AI Captures the Essence, But Misses the Shot: A Look at Dramatic Style Generation with Leonardo-ai
- 9 minutes read - 1787 wordsTable of Contents
The dramatic style, characterized by its use of light and shadow, composition, and emotional impact, is a popular choice for photographers and filmmakers. It’s often used to create a sense of grandeur, suspense, or even tragedy. This style is particularly challenging for AI models to replicate, as it requires a deep understanding of visual composition and the ability to evoke specific emotions. This blog post delves into the results of an AI model attempting to generate images in this style, highlighting its strengths and weaknesses.
Created with: leonardo-ai
A Hiker’s Journey Through Majestic Serenity
Witness the breathtaking beauty of a lone hiker traversing a snow-capped mountain, bathed in the golden glow of the sun. The vastness of the landscape evokes a sense of awe and wonder, while the clear blue sky and pristine snow create a serene and tranquil atmosphere.
Prompt
Cinema Verité: Awe-inspiring, determined ; A lone hiker; wide shot; Adventure; Majestic mountain range with snow-capped peaks; cinematic
Characteristic
Shot : A lone hiker walks up a snowy mountain pass with a majestic mountain range in the background.
Aesthetic Score : 0.8
Mood : serene, adventurous, inspirational
Quality
Entropy : 6.59
Noise : 89
Prompt Clip Score : 0.30
AI Evaluation
Likelihood of AI : 0.10
Image errors : Slight noise in the shadows, likely due to compression or low light conditions.
Firefighter Bravely Battles Blaze in Dramatic Scene
A firefighter in full gear confronts a raging inferno, spraying water from a hose at a building engulfed in flames. The image captures the intensity and danger of the situation, showcasing the heroism of those who risk their lives to protect others.
Prompt
Cinema Verité: Urgent, heroic, chaotic ; A firefighter battling a blaze; close-up; Heroism; Smoke and flames engulfing a building; cinematic
Characteristic
Shot : A firefighter is spraying water on a burning building, the fire is intense and there is a lot of smoke.
Aesthetic Score : 0.6
Mood : intense, dramatic, heroic
Quality
Entropy : 6.64
Noise : 87
Prompt Clip Score : 0.28
AI Evaluation
Likelihood of AI : 0.10
Image errors : The image is well-composed and the colours are accurate.
The Controller in Their Grip: A Moment of Intense Focus
A close-up shot captures the hand of a gamer gripping their controller, the blurry background hinting at the intensity of the game. The lighting and composition draw the viewer’s eye to the controller, emphasizing the player’s focus and determination.
Prompt
Cinema Verité: Intense, focused, exhilarating ; A gamer’s hands furiously manipulating a controller; close-up; Gaming; Blurred background of a computer screen displaying a fast-paced game; cinematic
Characteristic
Shot : A person is using a gaming controller with a blurred out monitor in the background.
Aesthetic Score : 0.5
Mood : focused, intense, serious
Quality
Entropy : 6.60
Noise : 76
Prompt Clip Score : 0.31
AI Evaluation
Likelihood of AI : 0.20
Image errors : There is some slight noise in the image, particularly in the background. The monitor screen appears blurry.
Family Fun in the City of Lights
A heartwarming moment captured as a family enjoys a day out in a European city. The father’s laughter and the youngest child’s curious gaze add a touch of playful charm to this candid photo, set against the backdrop of a grand architectural masterpiece.
Prompt
Cinema Verité: Joyful, celebratory, memorable ; A family laughing and taking photos in front of a famous landmark; medium shot; Tourism; Vibrant cityscape with iconic architecture; cinematic
Characteristic
Shot : A family of four is standing in front of a large, ornate building with a dome. They are all smiling and laughing, and the children are holding phones.
Aesthetic Score : 0.7
Mood : happy, joyful, touristy
Quality
Entropy : 6.80
Noise : 97
Prompt Clip Score : 0.30
AI Evaluation
Likelihood of AI : 0.10
Image errors : None
Silhouetted Solitude: A Moment of Tranquility Above the City
A lone figure finds peace on a rocky outcrop, gazing out at the city skyline as the sun sets. The dramatic silhouette against the vast cityscape evokes a sense of isolation and contemplation, capturing a moment of tranquil beauty.
Prompt
Cinema Verité: Tranquil, contemplative, awe-inspiring ; A backpacker gazing out at a breathtaking sunset over a foreign city; long shot; Travel; Silhouettes of buildings against a fiery sky; cinematic
Characteristic
Shot : A lone figure sits on a hilltop overlooking a cityscape at sunset, with a bright orange sky and a vibrant red sun.
Aesthetic Score : 0.8
Mood : tranquil, contemplative, peaceful
Quality
Entropy : 6.73
Noise : 94
Prompt Clip Score : 0.31
AI Evaluation
Likelihood of AI : 0.20
Image errors : No major image artifacts or errors, but some slight compression artifacts are visible.
A Moment of Wonder: Butterfly Lands on Child’s Hand
Capture the gentle beauty of a butterfly landing on a child’s hand in a field of wildflowers. The soft lighting and blurred background create a peaceful and delicate mood, evoking a sense of wonder and delight.
Prompt
Cinema Verité: Innocent, curious, heartwarming ; A young child’s hand reaching out to touch a butterfly; close-up; Family; Lush green meadow with wildflowers; cinematic
Characteristic
Shot : A child’s hand gently holds a butterfly while another hand reaches out toward the insect. The scene is set in a lush field of wildflowers and green grass.
Aesthetic Score : 0.7
Mood : gentle, peaceful, whimsical
Quality
Entropy : 6.74
Noise : 88
Prompt Clip Score : 0.32
AI Evaluation
Likelihood of AI : 0.10
Image errors : The image is slightly out of focus in certain areas, specifically the butterfly’s wings and the surrounding flowers. This might be due to the shallow depth of field.
The Roar of the Crowd: A Stadium Erupts in Excitement
A sea of faces, illuminated by stadium lights, erupts in cheers. The energy is palpable, the excitement contagious. This image captures the raw emotion of a crowd united in their passion, a moment of pure joy and anticipation.
Prompt
Cinema Verité: Energetic, passionate, communal ; A group of friends cheering on their favorite team at a sporting event; wide shot; Heroism; Stadium filled with excited fans; cinematic
Characteristic
Shot : A large crowd of people cheering at a sporting event or concert, with a stadium in the background.
Aesthetic Score : 0.7
Mood : excitement, joy, passion
Quality
Entropy : 6.70
Noise : 97
Prompt Clip Score : 0.33
AI Evaluation
Likelihood of AI : 0.20
Image errors : There are no visible artifacts or errors in the image.
A Symphony of Colors and Spices: Life on a Bustling Indian Market Street
Immerse yourself in the vibrant energy of an Indian market, where the air is thick with the aroma of spices and the streets are alive with activity. This captivating scene captures the depth and perspective of a narrow street, leading your eye towards the distant end, where the bustling life of the market continues.
Prompt
Cinema Verité: Adventurous, curious, vibrant ; A couple exploring a bustling market in a foreign country; medium shot; Travel; Colorful stalls overflowing with exotic goods; cinematic
Characteristic
Shot : A bustling street market in India with vibrant colors and textures. People are walking through the market, buying and selling goods.
Aesthetic Score : 0.7
Mood : exotic, lively, vibrant
Quality
Entropy : 6.83
Noise : 109
Prompt Clip Score : 0.31
AI Evaluation
Likelihood of AI : 0.10
Image errors : The image has some minor artifacts, such as the light flares in the background. There is also some slight noise in the image, but it is not too noticeable.
Lost in Thought: A Man’s Pensive Gaze in the Blue Light
A close-up portrait captures a man’s face, bathed in the blue glow of a computer screen. His downcast eyes and serious expression suggest deep contemplation, creating an atmosphere of mystery and intrigue in the dimly lit room.
Prompt
Cinema Verité: Focused, intense, absorbed ; A gamer’s face lit by the glow of a computer screen, eyes glued to the action; close-up; Gaming; Dark room with only the screen illuminating the face; cinematic
Characteristic
Shot : A man is sitting in a dark room, looking at a computer screen. The screen is lit up with a blue light, casting a glow on his face. The man’s expression is serious and thoughtful.
Aesthetic Score : 0.6
Mood : serious, contemplative, introspective
Quality
Entropy : 5.32
Noise : 71
Prompt Clip Score : 0.32
AI Evaluation
Likelihood of AI : 0.20
Image errors : There is some noise in the image, particularly in the shadows.
Campfire Cozy Under a Starry Sky
A warm and inviting scene of three friends gathered around a crackling campfire, bathed in the glow of the flames against the backdrop of a star-filled night. The tent in the distance suggests a night of adventure and relaxation under the open sky.
Prompt
Cinema Verité: Warm, intimate, nostalgic ; A family sharing a meal together around a campfire; medium shot; Family; Campsite under a starry night sky; cinematic
Characteristic
Shot : A group of four friends are gathered around a campfire under a starry night sky. There are two tents in the background, suggesting a camping trip. The fire is blazing brightly, illuminating the faces of the friends. There is a sense of warmth and camaraderie.
Aesthetic Score : 0.7
Mood : cozy, cheerful, adventurous
Quality
Entropy : 6.09
Noise : 91
Prompt Clip Score : 0.34
AI Evaluation
Likelihood of AI : 0.20
Image errors : No obvious artifacts or errors. The image appears to be well-exposed and balanced.
Conclusion
The results indicate that the generative AI model performed well in terms of understanding the scene and camera position, but struggled with achieving the desired aesthetic. Here’s a breakdown:
- Camera Position: The model scored a 0.3, which is considered below average. This suggests that the model didn’t accurately translate the camera position described in the prompt into the generated image.
- Shot Analysis: The model scored a 0.5, which is considered average. This means the model was able to understand the scene in the prompt to a reasonable degree, but there’s room for improvement.
- Aesthetic Analysis: The model scored a 0.08, which is considered very good. This indicates that the generated image closely matched the expected aesthetic, despite the other shortcomings.
Overall, the model shows promise in understanding the scene and achieving the desired aesthetic, but needs improvement in accurately translating camera positions.
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