AI's Artistic Journey: Capturing the Scene, Missing the Feeling with Leonardo-ai
- 9 minutes read - 1775 wordsTable of Contents
The world of AI image generation is rapidly evolving, with models capable of creating stunning visuals based on text prompts. However, achieving the desired aesthetic remains a challenge. This blog post delves into an experiment that tested the capabilities of a generative AI model in capturing the essence of a scene, exploring its strengths and weaknesses in understanding camera angles, shot composition, and aesthetic style.
Created with: leonardo-ai
A Solitary Figure Contemplates Ruin in the Setting Sun
A lone figure, cloaked in darkness, stands at the threshold of a crumbling archway. The setting sun casts a warm glow over the ruined cityscape, creating a melancholic and contemplative atmosphere. The juxtaposition of the solitary figure and the vast, ruined landscape evokes a sense of isolation and profound reflection.
Prompt
poses looking-back: Melancholy, yet hopeful ; Lone figure in a tattered cloak; wide shot; Heroism; Ruins of a fallen city bathed in the golden light of a setting sun; cinematic
Characteristic
Shot : A lone figure in a dark cloak stands in a doorway overlooking a ruined cityscape at sunset.
Aesthetic Score : 0.7
Mood : melancholy, solitude, somber
Quality
Entropy : 6.67
Noise : 103
Prompt Clip Score : 0.35
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image is slightly overexposed, causing some details in the cityscape to be washed out. There is also some noise in the shadows.
Unveiling the Secrets of the Jungle Temple
Two intrepid explorers venture deep into the lush jungle, their path leading towards an ancient temple shrouded in mystery. The air crackles with anticipation as they approach the enigmatic structure, beckoning viewers to join their adventure.
Prompt
poses looking-back: Excited, adventurous ; A group of explorers; medium shot; Adventure; Lush jungle with ancient temples in the distance; cinematic
Characteristic
Shot : Two men in hiking gear walking on a dirt path through lush green jungle toward an ancient temple in the distance.
Aesthetic Score : 0.7
Mood : serene, adventurous, nostalgic
Quality
Entropy : 6.91
Noise : 116
Prompt Clip Score : 0.24
AI Evaluation
Likelihood of AI : 0.10
Image errors : No noticeable errors.
Lost in the Code: A Young Man’s Intense Focus Under Neon Lights
A young man, shrouded in darkness and illuminated by vibrant hues, is completely absorbed in his work. Headphones on, sunglasses shielding his eyes, he types furiously on a keyboard, his concentration palpable. The scene exudes an air of mystery and intensity, leaving you wondering what secrets lie within the code he’s crafting.
Prompt
poses looking-back: Intense, focused ; A gamer’s hands on a keyboard; close-up; Gaming; Neon lights reflecting on the screen, displaying a virtual world; cinematic
Characteristic
Shot : A young man, wearing headphones and glasses, is typing on a keyboard in a dimly lit room with colorful lights in the background. The composition focuses on his hands and the keyboard.
Aesthetic Score : 0.6
Mood : focused, concentrated, intense
Quality
Entropy : 6.26
Noise : 91
Prompt Clip Score : 0.27
AI Evaluation
Likelihood of AI : 0.20
Image errors : No significant errors, but the lighting and contrast could be improved
A Moment of Solitude Amidst Majestic Peaks
A lone hiker finds peace and perspective on a snow-covered mountain peak, dwarfed by the vast and awe-inspiring mountain range. The clear blue sky and bright sunshine create a serene and adventurous atmosphere.
Prompt
poses looking-back: Awe-inspiring, peaceful ; A lone traveler standing on a mountain peak; long shot; Tourism; Breathtaking panoramic view of a snow-capped mountain range; cinematic
Characteristic
Shot : A lone hiker sits on a snow-covered mountain peak, gazing out at a breathtaking panorama of snow-capped mountains under a clear blue sky.
Aesthetic Score : 0.8
Mood : serene, awe-inspiring, majestic
Quality
Entropy : 6.74
Noise : 100
Prompt Clip Score : 0.27
AI Evaluation
Likelihood of AI : 0.10
Image errors : No noticeable errors
Sunset Serenade: A Train Journey Through the Desert
A long train glides through a vast desert landscape as the sun dips below the horizon, casting a warm glow over the scene. The tranquil atmosphere evokes a sense of nostalgia and adventure, while the dramatic lighting highlights the beauty of the train and its surroundings.
Prompt
poses looking-back: Nostalgic, adventurous ; A vintage train speeding through a desert landscape; medium shot; Travel; Sun setting over the horizon, casting long shadows; cinematic
Characteristic
Shot : A vintage train is travelling through a desert landscape at sunset. The warm light casts long shadows across the sand. The train is the focal point of the image.
Aesthetic Score : 0.7
Mood : nostalgia, solitude, adventure
Quality
Entropy : 6.84
Noise : 101
Prompt Clip Score : 0.29
AI Evaluation
Likelihood of AI : 0.20
Image errors : No visible artifacts or errors
Friendship, Laughter, and Vibrant Graffiti: A Day in the City
Three young friends stroll down a city street, their laughter echoing against a colorful graffiti wall. The scene captures the joy of friendship and the vibrant energy of urban life.
Prompt
poses looking-back: Joyful, carefree ; A group of friends laughing and talking; medium shot; Groups; A bustling city street with vibrant street art; cinematic
Characteristic
Shot : Three young adults, two women and one man, are walking down a city street, laughing. A graffiti wall is in the background.
Aesthetic Score : 0.7
Mood : happy, carefree, youthful
Quality
Entropy : 6.94
Noise : 102
Prompt Clip Score : 0.24
AI Evaluation
Likelihood of AI : 0.10
Image errors : No noticeable errors or artifacts.
A Moment of Awe: Astronaut Gazes Upon Earth’s Majesty
A lone astronaut, silhouetted against the inky blackness of space, floats in wonder as they behold the vibrant blue marble of Earth. The vastness of the universe is emphasized by the astronaut’s small figure and the distant spacecraft, a testament to humanity’s exploration of the cosmos.
Prompt
poses looking-back: Awe-inspiring, contemplative ; A lone astronaut floating in space; long shot; Heroism; Earth hanging in the distance, a blue marble against the black void; cinematic
Characteristic
Shot : An astronaut floating in space, with Earth in the background. A space station is partially visible in the upper left corner.
Aesthetic Score : 0.8
Mood : awe, wonder, isolation
Quality
Entropy : 6.43
Noise : 91
Prompt Clip Score : 0.23
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image is slightly overexposed, especially in the background, but the astronaut’s helmet is well lit.
Whitewater Rafting Adventure: Smiles, Thrills, and Rapids!
Experience the rush of whitewater rafting with this exhilarating image. Four friends navigate a turbulent river, their laughter echoing through the forest as they conquer the rapids. The scene captures the pure joy and excitement of an adventurous journey.
Prompt
poses looking-back: Thrilling, exhilarating ; A group of adventurers on a raft; medium shot; Adventure; Rapids churning whitewater, a sense of danger and excitement; cinematic
Characteristic
Shot : A group of four people are whitewater rafting down a river, they are smiling and seem to be having fun. They are wearing life jackets and helmets. The river is fast-flowing and there are rapids. The background is a lush green forest.
Aesthetic Score : 0.7
Mood : joyful, exciting, adventurous
Quality
Entropy : 6.88
Noise : 108
Prompt Clip Score : 0.26
AI Evaluation
Likelihood of AI : 0.10
Image errors : No visible image errors.
A Solitary Figure Contemplates the Vastness of the World
A lone figure stands on a mountain peak, silhouetted against a breathtaking sunset. The sprawling valley below and the distant castle create a sense of epic scale, while the figure’s solitude evokes a feeling of contemplation and wonder. This image captures the majesty of nature and the human spirit’s yearning for connection with the vastness of the world.
Prompt
poses looking-back: Triumphant, accomplished ; A gamer’s avatar standing on a virtual mountain peak; close-up; Gaming; A vast, fantastical landscape stretching out before them; cinematic
Characteristic
Shot : A lone figure stands on a mountain peak overlooking a valley with a distant castle and snowy peaks in the background. The sun is setting, casting a warm glow over the scene.
Aesthetic Score : 0.7
Mood : epic, serene, contemplative
Quality
Entropy : 6.87
Noise : 103
Prompt Clip Score : 0.28
AI Evaluation
Likelihood of AI : 0.80
Image errors : The image appears to be very slightly blurry, especially in the distance. The textures on the rocks are a bit repetitive and the lighting is a bit flat.
Sunset Romance on the Beach
A couple strolls hand-in-hand along a sandy beach as the sun dips below the horizon, casting a warm glow that evokes feelings of love and nostalgia. Their silhouettes against the sky add a touch of mystery to this serene and romantic scene.
Prompt
poses looking-back: Romantic, peaceful ; A couple walking hand-in-hand on a beach; long shot; Tourism; Sunset painting the sky in vibrant hues of orange and pink; cinematic
Characteristic
Shot : A couple is walking hand-in-hand on a sandy beach at sunset. The sky is a vibrant orange and pink, casting a warm glow on the scene.
Aesthetic Score : 0.8
Mood : romantic, serene, hopeful
Quality
Entropy : 6.64
Noise : 97
Prompt Clip Score : 0.28
AI Evaluation
Likelihood of AI : 0.10
Image errors : There are no noticeable errors or artifacts in the image.
Conclusion
The results show that the generative AI model performed well in understanding the camera position and shot composition, but struggled with the aesthetic aspect. Here’s a breakdown:
- Camera Position: The model scored 0.45, which is slightly below the “good” range of 0.5 to 0.75. This suggests that the model’s ability to accurately interpret and recreate the camera position specified in the prompt is decent, but could be improved.
- Shot Analysis: The model scored 0.505, which falls within the “good” range. This indicates that the model is capable of understanding the scene and shot type described in the prompt, and generating images that reflect this understanding.
- Aesthetic Analysis: The model scored 0.05, which is significantly lower than the “very good” range of -0.2 to 0.1. This suggests that the generated image’s aesthetic deviated considerably from the expected aesthetic based on the prompt.
Overall, the model demonstrates a good understanding of camera position and shot composition, but needs improvement in generating images that match the desired aesthetic.