AI Struggles to Capture the 'Dramatic' Aesthetic with Midjourney

The ‘dramatic’ aesthetic is a powerful tool in visual storytelling, often used to evoke strong emotions and create a sense of tension or excitement. It’s characterized by dramatic lighting, strong contrasts, and a focus on creating a sense of depth and scale. This aesthetic is commonly used in film, photography, and even video games to enhance the narrative and create a more immersive experience. However, teaching AI to understand and replicate this aesthetic presents unique challenges. This blog post explores the results of an experiment where an AI model was tasked with generating images based on specific aesthetic styles and scenes, specifically focusing on the ‘dramatic’ aesthetic. We analyze the results and discuss the challenges of teaching AI to understand and replicate artistic styles.

Created with: midjourney

Lost in the Clouds: A Solitary Figure on a Mountain Peak

A lone figure stands on a mountaintop, dwarfed by swirling clouds. The scene evokes a sense of serenity, mystery, and awe, with the dramatic contrast between the small figure and the vast, ethereal landscape.

Prompt

Abstract: Epic, triumphant ; A lone figure standing on a mountain peak; wide shot; Heroism; a vast, swirling sea of clouds; cinematic

Characteristic

Shot : A lone figure stands on the peak of a mountain, surrounded by a sea of clouds. The sky is a soft, pale blue, and the clouds are a swirling mass of white and gray.

Aesthetic Score : 0.8

Mood : serene, ethereal, contemplative

Quality

Entropy : 6.58

Noise : 97

Prompt Clip Score : 0.30

AI Evaluation

Likelihood of AI : 0.90

Image errors : Some minor artifacts are visible in the clouds, likely due to image processing.

A Hand Reaches into the Dreamy Vortex

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 hand, reaching towards a swirling, abstract vortex of colors, evokes a sense of mystery and wonder. The ethereal mood and dramatic effect draw the viewer into the captivating scene, leaving them curious about what lies within the swirling depths.

Prompt

Abstract: Mysterious, exciting ; A hand reaching out to grasp a shimmering, ethereal portal; close-up; Adventure; a swirling vortex of colors; cinematic

Characteristic

Shot : A hand reaches towards a swirling, colorful abstract background

Aesthetic Score : 0.7

Mood : dreamy, mystical, abstract

Quality

Entropy : 6.68

Noise : 102

Prompt Clip Score : 0.30

AI Evaluation

Likelihood of AI : 0.80

Image errors : The image has a slightly digital and unrealistic look. The background has a slight blur effect.

Lost in the Neon Labyrinth: A Cyberpunk City Awakens

Dive into a vibrant, chaotic cityscape where towering structures pierce the sky and neon lights paint a mesmerizing canvas. This futuristic metropolis pulsates with energy, showcasing the overwhelming scale and dynamism of a cyberpunk world.

Prompt

Abstract: Energetic, futuristic ; A pixelated landscape with glowing, abstract figures; medium shot; Gaming; a digital, neon-lit cityscape; cinematic

Characteristic

Shot : A digital cityscape with a focus on lights, neon signs, and a futuristic vibe.

Aesthetic Score : 0.7

Mood : cyberpunk, futuristic, abstract

Quality

Entropy : 6.51

Noise : 121

Prompt Clip Score : 0.33

AI Evaluation

Likelihood of AI : 0.90

Image errors : The image appears to have some pixelation and aliasing.

A Single Rose Blooms in the Face of Adversity

A vibrant pink rose pushes through cracked, dry earth, offering a beacon of hope against a backdrop of a cloudy, overcast sky. The stark contrast between the delicate flower and the barren landscape evokes a sense of resilience and somber beauty.

Prompt

Abstract: Hopeful, melancholic ; A single, vibrant flower blooming in a desolate, cracked landscape; close-up; Tourism; a surreal, otherworldly desert; cinematic

Characteristic

Shot : A single pink rose growing out of cracked, dry earth, with a dramatic sky in the background

Aesthetic Score : 0.7

Mood : hopeful, resilience, survival

Quality

Entropy : 6.75

Noise : 98

Prompt Clip Score : 0.30

AI Evaluation

Likelihood of AI : 0.30

Image errors : No visible artifacts or errors

City Lights, City Life

A vibrant cityscape at night, captured with a sense of energy and motion. Light trails from cars and buildings create a dynamic composition, drawing the viewer into the heart of the urban scene.

Prompt

Abstract: Dynamic, chaotic ; A blurred, kaleidoscopic image of a bustling city street; long shot; Travel; a whirlwind of colors and movement; cinematic

Characteristic

Shot : A busy city street at night with buildings and lights blurred by motion.

Aesthetic Score : 0.6

Mood : dynamic, energetic, urban

Quality

Entropy : 6.64

Noise : 113

Prompt Clip Score : 0.33

AI Evaluation

Likelihood of AI : 0.20

Image errors : No significant errors, but some minor artifacts around the edges.

Silhouettes of Hope: A Family’s Sunset Walk

A painterly depiction of a family walking into the sunset, their silhouettes bathed in warm light. The scene evokes a sense of warmth, hope, and nostalgia, capturing the beauty of shared moments and the promise of a bright future.

Prompt

Abstract: Hopeful, nostalgic ; A silhouette of a family holding hands, walking towards a glowing, abstract sun; medium shot; Family; a warm, golden sunset; cinematic

Characteristic

Shot : Silhouettes of a family walking towards a setting sun

Aesthetic Score : 0.6

Mood : tranquil, hopeful, sentimental

Quality

Entropy : 6.67

Noise : 100

Prompt Clip Score : 0.34

AI Evaluation

Likelihood of AI : 0.90

Image errors : The image has some artifacts and noise, particularly in the sky and around the silhouettes.

A City’s Reflection in a Shattered Gaze

A close-up shot captures an eye peering through a broken window, the city’s lights and shadows fragmented and distorted in the shattered glass. The image evokes a sense of vulnerability and unease, highlighting the harsh realities of urban life.

Prompt

Abstract: Intense, suspenseful ; A single, abstract eye peering through a cracked, distorted window; close-up; Heroism; a dark, ominous cityscape; cinematic

Characteristic

Shot : A close-up of an eye looking through a shattered windowpane at a cityscape. The eye is the focal point and the city is blurred in the background.

Aesthetic Score : 0.6

Mood : dark, mysterious, intense

Quality

Entropy : 6.80

Noise : 113

Prompt Clip Score : 0.30

AI Evaluation

Likelihood of AI : 0.70

Image errors : The image has some minor artifacts around the edges of the broken glass. The city buildings are not sharply focused and some of the edges appear blurry.

Dive into a Psychedelic Vortex of Color and Light

Experience a mesmerizing digital tunnel where vibrant colors swirl and dance, creating a dynamic and futuristic atmosphere. The swirling pattern pulls you into its depths, offering a psychedelic journey through a world of abstract beauty.

Prompt

Abstract: Intense, exhilarating ; A swirling vortex of colors and shapes representing a chaotic, digital world; wide shot; Gaming; a vibrant, neon-lit landscape; cinematic

Characteristic

Shot : Abstract spiral of colorful lights and geometric shapes, resembling a futuristic tunnel or portal

Aesthetic Score : 0.7

Mood : psychedelic, vibrant, dynamic

Quality

Entropy : 6.59

Noise : 121

Prompt Clip Score : 0.31

AI Evaluation

Likelihood of AI : 0.90

Image errors : Minor aliasing artifacts and some pixelation around the edges.

Confronting the Storm: A Solitary Figure on the Cliff’s Edge

A lone figure stands defiant against the raw power of nature. The stormy sea churns below, while swirling clouds fill the sky, creating a dramatic and melancholic scene. The image evokes a sense of contemplation and the vastness of the natural world.

Prompt

Abstract: Solitary, contemplative ; A lone, abstract figure standing on a cliff overlooking a vast, swirling ocean; wide shot; Travel; a stormy, dramatic seascape; cinematic

Characteristic

Shot : A lone figure stands on a cliff overlooking a swirling, stormy sea. The sky is dark and brooding, with hints of light breaking through the clouds.

Aesthetic Score : 0.7

Mood : dramatic, powerful, melancholic

Quality

Entropy : 6.72

Noise : 124

Prompt Clip Score : 0.30

AI Evaluation

Likelihood of AI : 0.10

Image errors : The image is slightly blurry and the brushstrokes are quite visible, giving it a slightly unfinished feel.

Mystical Silhouettes in an Ethereal Landscape

This abstract painting evokes a sense of mystery and intrigue with its silhouettes of four figures against a painterly background. The ethereal mood and dramatic effect create a captivating and evocative experience.

Prompt

Abstract: Sentimental, reflective ; A series of overlapping, abstract shapes representing a family’s journey through life; medium shot; Family; a warm, nostalgic glow; cinematic

Characteristic

Shot : Silhouettes of a family, possibly a mother and two children, against a background of swirling colors and abstract shapes.

Aesthetic Score : 0.6

Mood : mystical, dreamlike, warm

Quality

Entropy : 6.53

Noise : 109

Prompt Clip Score : 0.28

AI Evaluation

Likelihood of AI : 0.80

Image errors : The image has a slightly pixelated appearance, particularly in the background. The shapes and silhouettes are somewhat blurry, which might indicate a digital overlay or filter applied to the image.

Conclusion

The results show that the generative AI model performed well in understanding the scene and camera position, but struggled with the aesthetic. Here’s a breakdown:

• Camera Position: The model scored 0.2, 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 0.52, indicating it performed moderately well in understanding the scene described in the prompt. A score between 0.5 and 0.75 would be considered good, and above 0.75 very good.
• Aesthetic Analysis: The model scored 0.06, indicating it did not perform well in achieving the desired aesthetic. A score between -0.2 and 0.1 would be considered very good.

Overall, the model seems to have difficulty translating the prompt’s aesthetic and camera position into the generated image. It performed better in understanding the scene itself.