AI's Artistic Eye: Capturing the 'style-aesthetic' but Missing the Scene with Leonardo-ai
- 9 minutes read - 1729 wordsTable of Contents
The ‘style-aesthetic’ is a powerful tool in visual storytelling, allowing artists to evoke specific emotions and atmospheres through their work. This aesthetic often involves dramatic lighting, bold colors, and striking compositions, creating a sense of grandeur and intensity. It’s commonly used in genres like fantasy, sci-fi, and historical fiction, where the visual language needs to convey epic narratives and powerful emotions. This blog post explores the challenges of capturing this aesthetic using AI, analyzing the results of a generative model tasked with creating images based on specific scenes and aesthetics.
Created with: leonardo-ai
Solitude on the Mountaintop
A lone figure stands silhouetted against a dramatic sky, contemplating the vastness of the world from a mountain peak. The scene evokes a sense of serenity and contemplation, with the contrast between the bright clouds and the dark mountains adding a touch of drama.
Prompt
Minimalist: Epic, triumphant ; Lone figure standing on a mountain peak; wide shot; Heroism; Dramatic sky with clouds; cinematic
Characteristic
Shot : A lone hiker stands on a mountain peak, looking out at a vast expanse of rolling hills and a dramatic sky filled with large, fluffy clouds.
Aesthetic Score : 0.75
Mood : serene, dramatic, contemplative
Quality
Entropy : 6.73
Noise : 89
Prompt Clip Score : 0.32
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image appears to be slightly overexposed, with a slight halo effect around the clouds. The colors are a bit washed out and the details in the mountains are not sharp.
Uncharted Territories Await: A Vintage Compass Beckons
A weathered brass compass rests upon a worn leather bag, whispering tales of adventure and discovery. The image evokes a sense of mystery and exploration, inviting you to embark on a journey to the unknown.
Prompt
Minimalist: Intriguing, mysterious ; A single, weathered compass; close-up; Adventure; Dusty, worn leather bag; cinematic
Characteristic
Shot : A close-up of a vintage compass resting on a worn leather bag. The compass is in focus, while the bag is slightly blurred in the background.
Aesthetic Score : 0.75
Mood : vintage, rustic, adventurous
Quality
Entropy : 6.54
Noise : 91
Prompt Clip Score : 0.31
AI Evaluation
Likelihood of AI : 0.10
Image errors : Minor noise and grain are visible in the shadows, especially on the leather bag.
Immersed in the Game: A Close-Up Look at a Gamer’s Focus
This image captures the intensity of a gaming session, with a close-up shot of a player’s hands gripping a controller. The blurred background emphasizes the player’s focus, while the vibrant buttons add a touch of energy to the scene.
Prompt
Minimalist: Focused, intense ; A pair of hands holding a joystick; close-up; Gaming; Blurred background of a vibrant video game screen; cinematic
Characteristic
Shot : Close-up of a hand holding a black gaming controller with blurred background
Aesthetic Score : 0.6
Mood : focused, intense, playful
Quality
Entropy : 6.53
Noise : 70
Prompt Clip Score : 0.32
AI Evaluation
Likelihood of AI : 0.10
Image errors : No significant errors, but the image is a bit blurry in some areas, and the colors are not very vibrant.
A Suitcase Full of Secrets in a Forgotten Town
A vintage suitcase rests on the worn cobblestones of an empty street, whispering tales of journeys past and mysteries yet to be unraveled. The scene evokes a sense of nostalgia and intrigue, leaving you wondering about the stories hidden within the suitcase and the secrets it holds.
Prompt
Minimalist: Nostalgic, hopeful ; A lone suitcase on a cobblestone street; medium shot; Tourism; A quaint, European town in the background; cinematic
Characteristic
Shot : A vintage suitcase sits alone in the middle of a cobblestone street in a narrow, old town alleyway.
Aesthetic Score : 0.7
Mood : lonely, nostalgic, travel
Quality
Entropy : 6.93
Noise : 102
Prompt Clip Score : 0.35
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image has a slight blur in the background, especially in the sky. It appears to be a digital artifact. The colors are a bit muted and lack vibrancy.
Footprints in the Sand: A Mystery Unfolds
A tranquil beach scene invites contemplation as footprints lead away from the viewer, leaving a sense of mystery and intrigue. The ocean stretches out in the background, adding to the serene atmosphere. Who made these footprints, and where are they going?
Prompt
Minimalist: Serene, liberating ; A pair of feet walking on a sandy beach; low-angle shot; Travel; Vast ocean and horizon in the background; cinematic
Characteristic
Shot : Footprints leading away from the viewer on a sandy beach, the ocean is in the background out of focus.
Aesthetic Score : 0.7
Mood : tranquil, peaceful, contemplative
Quality
Entropy : 6.31
Noise : 95
Prompt Clip Score : 0.33
AI Evaluation
Likelihood of AI : 0.10
Image errors : No significant errors.
Tender Touch: A Moment of Love Captured
A close-up shot of two hands intertwined, set against a blurred playground backdrop, evokes a tender and playful mood. The intimacy of the close-up emphasizes the connection between the two individuals, creating a heartwarming image.
Prompt
Minimalist: Warm, loving ; A hand holding a child’s hand; close-up; Family; A blurred background of a park or playground; cinematic
Characteristic
Shot : A close-up shot of an adult holding a child’s hand while walking on a path in a park. The background is blurred and shows a playground with green grass.
Aesthetic Score : 0.7
Mood : tender, loving, protective
Quality
Entropy : 6.85
Noise : 76
Prompt Clip Score : 0.32
AI Evaluation
Likelihood of AI : 0.20
Image errors : There are no obvious errors or artifacts in the image.
A Single Red Rose, A Story Untold
A solitary red rose rests atop a black leather glove, its vibrant color a stark contrast against the dark backdrop. The worn wooden surface adds a touch of melancholy, hinting at a story waiting to be revealed. This image evokes a sense of dark romance and intrigue, leaving the viewer to ponder the emotions behind this poignant scene.
Prompt
Minimalist: Romantic, symbolic ; A single, red rose; close-up; Heroism; A weathered, worn leather glove; cinematic
Characteristic
Shot : A single red rose lying on top of a leather glove on a rustic wooden table
Aesthetic Score : 0.7
Mood : romantic, dark, vintage
Quality
Entropy : 6.59
Noise : 87
Prompt Clip Score : 0.37
AI Evaluation
Likelihood of AI : 0.20
Image errors : No visible errors
Unveiling the Past: A Journey Through Time in a Vintage Map
A close-up of an antique, leather-bound book reveals a faded, hand-drawn map of a coastal region, transporting you to a bygone era of exploration and adventure. The warm lighting and shallow depth of field create a nostalgic and intimate atmosphere, inviting you to delve into the secrets hidden within the map’s intricate details.
Prompt
Minimalist: Intriguing, adventurous ; A map with a single pin marking a destination; close-up; Adventure; A worn, leather-bound journal; cinematic
Characteristic
Shot : A close-up of an old, worn leather-bound book with a map of Europe inside. The book is lying open on a wooden table, and the map is visible in the background.
Aesthetic Score : 0.7
Mood : nostalgic, vintage, adventurous
Quality
Entropy : 6.88
Noise : 90
Prompt Clip Score : 0.31
AI Evaluation
Likelihood of AI : 0.00
Image errors : None
Lost in the Sound: A Techy Oasis
A pair of sleek black headphones take center stage, bathed in low-key lighting. The blurred background of a computer monitor, keyboard, and mouse hints at a world of possibilities, while the shallow depth of field adds a touch of mystery. This image evokes a mood of quiet focus and technological immersion.
Prompt
Minimalist: Immersive, futuristic ; A pair of headphones with a cityscape reflected in the earcups; close-up; Gaming; A dimly lit room with a computer screen in the background; cinematic
Characteristic
Shot : A pair of black headphones on a desk in front of a computer monitor and keyboard
Aesthetic Score : 0.7
Mood : dark, tech, modern
Quality
Entropy : 6.27
Noise : 77
Prompt Clip Score : 0.29
AI Evaluation
Likelihood of AI : 0.10
Image errors : No noticeable image errors
A Moment Frozen in Time: Vintage Camera Captures Serene Nostalgia
This image evokes a sense of calm and reflection. A vintage camera, perfectly in focus, sits on a weathered wooden surface, its lens seemingly gazing out at a blurry backdrop of rolling green hills and a clear blue sky. The shallow depth of field creates a nostalgic atmosphere, inviting viewers to imagine the stories captured by this timeless device.
Prompt
Minimalist: Nostalgic, adventurous ; A vintage camera with a viewfinder showing a breathtaking landscape; close-up; Tourism; A vibrant, colorful landscape in the background; cinematic
Characteristic
Shot : A vintage camera resting on a wooden surface in front of a panoramic view of rolling hills.
Aesthetic Score : 0.7
Mood : nostalgic, serene, adventurous
Quality
Entropy : 6.93
Noise : 85
Prompt Clip Score : 0.35
AI Evaluation
Likelihood of AI : 0.10
Image errors : No noticeable artifacts or errors.
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 0.3, which is considered below average. This suggests that the model didn’t accurately capture the intended camera position described in the prompt.
- Shot Analysis: The model scored 0.455, which is also below average. This indicates that the model didn’t fully understand the scene described in the prompt and didn’t create an image that accurately reflects it.
- Aesthetic Analysis: The model scored 0.06, which is considered very good. This means that the generated image closely matched the expected aesthetic style.
Overall, the model seems to be better at capturing the desired aesthetic than understanding the scene and camera position. This suggests that the model might need further training to improve its ability to interpret and translate prompts into accurate visual representations.
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://leonardo.ai