AI's Artistic Journey: Capturing Poses, But Missing the Mood with Scenario
- 10 minutes read - 1997 wordsTable of Contents
In the realm of AI image generation, capturing the essence of a scene goes beyond simply depicting objects and landscapes. It involves conveying emotions, moods, and the very essence of a moment. This is where the concept of ‘dramatic style poses’ comes into play. These poses, often used in photography and filmmaking, are designed to evoke specific feelings and tell a story through body language. They can range from heroic stances to expressions of vulnerability, each adding a layer of depth and meaning to the image. For example, a lone warrior standing tall against a setting sun evokes a sense of heroism and resilience, while a group of friends huddled together on a rooftop conveys intimacy and camaraderie. This blog post delves into the fascinating world of AI image generation, exploring its ability to capture these dramatic poses and the challenges it faces in translating them into visually compelling and aesthetically pleasing images.
Created with: scenario
Warrior’s Sunset: A Silhouette of Power
A female warrior, bathed in the golden light of a desert sunset, stands resolute with her sword drawn. The dramatic lighting and her powerful pose evoke a sense of epic determination.
Prompt
poses fighting: epic, determined ; A lone warrior; wide shot; heroism; a desolate battlefield with the setting sun in the background; cinematic
Characteristic
Shot : A female warrior in full armor stands in a desert landscape, holding a sword, with the sun setting behind her.
Aesthetic Score : 0.7
Mood : epic, powerful, dramatic
Quality
Entropy : 6.79
Noise : 89
Prompt Clip Score : 0.22
AI Evaluation
Likelihood of AI : 0.80
Image errors : The lighting is a bit too artificial, the sand looks a bit too smooth and unnatural, and the overall composition could be improved by adding more depth and interest to the background.
Warriors Clash in the Jungle’s Shadow
A tense standoff unfolds amidst the lush foliage of a jungle, with a group of warriors facing off against a backdrop of ancient stone. The scene is charged with drama and adventure, as the characters’ stances and weapons hint at an impending conflict.
Prompt
poses fighting: intense, adventurous ; A group of adventurers; medium shot; adventure; a dense jungle with ancient ruins in the distance; cinematic
Characteristic
Shot : A group of warriors in a jungle setting are facing off against each other. A man in the foreground holds a spear and is looking directly at the viewer. He is wearing leather armor and has long hair. Behind him are two women, one of whom is drawing a bow and the other is holding a sword. There is a temple in the background.
Aesthetic Score : 0.7
Mood : dramatic, tense, suspenseful
Quality
Entropy : 6.59
Noise : 118
Prompt Clip Score : 0.29
AI Evaluation
Likelihood of AI : 0.10
Image errors : There are some minor artifacts in the image, particularly in the foliage. The image is also slightly blurry.
Cyberpunk Dreams: A Woman’s Gaze into the Neon Future
A woman in a cyberpunk-style jacket stands amidst a city bathed in vibrant neon lights, her gaze directed upwards. The scene evokes a sense of mystery, hope, and anticipation, with the woman’s powerful pose and the dramatic lighting suggesting a future filled with possibilities.
Prompt
poses fighting: dynamic, futuristic ; A player character; close-up; gaming; a neon-lit cityscape with holographic projections; cinematic
Characteristic
Shot : A young woman in a cyberpunk-style outfit stands in a city street with neon signs in the background. She is looking up, her expression is one of contemplation or curiosity.
Aesthetic Score : 0.8
Mood : cyberpunk, futuristic, mysterious
Quality
Entropy : 6.76
Noise : 91
Prompt Clip Score : 0.25
AI Evaluation
Likelihood of AI : 1.00
Image errors : The image is well-composed and rendered. No artifacts or errors are visible. The subject is in sharp focus and the lighting is well-balanced.
Laughter and Light: Joyful Moments in a Vibrant Marketplace
Two women in colorful traditional clothing share a moment of genuine laughter and connection amidst the bustling energy of a marketplace. Their playful interaction captures the vibrant spirit of the scene, radiating joy and warmth.
Prompt
poses fighting: chaotic, humorous ; Two tourists; medium shot; tourism; a bustling marketplace with colorful stalls and vibrant crowds; cinematic
Characteristic
Shot : Two women dressed in colourful clothing are playfully interacting in an open market setting, with the background of a traditional market area and other people in the background.
Aesthetic Score : 0.7
Mood : joyful, vibrant, playful
Quality
Entropy : 6.71
Noise : 107
Prompt Clip Score : 0.26
AI Evaluation
Likelihood of AI : 0.20
Image errors : No noticeable errors in the image. The color balance is good, and the overall sharpness is sufficient.
A Solitary Figure in the Desert’s Embrace
A woman, cloaked in a long brown dress, stands alone on a sand dune, her gaze fixed on the horizon. The setting sun paints the sky in hues of orange and pink, casting a warm glow over the vast, desolate landscape. The scene evokes a sense of serenity, contemplation, and a touch of mystery, leaving the viewer to ponder the woman’s story and the secrets held by the desert.
Prompt
poses fighting: isolated, desperate ; A lone traveler; long shot; travel; a vast desert landscape with a lone sand dune in the foreground; cinematic
Characteristic
Shot : A lone figure stands on a sand dune in a desert landscape, the setting sun casting a warm glow over the scene.
Aesthetic Score : 0.7
Mood : serene, contemplative, dramatic
Quality
Entropy : 6.07
Noise : 82
Prompt Clip Score : 0.26
AI Evaluation
Likelihood of AI : 0.60
Image errors : The image is slightly overexposed, and the sand dunes in the background appear a bit too smooth and uniform. The color of the character’s clothes is not quite consistent throughout the image, they appear more brown in the upper part than in the lower one.
Golden Hour Friends: Rooftop Fun with a City View
Capture the carefree spirit of youth as friends gather on a rooftop at dusk, bathed in the warm glow of the setting sun. The city lights twinkle behind them, adding a touch of glamour to this fun and youthful moment.
Prompt
poses fighting: energetic, playful ; A group of friends; medium shot; groups; a rooftop overlooking a city skyline at night; cinematic
Characteristic
Shot : A group of friends are hanging out on a rooftop at dusk, enjoying the city lights
Aesthetic Score : 0.7
Mood : fun, playful, youthful
Quality
Entropy : 6.68
Noise : 92
Prompt Clip Score : 0.27
AI Evaluation
Likelihood of AI : 0.20
Image errors : No noticeable errors.
Fiery Determination: A Warrior Stands Against the Flames
A female warrior, clad in armor and blue clothing, stands defiantly against a backdrop of roaring flames. Her sword is drawn, her stance resolute, capturing the intensity and drama of a fierce battle. The fire, a symbol of both danger and courage, highlights her strength and unwavering spirit.
Prompt
poses fighting: tragic, determined ; A lone warrior; close-up; heroism; a burning village with smoke billowing in the air; cinematic
Characteristic
Shot : A female warrior in full armor stands in a dramatic pose, holding a sword in front of her. She is in a desert setting with large flames and smoke surrounding her, creating a sense of intensity and conflict.
Aesthetic Score : 0.7
Mood : intense, dramatic, powerful
Quality
Entropy : 6.68
Noise : 98
Prompt Clip Score : 0.24
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image has some slight artifacts in the smoke and flames, but they are not overly distracting.
Five Adventurers Brave the Unknown Depths of a Mysterious Cave
A flickering fire illuminates a group of five adventurers, clad in medieval garb, as they venture deeper into a cavernous, rock-hewn passage. Their weapons are at the ready, their expressions a mix of anticipation and caution. The scene evokes a sense of adventure, mystery, and suspense, leaving the viewer to wonder what secrets lie hidden within the cave’s depths.
Prompt
poses fighting: suspenseful, adventurous ; A group of explorers; wide shot; adventure; a dark cave with flickering torches and mysterious shadows; cinematic
Characteristic
Shot : A group of adventurers are exploring a cave, they are holding torches and weapons. The light of the torches illuminates the rocky walls of the cave, casting shadows and creating a sense of mystery and danger.
Aesthetic Score : 0.8
Mood : adventurous, mysterious, dramatic
Quality
Entropy : 6.72
Noise : 104
Prompt Clip Score : 0.27
AI Evaluation
Likelihood of AI : 0.80
Image errors : The image is free of major artifacts or errors. Some slight aliasing can be observed on the edges of the characters, but this is minor.
Lost in the Neon Glow: A Gamer’s Immersive Journey
A young woman, eyes locked on the virtual world, wields a toy gun in a futuristic setting bathed in vibrant neon light. Her focused expression and dynamic pose capture the excitement and intensity of her immersive gaming experience.
Prompt
poses fighting: immersive, intense ; A gamer; close-up; gaming; a virtual reality headset with a pixelated world projected in the background; cinematic
Characteristic
Shot : A woman is wearing a VR headset and holding a toy gun, likely playing a virtual reality game. The background is a pink wall with a few geometric shapes. The scene appears to be in a gaming space or home entertainment area.
Aesthetic Score : 0.6
Mood : intense, playful, futuristic
Quality
Entropy : 6.51
Noise : 80
Prompt Clip Score : 0.27
AI Evaluation
Likelihood of AI : 0.20
Image errors : There are no significant errors in the image. However, the light reflection in the VR headset lens could be slightly more natural.
Running on the Rails: A Moment of Youthful Adventure
Two young women, full of energy and excitement, race across a train platform. The woman in front, clad in dark green, carries her friend on her back, their laughter echoing in the air. The blurred background captures the intensity of their movement, hinting at a thrilling journey ahead.
Prompt
poses fighting: fast-paced, chaotic ; Two travelers; medium shot; travel; a crowded train station with people rushing in all directions; cinematic
Characteristic
Shot : Two young women are standing on a train platform, one is holding the other on her back. The train is in the background and there are other people walking around on the platform.
Aesthetic Score : 0.7
Mood : suspenseful, energetic, playful
Quality
Entropy : 6.81
Noise : 92
Prompt Clip Score : 0.29
AI Evaluation
Likelihood of AI : 0.10
Image errors : No notable artifacts or errors.
Conclusion
The results show that the generative AI model performed well in terms of camera position and shot analysis, but struggled with aesthetic analysis.
Here’s a breakdown:
- Camera Position: The model scored a 0.5, which falls within the “good” range. This indicates that the model was able to reasonably interpret and implement the camera position specified in the prompt.
- Shot Analysis: The model scored a 0.62, also within the “good” range. This suggests that the model understood the scene described in the prompt and generated an image with a shot composition that aligns well with the prompt’s intent.
- Aesthetic Analysis: The model scored a 0.05, which is significantly lower than the ideal range of -0.2 to 0.1. This indicates that the generated image’s aesthetic deviated from the expected aesthetic based on the prompt.
Overall, the model demonstrates a good understanding of camera position and shot composition, but needs improvement in generating images that match the desired aesthetic.
Sources:
- https://www.writerswrite.co.za/cheat-sheets-for-writing-body-language/
- https://mads3df.wordpress.com/2013/09/04/storytelling-poses/
- https://www.pinterest.com/pegasister890/character-poses/
- https://www.youtube.com/watch?v=udky6ANxWws
- https://maven.com/articles/storytelling-techniques
- https://www.scenario.com