AI's Artistic Eye: Capturing Aesthetics, But Struggling with Camera Shots with Dall-e-3
- 9 minutes read - 1904 wordsTable of Contents
In the realm of AI image generation, the ability to translate textual prompts into visually compelling images is a constant pursuit. One key aspect of this translation is the understanding of camera positions and shot types. These elements, often referred to as ‘camera-positions’ in the world of filmmaking, play a crucial role in conveying mood, perspective, and narrative. For example, a low-angle shot can make a character appear powerful, while a high-angle shot can make them seem vulnerable. This blog post explores the results of an experiment that tested an AI model’s ability to interpret these camera-positions and generate images accordingly.
Created with: dall-e-3
Silhouetted Against the Sunset: A Moment of Hope and Wonder
A lone figure stands on a rocky precipice, their silhouette stark against the fiery hues of a setting sun. The vast, misty valley below adds to the sense of solitude and mystery, while the dramatic lighting evokes a feeling of awe and hope.
Prompt
camera-positions Two-shot: Epic, hopeful, determined ; A lone hero, silhouetted against the setting sun; Two-shot; Heroism; A vast, desolate landscape; cinematic
Characteristic
Shot : A lone figure stands silhouetted against a vibrant sunset, overlooking a misty valley. The mountains in the background are bathed in warm golden light, adding to the dramatic feel of the scene.
Aesthetic Score : 0.7
Mood : epic, hopeful, dramatic
Quality
Entropy : 6.82
Noise : 107
Prompt Clip Score : 0.23
AI Evaluation
Likelihood of AI : 0.80
Image errors : The image exhibits a slight blurriness, especially in the background, suggesting potential processing artifacts.
Lost in Wonder: A Couple’s Romantic Encounter with a Majestic Waterfall
Two explorers stand mesmerized before a breathtaking waterfall cascading through a vibrant jungle. The scene evokes a sense of awe, adventure, and romance, captured in a dramatic composition with sunlight illuminating the cascading water.
Prompt
camera-positions Two-shot: Wonder, excitement, awe ; Two adventurers, gazing in awe at a towering waterfall; Two-shot; Adventure; Lush, tropical rainforest; cinematic
Characteristic
Shot : A couple of hikers are standing in front of a waterfall in a lush green jungle, looking up in awe.
Aesthetic Score : 0.6
Mood : wonder, awe, adventurous
Quality
Entropy : 6.62
Noise : 121
Prompt Clip Score : 0.30
AI Evaluation
Likelihood of AI : 0.70
Image errors : The waterfall looks a bit artificial and the water in the river doesn’t look entirely natural. There are a few minor artifacts around the edges of the couple’s figures.
The Glow of Competition: A Couple’s Intense Gaming Session
A young couple is locked in a fierce video game battle, their focus unwavering under the dramatic spotlight. The intensity of their competition is palpable, creating a captivating scene of focused energy and playful rivalry.
Prompt
camera-positions Two-shot: Intense, focused, competitive ; Two gamers, intensely focused on a screen, controllers in hand; Two-shot; Gaming; A dimly lit room with neon lights; cinematic
Characteristic
Shot : Two people, a man and a woman, are playing video games with controllers in their hands, focusing on the screen.
Aesthetic Score : 0.7
Mood : intense, focused, competitive
Quality
Entropy : 6.59
Noise : 89
Prompt Clip Score : 0.27
AI Evaluation
Likelihood of AI : 0.10
Image errors : The image has some slight blurriness, particularly around the edges. This could be due to compression or camera shake.
Love in Rome: Couple Captures a Moment of Joy at St. Peter’s Basilica
A young couple beams with happiness as they take a selfie in front of the majestic St. Peter’s Basilica in Rome. The iconic backdrop and their infectious joy create a picture-perfect moment of romance and travel excitement.
Prompt
camera-positions Two-shot: Happy, carefree, celebratory ; Two tourists, smiling and taking a selfie in front of a famous landmark; Two-shot; Tourism; A bustling city square; cinematic
Characteristic
Shot : A young couple is taking a selfie in front of St. Peter’s Basilica in Rome. The man is holding the camera, and the woman is smiling and looking at the camera. The background is filled with tourists and a beautiful view of the basilica.
Aesthetic Score : 0.7
Mood : joyful, romantic, touristy
Quality
Entropy : 6.48
Noise : 100
Prompt Clip Score : 0.28
AI Evaluation
Likelihood of AI : 0.10
Image errors : No visible errors or artifacts.
Love and Laughter in the Market
A young couple captures their joy and carefree spirit in a selfie amidst the bustling energy of a crowded market. Their genuine laughter radiates happiness, making this a truly heartwarming moment.
Prompt
camera-positions Two-shot: Joyful, adventurous, curious ; Two friends, sharing a laugh as they explore a foreign city; Two-shot; Travel; A vibrant, colorful street market; cinematic
Characteristic
Shot : A couple is taking a selfie in a crowded market. They are both laughing and appear to be enjoying themselves. The market is filled with colorful stalls and people, creating a lively and vibrant atmosphere.
Aesthetic Score : 0.7
Mood : joyful, carefree, vibrant
Quality
Entropy : 6.79
Noise : 101
Prompt Clip Score : 0.27
AI Evaluation
Likelihood of AI : 0.20
Image errors : No significant errors. The focus is a bit soft but it doesn’t detract from the image’s overall appeal.
Cheers to Friendship: A Warm and Inviting Moment at the Bar
Capture the joy and camaraderie of a group of friends toasting each other at a bar. The soft lighting and warm colors create a welcoming and intimate atmosphere, making this image a perfect representation of friendship and good times.
Prompt
camera-positions Two-shot: Warm, celebratory, intimate ; A group of friends, raising their glasses in a toast; Two-shot; Groups; A cozy, dimly lit pub; cinematic
Characteristic
Shot : A group of friends toasting each other at a bar with drinks in their hands, the bar is dimly lit and has a rustic and cozy vibe, with warm lighting and a wooden counter.
Aesthetic Score : 0.7
Mood : happy, social, friendly
Quality
Entropy : 6.72
Noise : 90
Prompt Clip Score : 0.26
AI Evaluation
Likelihood of AI : 0.20
Image errors : No visible artifacts or errors.
Gazing at the Unknown: Astronauts Contemplate a Distant World
Two astronauts, a man and a woman, stand silhouetted against a spacecraft window, their faces etched with a mixture of awe and contemplation as they gaze upon a distant planet. The composition evokes a sense of isolation and wonder, highlighting the vastness of space and the human desire to explore the unknown.
Prompt
camera-positions Two-shot: Serious, focused, determined ; Two astronauts, working together in a space station; Two-shot; Heroism; The vast emptiness of space; cinematic
Characteristic
Shot : Two astronauts, a man and a woman, look out a spacecraft window at a planet in the distance.
Aesthetic Score : 0.7
Mood : serious, contemplative, futuristic
Quality
Entropy : 6.51
Noise : 92
Prompt Clip Score : 0.25
AI Evaluation
Likelihood of AI : 0.90
Image errors : No obvious errors are present in the image, although the astronauts’ skin tones might be slightly unrealistic.
Lost in the Jungle: A Tale of Mystery and Adventure
Two explorers, a man and a woman, venture deep into a dense, fog-shrouded jungle. The man studies a map, while the woman communicates through a walkie-talkie, their expressions hinting at the danger that lurks within. This captivating scene evokes a sense of mystery, adventure, and suspense, promising a thrilling journey into the unknown.
Prompt
camera-positions Two-shot: Suspenseful, adventurous, determined ; Two explorers, navigating a treacherous jungle path; Two-shot; Adventure; Dense, overgrown jungle; cinematic
Characteristic
Shot : Two adventurers, a man and a woman, are navigating a dense tropical jungle. They are both wearing backpacks and have a map in hand.
Aesthetic Score : 0.6
Mood : mysterious, adventurous, suspenseful
Quality
Entropy : 6.83
Noise : 117
Prompt Clip Score : 0.27
AI Evaluation
Likelihood of AI : 0.80
Image errors : The image has some noticeable artifacts, particularly around the edges of the figures and the foliage. The fog is a bit too pronounced and looks artificial. The woman’s hand looks a bit awkward in the bottom right corner.
Victory High Five: Gamers Celebrate Triumph with Joyful Energy
Two gamers, a man and a woman, share a celebratory high five after conquering a video game challenge. The dynamic lighting and their excited expressions capture the thrill of victory and the joy of shared accomplishment.
Prompt
camera-positions Two-shot: Excited, triumphant, celebratory ; Two gamers, celebrating a victory with a high-five; Two-shot; Gaming; A brightly lit gaming room with colorful lights; cinematic
Characteristic
Shot : Two young adults, likely a couple, celebrating a victory in a video game. They are giving each other a high five in front of two monitors. The scene is lit with bright neon lights, which create a vibrant and energetic atmosphere.
Aesthetic Score : 0.7
Mood : joyful, celebratory, energetic
Quality
Entropy : 6.78
Noise : 93
Prompt Clip Score : 0.25
AI Evaluation
Likelihood of AI : 0.90
Image errors : The image appears to be slightly blurry, especially in the background. There are also some minor artifacts around the edges of the subjects.
Silhouettes of Love at Sunset
A romantic and adventurous scene unfolds as a man and woman, silhouetted against a vibrant sunset, stroll along a sandy beach. The warm colors and soft lighting create a serene and captivating atmosphere.
Prompt
camera-positions Two-shot: Peaceful, romantic, contemplative ; Two travelers, gazing out at a breathtaking sunset over the ocean; Two-shot; Travel; A serene beach with golden sand; cinematic
Characteristic
Shot : A couple is standing on a beach at sunset, the man is wearing a turban, the woman is wearing a striped shirt, the setting sun is reflecting on the water.
Aesthetic Score : 0.6
Mood : romantic, adventurous, hopeful
Quality
Entropy : 6.65
Noise : 88
Prompt Clip Score : 0.29
AI Evaluation
Likelihood of AI : 0.30
Image errors : No visible artifacts, but the focus is slightly off, some noise in the sky.
Conclusion
The results show that the generative AI model performed okay in terms of camera position and shot analysis, but very well in terms of aesthetic analysis.
Here’s a breakdown:
- Camera Position Analysis: The score of 0.2 indicates that the model’s ability to react to camera positions in the prompt is below average. A score between 0.5 and 0.75 would be considered good, and above 0.75 very good.
- Shot Analysis: The score of 0.46 suggests that the model’s understanding of the scene in the prompt is slightly below average. A score between 0.5 and 0.75 would be considered good, and above 0.75 very good.
- Aesthetic Analysis: The score of 0.02 indicates that the model produced an image with an aesthetic very close to what was expected. A score between -0.2 and 0.1 is considered very good.
Overall, the model seems to be better at capturing the desired aesthetic than accurately interpreting camera positions and scene descriptions.
Sources:
- https://www.studiobinder.com/blog/types-of-camera-shot-angles-in-film/
- https://www.learnaboutfilm.com/film-language/picture/camera-position/
- https://boords.com/blog/16-types-of-camera-shots-and-angles-with-gifs
- https://shorthand.com/the-craft/8-tips-for-great-visual-storytelling/
- https://openai.com/index/dall-e-3/