl stands alone in a hallway, looking at the camera.

Aesthetic Score : 0.6

Mood : melancholy, lonely, introspective

Quality

Entropy : 6.52

Noise : 37

Prompt Clip Score : 0.19

AI Evaluation

Likelihood of AI : 0.20

Image errors : There are no noticeable artifacts or errors in the image.

A Soldier’s Vigil in the Aftermath of War

A lone soldier, clad in combat gear, kneels amidst a landscape ravaged by conflict. Smoke and fire engulf the scene, creating a stark and somber atmosphere. The soldier’s intense gaze into the distance reflects the gravity of the situation and the uncertainty that lies ahead.

Prompt

facial-expressions Sadness: Loss, regret ; A soldier kneeling on a battlefield; eye-level; Hero; Explosions in the distance, smoke filling the air; cinematic

Characteristic

Shot : A soldier in full gear is kneeling in a war zone, amidst burning debris and smoke. The soldier is looking intently at something off-screen, possibly a threat or a target.

Aesthetic Score : 0.7

Mood : intense, dramatic, somber

Quality

Entropy : 6.86

Noise : 62

Prompt Clip Score : 0.28

AI Evaluation

Likelihood of AI : 0.20

Image errors : The fire is slightly blurry in the background and the overall composition could be improved.

Popcorn and Tension: A Couple’s Silent Struggle

A tense atmosphere hangs heavy in the air as a couple sits on a couch, their silence punctuated by the scattered remnants of a spilled bowl of popcorn. The woman’s worried expression and the man’s crossed arms speak volumes about the unspoken conflict brewing between them.

Prompt

facial-expressions Sadness: Silence, unspoken tension ; A couple sitting on a couch; eye-level; Normal People; Empty popcorn bowl, remote control on the floor; cinematic

Characteristic

Shot : A young couple sits on a couch, looking away from each other. There is a large bowl of popcorn in the foreground, which is spilling onto the floor. The scene appears to be a staged photography set-up.

Aesthetic Score : 0.4

Mood : awkward, tense, uncomfortable

Quality

Entropy : 6.92

Noise : 57

Prompt Clip Score : 0.28

AI Evaluation

Likelihood of AI : 0.30

Image errors : The image appears to be slightly out of focus and the lighting is a bit uneven.

The Last Keystroke: A Moment of Frustration

A close-up shot captures the tense focus of a hand furiously typing on a keyboard. The blurred game over screen in the background hints at a frustrating defeat, leaving the viewer to wonder what the outcome will be.

Prompt

facial-expressions Sadness: Frustration, defeat ; A gamer’s hands on a keyboard; close-up; Gamer; Screen displaying a game over message; cinematic

Characteristic

Shot : A hand is typing on a keyboard in front of a computer monitor. The monitor is displaying a game-over screen.

Aesthetic Score : 0.5

Mood : intense, focused, determined

Quality

Entropy : 6.78

Noise : 48

Prompt Clip Score : 0.21

AI Evaluation

Likelihood of AI : 0.20

Image errors : The image has some slight noise and compression artifacts, especially in the background.

Lost in the City’s Embrace

A young woman with short brown hair navigates the bustling city streets at dusk, her gaze fixed on the camera with a hint of melancholy. The soft, warm lighting casts a mysterious glow, highlighting her introspective mood amidst the urban backdrop.

Prompt

facial-expressions Sadness: Alienation, loneliness ; A woman walking down a crowded street; eye-level; Single Person; People passing by, oblivious to her; cinematic

Characteristic

Shot : A young woman with short brown hair is standing in a crowded street, looking directly at the camera. She is wearing a green jacket and a grey shirt. The background is blurred, showing an urban environment with lights and people.

Aesthetic Score : 0.7

Mood : melancholy, pensive, isolated

Quality

Entropy : 6.83

Noise : 55

Prompt Clip Score : 0.25

AI Evaluation

Likelihood of AI : 0.20

Image errors : The image has some noise in the background.

Lost in the City Lights: A Moment of Melancholy

A young man, shrouded in shadow, stands on a rooftop, his gaze lost in the distant city lights. The image evokes a sense of melancholy and introspection, capturing a moment of quiet contemplation against the backdrop of a bustling urban landscape.

Prompt

facial-expressions Sadness: Reflection, introspection ; A hero standing on a rooftop; eye-level; Hero; City lights twinkling in the distance; cinematic

Characteristic

Shot : A young man stands on a rooftop overlooking a city at night. He is looking out at the city lights, which are blurred in the background.

Aesthetic Score : 0.7

Mood : pensive, melancholic, introspective

Quality

Entropy : 6.69

Noise : 43

Prompt Clip Score : 0.26

AI Evaluation

Likelihood of AI : 0.20

Image errors : The image is slightly overexposed, and the city lights are not very sharp.

Conclusion

The results show that the generative AI model performed well in understanding the camera position and scene, but struggled with the aesthetic aspect.

Here’s a breakdown:

• Camera Position: The model scored 0.1, 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 0.455, which is slightly below average. A score between 0.5 and 0.75 would be considered good, and above 0.75 very good. This suggests the model had some difficulty understanding the scene described in the prompt.
• Aesthetic Analysis: The model scored 0.19, which is very good. A score between -0.2 and 0.1 indicates a close match between the expected and actual aesthetic of the image. This suggests the model was able to create an image that visually aligned with the desired aesthetic.

Overall, the model seems to be better at capturing the desired aesthetic than understanding the camera position and scene. This suggests that the model might be more sensitive to visual cues than textual descriptions.