AI's Artistic Struggle: Capturing the Essence of Poses with Bfl-flux-pro
- 10 minutes read - 1932 wordsTable of Contents
In the realm of artificial intelligence, the ability to generate images based on textual descriptions is a rapidly evolving field. This experiment aimed to explore the capabilities of a generative AI model in capturing the essence of poses and translating them into visually compelling images. The results revealed both strengths and weaknesses, highlighting the ongoing challenges of achieving true artistic expression in AI-generated imagery. Dramatic style poses, often used in storytelling and visual media to convey emotion and action, were the focus of this experiment. These poses are characterized by exaggerated movements, dynamic angles, and a sense of heightened drama. Examples of dramatic style poses can be found in action movies, superhero comics, and even classical paintings. The goal was to see if the AI model could understand and replicate the essence of these poses, capturing their emotional impact and visual appeal.
Created with: flux-pro
Silhouetted Knight in a Dramatic Sunset
A lone knight stands tall against a fiery sunset, his sword held high, with a majestic castle looming in the background. The use of light and shadow creates a powerful and epic scene, highlighting the knight’s heroic stance.
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 knight in full armor stands confidently in a field with a castle in the background. The sun is setting behind him, casting a warm glow on the scene.
Aesthetic Score : 0.7
Mood : epic, heroic, dramatic
Quality
Entropy : 6.51
Noise : 74
Prompt Clip Score : 0.20
AI Evaluation
Likelihood of AI : 0.60
Image errors : There are some minor artifacts in the cape, which look a little bit too smooth and unrealistic.
Lost in the Jungle’s Embrace: A Mysterious Adventure Awaits
Three figures stand shrouded in mystery, their journey through a lush, overgrown jungle hinted at by their fantastical attire. A large rock formation looms in the background, adding to the sense of wonder and intrigue. The soft, atmospheric lighting casts long shadows, further enhancing the mysterious mood of this captivating scene.
Prompt
poses fighting: intense, adventurous ; A group of adventurers; medium shot; adventure; a dense jungle with ancient ruins in the distance; cinematic
Characteristic
Shot : Three figures, two male and one female, are standing in a lush green jungle-like environment. They are near a tall cliff face with a stone structure. The background is a misty, green haze, suggesting a dense forest or a very tall cliff.
Aesthetic Score : 0.6
Mood : mysterious, adventurous, contemplative
Quality
Entropy : 6.79
Noise : 111
Prompt Clip Score : 0.26
AI Evaluation
Likelihood of AI : 0.60
Image errors : The image has some slight artifacts in the form of blurry areas and a few pixels with slightly unnatural colors. These are minor and do not detract from the overall aesthetic.
Futuristic Firefight: Soldier Unleashes Explosive Power
A futuristic soldier, amidst a neon-lit urban landscape, unleashes a powerful blast from their weapon, creating a dazzling explosion. The scene captures the intensity and action of a futuristic battle, with the soldier’s pose adding to the dramatic effect.
Prompt
poses fighting: dynamic, futuristic ; A player character; close-up; gaming; a neon-lit cityscape with holographic projections; cinematic
Characteristic
Shot : A futuristic soldier firing a weapon in a city setting. The lighting is vibrant and colorful, giving a sense of energy and action. The soldier is positioned against a backdrop of towering buildings, further emphasizing the scale and power of the scene.
Aesthetic Score : 0.6
Mood : intense, futuristic, action
Quality
Entropy : 6.93
Noise : 100
Prompt Clip Score : 0.25
AI Evaluation
Likelihood of AI : 0.80
Image errors : There are some artifacts around the edges of the image, particularly near the soldier. There’s a slight blurriness around the edges of the soldier and the weapon. The explosion is somewhat unrealistic and lacks visual detail.
Love in the Bustling City: A Romantic Daytime Scene
In the heart of a vibrant city, a couple shares a romantic moment amidst the crowd. Their playful interaction and casual posing create a sense of intimacy and lightheartedness, making this scene a perfect blend of romance and urban energy.
Prompt
poses fighting: chaotic, humorous ; Two tourists; medium shot; tourism; a bustling marketplace with colorful stalls and vibrant crowds; cinematic
Characteristic
Shot : Two young people, a man and a woman, are standing in a crowded street market, the woman is looking at the man. The setting is a European city with historic buildings and cobblestone streets.
Aesthetic Score : 0.6
Mood : casual, romantic, urban
Quality
Entropy : 6.82
Noise : 70
Prompt Clip Score : 0.24
AI Evaluation
Likelihood of AI : 0.10
Image errors : Slight graininess and compression artifacts, especially visible in the shadows.
Silhouetted Against the Setting Sun: A Lone Figure in the Desert
A solitary figure traverses a vast, undulating desert landscape, their silhouette stark against the fiery hues of the setting sun. The scene evokes a sense of mystery, loneliness, and contemplation, leaving the viewer to ponder the figure’s journey and the secrets held by the endless dunes.
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 walks up a sand dune in a desert landscape at sunset.
Aesthetic Score : 0.7
Mood : serene, contemplative, adventurous
Quality
Entropy : 6.56
Noise : 66
Prompt Clip Score : 0.27
AI Evaluation
Likelihood of AI : 0.20
Image errors : No noticeable errors or artifacts.
Silhouettes of Joy: Friends Light Up the Night
A group of friends, their laughter echoing through the city, are captured in silhouette against a vibrant cityscape. The scene radiates joy, energy, and a sense of carefree camaraderie. The dramatic effect of their silhouettes against the city lights adds a touch of magic to this moment of pure happiness.
Prompt
poses fighting: energetic, playful ; A group of friends; medium shot; groups; a rooftop overlooking a city skyline at night; cinematic
Characteristic
Shot : Four friends, two men and two women, are silhouetted against a cityscape at night. They are laughing and interacting with each other.
Aesthetic Score : 0.6
Mood : joyful, playful, carefree
Quality
Entropy : 6.56
Noise : 73
Prompt Clip Score : 0.32
AI Evaluation
Likelihood of AI : 0.10
Image errors : There is some noise in the image, particularly in the shadows. The lighting is also somewhat uneven. The composition of the image could be improved by moving the subjects closer to the center of the frame and having them interact more.
Warrior’s Stand: A Moment of Epic Tension
A lone warrior, sword raised, stands against a backdrop of fiery destruction. The dramatic lighting and pose evoke a sense of anticipation and somberness, hinting at a battle fought and a story yet to unfold.
Prompt
poses fighting: tragic, determined ; A lone warrior; close-up; heroism; a burning village with smoke billowing in the air; cinematic
Characteristic
Shot : A lone warrior stands in a fiery, apocalyptic landscape, holding a sword aloft. The smoke and flames suggest a battle has just taken place or is about to begin.
Aesthetic Score : 0.7
Mood : epic, dramatic, melancholic
Quality
Entropy : 6.73
Noise : 70
Prompt Clip Score : 0.20
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image has some minor noise and grain, particularly in the background. The edges of the sword could be sharper.
Shadows and Light: A Journey Through the Cave
A group of adventurers, their torches casting flickering shadows, navigate the depths of a mysterious cave. The light from above paints the rough walls with an ethereal glow, creating a sense of wonder and anticipation. This captivating scene evokes a mood of adventure, mystery, and hope.
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 people walking through a cave with torches
Aesthetic Score : 0.6
Mood : mysterious, adventurous, hopeful
Quality
Entropy : 6.83
Noise : 83
Prompt Clip Score : 0.28
AI Evaluation
Likelihood of AI : 0.80
Image errors : The lighting is a bit flat and the textures on the cave walls are not very realistic.
Lost in the Digital Realm: A Glimpse into Virtual Reality
A young man, immersed in a futuristic virtual world, sits in a darkened room, his focus solely on the digital landscape reflected in his VR goggles. The image evokes a sense of mystery and intrigue, leaving the viewer to wonder what captivating experiences lie within the virtual realm.
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 man wearing a VR headset and holding a video game controller, the background is blurry and contains some colorful lights.
Aesthetic Score : 0.6
Mood : focused, intense, futuristic
Quality
Entropy : 6.63
Noise : 69
Prompt Clip Score : 0.24
AI Evaluation
Likelihood of AI : 0.10
Image errors : There are no noticeable errors.
A Walk in the City: Mystery and Connection on a Busy Street
A man in a suit and a woman in a jacket stroll down a bustling city street, their gazes fixed in the same direction. Their closeness is undeniable, but the nature of their relationship remains shrouded in intrigue. This captivating scene evokes a sense of urban energy, casual confidence, and a touch of mystery.
Prompt
poses fighting: fast-paced, chaotic ; Two travelers; medium shot; travel; a crowded train station with people rushing in all directions; cinematic
Characteristic
Shot : A couple is walking through an airport or train station. They are talking and seem to be in a good mood. There is a large digital display in the background.
Aesthetic Score : 0.6
Mood : romantic, casual, urban
Quality
Entropy : 6.87
Noise : 80
Prompt Clip Score : 0.22
AI Evaluation
Likelihood of AI : 0.20
Image errors : Some minor noise and artifacts are visible in the background.
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:
- Score: 0.45
- Interpretation: This score falls below the “good” range of 0.5 to 0.75. It suggests that the model didn’t perfectly capture the intended camera positions described in the prompt.
Shot Analysis:
- Score: 0.61
- Interpretation: This score falls within the “good” range of 0.5 to 0.75. It indicates that the model was able to understand the scene described in the prompt and create a shot that aligns with it to a decent degree.
Aesthetic Analysis:
- Score: 0.09
- Interpretation: This score is significantly higher than the “very good” range of -0.2 to 0.1. It suggests that the generated image’s aesthetic deviated significantly from the expected aesthetic described in the prompt.
Overall:
The model demonstrates a good understanding of shot composition and scene description, but struggles to achieve the desired aesthetic. This suggests that the model might need further training to better understand and translate aesthetic preferences into visual outputs.
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://api.bfl.ml/docs#/util/get_result_v1_get_result_get