AI's Artistic Struggle: Capturing the 'Dramatic' Aesthetic with Flux-schnell
- 9 minutes read - 1849 wordsTable of Contents
The ‘dramatic’ aesthetic is a powerful tool in visual storytelling, often used to evoke strong emotions and create a sense of grandeur. It’s characterized by elements like dramatic lighting, contrasting colors, and dynamic compositions. This style is commonly found in film, photography, and painting, and is often used to enhance the impact of a scene or narrative. In this blog post, we explore the results of an experiment testing an AI model’s ability to generate images with this specific aesthetic.
Created with: flux-schnell
Silhouetted Warrior at Sunset: A Dramatic Epic
A lone warrior, silhouetted against a vibrant sunset, stands poised with a spear. The scene evokes a sense of epic heroism and dramatic tension, capturing the essence of a timeless battle.
Prompt
style-aesthetic Stylized: Epic and melancholic ; A lone warrior; wide shot; Heroism; A desolate battlefield with a setting sun; cinematic
Characteristic
Shot : A lone figure, likely a warrior, stands silhouetted against a dramatic sunset with a spear held high. The figure is facing towards the viewer, and the scene is set in a vast, seemingly desolate landscape.
Aesthetic Score : 0.6
Mood : epic, melancholic, powerful
Quality
Entropy : 6.37
Noise : 58
Prompt Clip Score : 0.25
AI Evaluation
Likelihood of AI : 0.20
Image errors : There are no significant errors in the image, although the figure’s outline is slightly jagged in some areas. The sunset is a bit too bright and lacks depth.
Unveiling the Secrets of a Hidden Treasure
A mysterious cavern, bathed in soft light, reveals a treasure chest overflowing with gold coins. The dramatic lighting creates an air of wonder and adventure, hinting at the secrets this hidden location holds.
Prompt
style-aesthetic Stylized: Excitement and wonder ; A treasure chest overflowing with gold; close-up; Adventure; A dark and mysterious cave; cinematic
Characteristic
Shot : A treasure chest overflowing with gold coins, set against a dramatic backdrop of a dark cave with blue lighting
Aesthetic Score : 0.7
Mood : mysterious, adventurous, magical
Quality
Entropy : 6.38
Noise : 73
Prompt Clip Score : 0.25
AI Evaluation
Likelihood of AI : 0.80
Image errors : The image appears to be slightly blurry, especially in the background and some of the gold coins. There are some subtle artifacts and unnatural textures in the gold coins, they look too smooth and artificial
A Lone Warrior in a City of Glass and Steel
A dramatic image of a lone figure in dark armor standing amidst a futuristic cityscape. The city’s towering structures of glass and steel reach towards a hazy blue sky, creating a powerful and evocative scene. The figure’s pose and the dramatic lighting enhance the sense of power and mystery.
Prompt
style-aesthetic Stylized: Triumphant and futuristic ; A player’s avatar, a powerful warrior, standing triumphantly; medium shot; Gaming; A vibrant and futuristic cityscape; cinematic
Characteristic
Shot : A masked warrior stands in a futuristic city. The background is blurry, with tall buildings and bright lights. There is a sense of mystery and danger.
Aesthetic Score : 0.8
Mood : futuristic, epic, powerful
Quality
Entropy : 6.81
Noise : 94
Prompt Clip Score : 0.25
AI Evaluation
Likelihood of AI : 0.90
Image errors : No visible errors.
Golden Hour Majesty: City Skyline at Dusk
A breathtaking aerial view captures the vibrant energy of a modern city skyline bathed in the warm glow of the setting sun. The dramatic golden hour light highlights the architectural details and textures of the towering buildings, creating a sense of urban grandeur.
Prompt
style-aesthetic Stylized: Energetic and lively ; A panoramic view of a bustling city; long shot; Tourism; A vibrant and colorful cityscape; cinematic
Characteristic
Shot : A panoramic view of a cityscape, with tall buildings and a cloudy sky. The sunset is casting a warm glow over the scene, highlighting the buildings and adding depth to the image.
Aesthetic Score : 0.7
Mood : tranquil, vibrant, urban
Quality
Entropy : 6.85
Noise : 118
Prompt Clip Score : 0.22
AI Evaluation
Likelihood of AI : 0.20
Image errors : There are some minor artifacts present in the image, particularly around the edges of buildings and in the sky. The image also appears to be slightly over-sharpened.
Silhouetted Against the Setting Sun: A Moment of Contemplation
A lone traveler, silhouetted against a fiery sunset, stands in a vast, empty landscape. The scene evokes a sense of serenity, contemplation, and adventure, leaving the viewer to ponder the journey ahead.
Prompt
style-aesthetic Stylized: Serene and contemplative ; A lone traveler gazing at a breathtaking sunset; medium shot; Travel; A vast desert landscape; cinematic
Characteristic
Shot : A lone figure stands in a desert landscape, looking out at a setting sun.
Aesthetic Score : 0.7
Mood : tranquil, contemplative, hopeful
Quality
Entropy : 6.18
Noise : 49
Prompt Clip Score : 0.28
AI Evaluation
Likelihood of AI : 0.10
Image errors : The image appears to be slightly overexposed.
Family Fun in the Park: Laughter and Joy in Every Smile
A heartwarming scene of a family of four enjoying a sunny day in the park. Their laughter and playful interactions radiate joy and happiness, captured in a moment of genuine connection. The vibrant colors and natural lighting enhance the warmth and carefree spirit of the image.
Prompt
style-aesthetic Stylized: Joyful and heartwarming ; A family laughing and playing in a park; medium shot; Family; A sunny and idyllic park setting; cinematic
Characteristic
Shot : A family of four, including two young girls, is laughing and enjoying time together outdoors in a green park setting.
Aesthetic Score : 0.7
Mood : happy, playful, heartwarming
Quality
Entropy : 6.87
Noise : 104
Prompt Clip Score : 0.22
AI Evaluation
Likelihood of AI : 0.10
Image errors : The image appears to be slightly overexposed, with some blown-out highlights in the background.
Silhouetted Solitude: A Moment of Contemplation on the Cliff’s Edge
A lone figure stands silhouetted against a dramatic sky, their presence a stark contrast to the vast expanse of ocean below. The scene evokes a sense of melancholy and contemplation, capturing the raw beauty of solitude amidst nature’s grandeur.
Prompt
style-aesthetic Stylized: Dramatic and powerful ; A lone figure standing on a cliff overlooking a vast ocean; long shot; Heroism; A stormy sea with dramatic clouds; cinematic
Characteristic
Shot : A lone figure stands on a cliff overlooking a vast, blue ocean. The sky is overcast with clouds, adding a sense of mystery and drama to the scene.
Aesthetic Score : 0.7
Mood : melancholy, contemplative, dramatic
Quality
Entropy : 6.67
Noise : 88
Prompt Clip Score : 0.25
AI Evaluation
Likelihood of AI : 0.20
Image errors : No noticeable errors
Planning Your Next Adventure: A Map Filled with Possibilities
A close-up shot of a map, dotted with red push pins, captures the essence of planning a journey. The blurred background of a pub or restaurant adds a touch of nostalgia and adventure, hinting at the stories that await. The red pins create a focal point, symbolizing the anticipation and excitement of exploring new destinations.
Prompt
style-aesthetic Stylized: Intriguing and mysterious ; A map with pins marking locations of hidden treasures; close-up; Adventure; A dimly lit room with antique furniture; cinematic
Characteristic
Shot : A close-up shot of a map with red push pins marking locations. The map is on a wooden table in a dimly lit room, likely a pub or restaurant.
Aesthetic Score : 0.6
Mood : cozy, nostalgic, adventurous
Quality
Entropy : 6.87
Noise : 69
Prompt Clip Score : 0.24
AI Evaluation
Likelihood of AI : 0.10
Image errors : There is some slight blurriness around the edges of the image, which could be due to the low light conditions or the lens used.
A Hunter’s Focus: Intrigue and Tension in the Forest
A close-up shot captures a man with a serious expression, holding a bow and arrow in a dimly lit forest. The soft light and the man’s focused gaze create a sense of anticipation and mystery, hinting at a story waiting to unfold.
Prompt
style-aesthetic Stylized: Intense and focused ; A player’s character, a skilled archer, aiming at a target; close-up; Gaming; A dark and mysterious forest; cinematic
Characteristic
Shot : A young man in a forest, holding a bow and arrow, looking intensely focused
Aesthetic Score : 0.7
Mood : intense, mysterious, adventurous
Quality
Entropy : 6.34
Noise : 62
Prompt Clip Score : 0.29
AI Evaluation
Likelihood of AI : 0.20
Image errors : Slight chromatic aberration on the edges of the image and a bit of noise
Friends Enjoy a Cozy Night Under the City Skyline
Experience the perfect blend of relaxation and urban romance as a group of friends gather for a meal on a patio overlooking a stunning city skyline at night. The scene is set aglow by warm streetlights, while the city’s lights reflect off the water, creating a mesmerizing backdrop. A red umbrella adds a pop of color, and boats gently bob in the distance. The mood is set for an unforgettable evening.
Prompt
style-aesthetic Stylized: Social and celebratory ; A group of friends enjoying a meal at a restaurant with a view; medium shot; Tourism; A bustling city street with vibrant lights; cinematic
Characteristic
Shot : A group of friends enjoy a meal at an outdoor restaurant with a city skyline in the background.
Aesthetic Score : 0.7
Mood : cozy, urban, social
Quality
Entropy : 6.84
Noise : 101
Prompt Clip Score : 0.24
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image has some minor artifacts around the edges and a slight blurring effect in the background.
Conclusion
The results indicate that the generative AI model performed well in understanding and executing the camera position and shot instructions, but struggled with achieving the desired aesthetic. Here’s a breakdown:
- Camera Position: The model scored a 0.35, which falls below the “good” range of 0.5 to 0.75. This suggests that the model didn’t perfectly capture the intended camera positions described in the prompt.
- Shot Analysis: The model scored a 0.465, also below the “good” range. This indicates that the model didn’t fully understand the scene and shot composition as described in the prompt.
- Aesthetic Analysis: The model scored a 0.07, which is significantly below the “very good” range of -0.2 to 0.1. This suggests a significant difference between the expected aesthetic and the actual aesthetic of the generated image.
Overall, the model shows promise in understanding camera positions and shot composition, but needs improvement in capturing the desired aesthetic.
Sources:
- https://heartofnoir.com/knowing-noir/aesthetic-of-noir/
- https://www.yellowbrick.co/blog/film/maximizing-the-visual-impact-unveiling-the-art-of-film-aesthetics
- https://www.questjournals.org/jrhss/papers/vol10-issue8/1008255260.pdf
- https://www.jstor.org/stable/3331672
- https://www.cinepoetics.fu-berlin.de/activities/workshops/2020-12-ws/index.html
- https://resource.download.wjec.co.uk/vtc/2016-17/16-17_1-22/eng/Part%201%20What%20is%20Aesthetics.pdf
- https://fal.ai/models/fal-ai/flux/schnell/api