AI's Disgust: A Look at Facial Expressions in Generative Art with Stability-ai-ultra
- 10 minutes read - 1973 wordsTable of Contents
Facial expressions are a powerful tool for conveying emotions in art. In the realm of generative AI, the ability to create realistic and nuanced facial expressions is a key indicator of progress. This blog post examines the results of a generative AI model tasked with depicting disgust, exploring its strengths and weaknesses in capturing the nuances of this complex emotion. We’ll delve into the model’s performance in understanding scene descriptions, camera position, and aesthetics, providing insights into the current state of AI-generated facial expressions.
Created with: stability-ai-ultra
Lost in the Shadows: A Glimpse of Urban Decay
A solitary figure sits amidst the grime and graffiti of a dark alleyway, bathed in soft light that amplifies the sense of isolation and vulnerability. The scene evokes a somber mood, capturing the gritty reality of urban decay.
Prompt
facial-expressions Disgust: Despair and alienation ; A lone figure, hunched over in a dimly lit alleyway; eye-level; Single Person; overflowing trash bins and graffiti-covered walls; cinematic
Characteristic
Shot : A person in a hooded jacket is crouched down in a dark alleyway, surrounded by garbage and graffiti-covered walls. The alley is dimly lit and the person’s face is obscured by their hood.
Aesthetic Score : 0.4
Mood : desolate, lonely, somber
Quality
Entropy : 6.75
Noise : 100
Prompt Clip Score : 0.28
AI Evaluation
Likelihood of AI : 0.30
Image errors : The image has a slight blur, likely caused by camera shake.
Blood and Fury: Comic Panel Captures the Intensity of a Violent Confrontation
This comic book panel explodes with raw energy, showcasing a brutal fight with screaming characters and blood splattered across the page. The use of contrasting colors and exaggerated expressions creates a dramatic and visceral impact, emphasizing the intensity of the action.
Prompt
facial-expressions Disgust: Horror and disgust ; A superhero, their face contorted in revulsion, as they witness a horrific crime; eye-level; Hero; a chaotic crime scene with blood and debris; cinematic
Characteristic
Shot : A comic book style scene with a focus on the face of a person in distress. The background is a dark alleyway with blood splattered on the walls and there is a violent explosion.
Aesthetic Score : 0.6
Mood : intense, chaotic, violent
Quality
Entropy : 5.43
Noise : 73
Prompt Clip Score : 0.22
AI Evaluation
Likelihood of AI : 0.30
Image errors : The lines are a bit jagged in some parts, and the coloring feels slightly uneven.
A Plateful of Mystery: What’s Troubling This Woman?
A close-up shot reveals a woman in a kitchen, her face etched with concern. A plate of food sits in the foreground, adding an air of mystery to the scene. The mood is suspenseful, leaving viewers wondering what secrets lie beneath the surface.
Prompt
facial-expressions Disgust: Disappointment and disgust ; A young woman, her face pale and wrinkled, as she stares at a plate of spoiled food; eye-level; Normal Person; a cluttered kitchen with dirty dishes and a overflowing trash can; cinematic
Characteristic
Shot : A woman in a kitchen looking directly at the camera, with a plate of food in the foreground and a pot out of focus in the background.
Aesthetic Score : 0.5
Mood : unsettling, intense, suspicious
Quality
Entropy : 6.91
Noise : 83
Prompt Clip Score : 0.30
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image is slightly blurry, especially in the background.
Lost in the Game: Immersive VR Experience Captures the Thrill of the Hunt
A young man is completely absorbed in a virtual reality game, his face illuminated by the colorful lights of his gaming setup. The intensity of the moment is palpable as he faces off against a monstrous opponent on the screen, creating a sense of excitement and suspense.
Prompt
facial-expressions Disgust: Unease and disgust ; A gamer, their eyes wide with disgust, as they witness a grotesque scene in a virtual reality game; eye-level; Gamer; a brightly lit gaming room with multiple monitors and controllers; cinematic
Characteristic
Shot : A person wearing a VR headset is playing a game with a demonic creature on the screen in front of them.
Aesthetic Score : 0.6
Mood : intense, suspenseful, futuristic
Quality
Entropy : 6.96
Noise : 84
Prompt Clip Score : 0.27
AI Evaluation
Likelihood of AI : 0.10
Image errors : There are some minor artifacts in the image, particularly around the edges of the screens.
Man Navigates a Sea of Trash in Gloomy Alley
A solitary figure walks through a narrow alleyway choked with overflowing trash cans and scattered garbage. The image captures a stark contrast between the clean-cut man and the desolate, filthy environment, creating a dramatic and gloomy atmosphere.
Prompt
facial-expressions Disgust: Repulsion and disgust ; A man, his face contorted in disgust, as he walks past a pile of rotting garbage; eye-level; Single Person; a dirty and neglected street with overflowing trash cans; cinematic
Characteristic
Shot : A narrow alleyway cluttered with garbage and overflowing trash bins. A man in a dark jacket walks through the mess.
Aesthetic Score : 0.2
Mood : gloomy, chaotic, depressing
Quality
Entropy : 6.98
Noise : 97
Prompt Clip Score : 0.28
AI Evaluation
Likelihood of AI : 0.10
Image errors : The image suffers from a lack of clarity and sharpness, particularly in the lower portion. The lighting is uneven and contributes to the overall gloominess.
Batman and Superman: A Confrontation in the Shadows
A tense standoff between Batman and Superman, with blood staining Superman’s face, hints at a violent clash. The close-up shot and ominous city lights amplify the dramatic tension of this confrontation.
Prompt
facial-expressions Disgust: Anger and disgust ; A superhero, their face etched with disgust, as they confront a villain who has committed a heinous act; eye-level; Hero; a dark and smoky cityscape with a towering villainous figure; cinematic
Characteristic
Shot : A close-up shot of Batman and Superman facing each other. They are both in their superhero costumes, and Superman appears to be injured.
Aesthetic Score : 0.6
Mood : intense, dramatic, conflict
Quality
Entropy : 6.42
Noise : 96
Prompt Clip Score : 0.25
AI Evaluation
Likelihood of AI : 0.80
Image errors : The image appears to be slightly over-saturated, and the lighting is uneven. The background is blurred, and the overall composition is somewhat static.
Chaos in the Kitchen: Rat Triggers Terrified Reactions
A chaotic kitchen scene unfolds with three young girls reacting in fear to a rat in the foreground. The messiness and the girls’ expressions create a sense of shock and disgust, capturing a moment of unexpected chaos.
Prompt
facial-expressions Disgust: Horror and disgust ; A family, their faces twisted in disgust, as they discover a dead rat in their kitchen; eye-level; Normal People; a cluttered and messy kitchen with dirty dishes and a overflowing trash can; cinematic
Characteristic
Shot : The image depicts a messy kitchen with three young girls reacting in horror to a rat crawling on the floor. The scene is chaotic with shattered glass, overflowing trash, and a general sense of disarray.
Aesthetic Score : 0.6
Mood : horror, chaos, surprise
Quality
Entropy : 6.92
Noise : 77
Prompt Clip Score : 0.30
AI Evaluation
Likelihood of AI : 0.80
Image errors : The image has some slight artifacts, particularly around the edges of the objects. The colors are a bit saturated and the overall style is slightly cartoonish.
Fear in the Blue Light: A Tense Gaming Session Takes a Dark Turn
Three friends huddle around a computer screen, their faces illuminated by the eerie blue glow. A sense of dread hangs in the air as they stare at the monitor, their expressions filled with fear. The dimly lit room, punctuated by flashes of red light, adds to the suspenseful atmosphere. What terrifying game are they playing, and what secrets lie hidden in the shadows?
Prompt
facial-expressions Disgust: Fear and disgust ; A gamer, their face pale and sweaty, as they witness a disturbing scene in a horror game; eye-level; Gamer; a dimly lit gaming room with a flickering monitor and a dark, ominous atmosphere; cinematic
Characteristic
Shot : The scene depicts a group of people watching a horror movie on a computer screen in a dimly lit room.
Aesthetic Score : 0.4
Mood : suspense, horror, anticipation
Quality
Entropy : 6.34
Noise : 72
Prompt Clip Score : 0.31
AI Evaluation
Likelihood of AI : 0.30
Image errors : There are some slight artifacts in the background and on the computer screen, indicating potential compression or editing issues.
Cockroach Surprise: Woman’s Shocked Reaction Goes Viral
A woman’s face contorts in disgust as she discovers a cockroach on her plate of food. The close-up shot captures her shock and the scene’s comedic absurdity, making for a viral moment.
Prompt
facial-expressions Disgust: Revulsion and disgust ; A woman, her face contorted in disgust, as she discovers a cockroach in her food; eye-level; Single Person; a brightly lit restaurant with a table full of food and a cockroach crawling on a plate; cinematic
Characteristic
Shot : A woman is sitting at a table in a restaurant. She is looking at a cockroach on her plate with a look of disgust. The cockroach is on a burger, and there are other burgers on the plate.
Aesthetic Score : 0.2
Mood : disgust, shock, fear
Quality
Entropy : 6.89
Noise : 84
Prompt Clip Score : 0.29
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image is slightly blurry and the lighting is uneven.
Trump Holds Court in Oval Office Amidst Serious Atmosphere
A cartoon depiction of Donald Trump in the Oval Office, surrounded by men in suits, captures a serious and powerful mood. The image portrays Trump with a stern expression, while the other men in the room appear equally serious, suggesting a weighty political moment.
Prompt
facial-expressions Disgust: Disdain and disgust ; A hero, their face hardened with disgust, as they confront a corrupt politician; eye-level; Hero; a grand, opulent office with a powerful politician sitting behind a large desk; cinematic
Characteristic
Shot : Donald Trump sitting at the Resolute Desk in the Oval Office with two men standing behind him, one on each side.
Aesthetic Score : 0.5
Mood : serious, political, powerful
Quality
Entropy : 6.48
Noise : 80
Prompt Clip Score : 0.25
AI Evaluation
Likelihood of AI : 0.70
Image errors : The image has a slightly cartoonish style, and the characters’ faces are not very realistic. The lighting is also a bit flat.
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 0.2, indicating it did not perform well in capturing the intended camera position. This suggests the model may not be very sensitive to camera position instructions.
- Shot Analysis: The model scored 0.56, which is considered good. This means the model was able to understand the scene in the prompt and create an image that reflects it fairly well.
- Aesthetic Analysis: The model scored 0.29, which is considered very good. This means the generated image closely matched the expected aesthetic, indicating the model is capable of producing visually appealing results.
Overall, the model shows promise in understanding scene descriptions and creating visually pleasing images. However, it needs improvement in 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://stability.ai