AI's Dolly Shot: A Step Closer to Cinematic Storytelling with Ideogram-v2-turbo
- 9 minutes read - 1707 words
Table of Contents
The dolly shot, a cinematic technique where the camera moves smoothly along a track, is a powerful tool for creating dynamic and engaging visuals. It can be used to follow a character, reveal a new environment, or simply add a sense of movement to a scene. In this experiment, we used generative AI to create dolly shots for a variety of scenes, exploring the AI’s ability to understand and implement camera positions and shot composition. The results show that the AI is capable of creating shots that are technically sound, but still needs improvement in achieving the desired aesthetic.
Created with: ideogram-v2-turbo
A Soldier’s Resolve Amidst the Ruins
A powerful image captures the grim determination of a soldier standing in a war-torn cityscape. The stark contrast between his focused expression and the desolate background creates a palpable sense of tension and foreboding.
Prompt
camera-positions Dolly shot: intense, determined ; A lone soldier; dolly shot; heroism; a battlefield littered with debris and smoke; cinematic
Characteristic
Shot : A man in military uniform stands in a war-torn cityscape, looking over his shoulder with a determined expression. The background is filled with debris and destruction.
Aesthetic Score : 0.6
Mood : tense, dramatic, serious
Quality
Entropy : 6.88
Noise : 95
Prompt Clip Score : 0.29
AI Evaluation
Likelihood of AI : 0.20
Image errors : Some slight noise and grain are visible in the image.
Adventure Awaits: Explorers Charge Towards Mayan Mystery
A group of intrepid explorers, clad in their gear, race through a lush jungle towards a majestic Mayan pyramid. Their smiles and laughter capture the thrill of discovery and the joy of adventure. This scene evokes a sense of excitement and wonder, promising an unforgettable journey.
Prompt
camera-positions Dolly shot: excited, adventurous ; A group of explorers; dolly shot; adventure; a dense jungle with ancient ruins in the distance; cinematic
Characteristic
Shot : A group of people are running through a jungle, with a Mayan pyramid in the background. They are all looking at the camera, smiling and laughing, and they are wearing explorer-type clothing.
Aesthetic Score : 0.6
Mood : adventurous, exciting, playful
Quality
Entropy : 6.60
Noise : 122
Prompt Clip Score : 0.28
AI Evaluation
Likelihood of AI : 0.20
Image errors : There are some minor artifacts in the image, particularly in the shadows.
A Hand, a Mouse, and a World Beyond
A mysterious hooded figure stands against a backdrop of floating islands and a fantastical landscape. The hand, holding a sleek black gaming mouse, is sharply in focus, while the figure and background blur into a dreamlike haze. This image evokes a sense of intrigue, mystery, and futuristic cyberpunk aesthetics.
Prompt
camera-positions Dolly shot: focused, intense ; A gamer’s hands; dolly shot; gaming; entering game world; cinematic
Characteristic
Shot : A hand with a black gaming mouse in front of a hooded figure, against a background of floating islands and a fantasy landscape
Aesthetic Score : 0.6
Mood : mysterious, futuristic, cyberpunk
Quality
Entropy : 6.72
Noise : 91
Prompt Clip Score : 0.17
AI Evaluation
Likelihood of AI : 0.90
Image errors : The image has some minor artifacts, such as the floating islands appearing to be slightly distorted.
A Nostalgic Journey Through a Bustling Market
A vintage camera glides through a vibrant marketplace, capturing the blur of activity and leaving a trail of mystery in its wake. The scene evokes a sense of nostalgia and intrigue, inviting you to explore the hidden stories within the bustling crowd.
Prompt
camera-positions Dolly shot: energetic, vibrant ; A bustling marketplace; dolly shot; tourism; vibrant colors, exotic goods, and lively crowds; cinematic
Characteristic
Shot : A vintage camera on a track moving through a crowded market place. The camera is in focus and the people in the background are blurred.
Aesthetic Score : 0.7
Mood : nostalgic, busy, mysterious
Quality
Entropy : 6.77
Noise : 100
Prompt Clip Score : 0.27
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image has some slight motion blur on the people in the background.
A Family Road Trip Through Time
A vintage car cruises down a sun-drenched highway, carrying a family on a nostalgic adventure through rolling hills and lush greenery. The image evokes a sense of peace, happiness, and the freedom of the open road.
Prompt
camera-positions Dolly shot: peaceful, nostalgic ; A family driving down a scenic highway; dolly shot; travel; rolling hills, lush forests, and a clear blue sky; cinematic
Characteristic
Shot : The image shows a family driving on a highway in a vintage car. The road stretches out ahead of them, leading through a picturesque landscape of rolling hills and lush green trees. The sun is shining brightly, and the sky is a beautiful blue.
Aesthetic Score : 0.6
Mood : peaceful, nostalgic, happy
Quality
Entropy : 6.69
Noise : 61
Prompt Clip Score : 0.30
AI Evaluation
Likelihood of AI : 0.10
Image errors : The image has some minor blurriness, especially in the background. The lighting is also a bit uneven.
Tiny Hero Faces Fiery Peril
A young boy, dressed in a firefighter uniform, stands bravely before a burning building, the flames and smoke a stark contrast to his innocent face. The scene is both intense and dramatic, highlighting the courage of a child facing a perilous situation.
Prompt
camera-positions Dolly shot: brave, determined ; A young boy; dolly shot; heroism; a burning building with people trapped inside; cinematic
Characteristic
Shot : A young boy, dressed in a firefighter uniform, stands in front of a burning building. There are people trapped in the windows of the building. The flames are visible and the smoke is rising.
Aesthetic Score : 0.6
Mood : intense, dramatic, serious
Quality
Entropy : 6.91
Noise : 113
Prompt Clip Score : 0.27
AI Evaluation
Likelihood of AI : 0.20
Image errors : There are no visible artifacts or errors in the image.
Friends Discover Wonder at the Pyramids of Giza
A group of four friends stand awestruck before the Great Pyramids of Giza, their faces alight with excitement and wonder. The image captures the thrill of adventure and the majesty of ancient Egypt, leaving viewers yearning to experience the pyramids firsthand.
Prompt
camera-positions Dolly shot: excited, adventurous ; A group of friends; dolly shot; adventure; a vast desert landscape with ancient pyramids in the distance; cinematic
Characteristic
Shot : A group of four friends is standing in front of the great pyramids of Giza, looking at something in the distance
Aesthetic Score : 0.7
Mood : happy, excited, adventurous
Quality
Entropy : 6.80
Noise : 95
Prompt Clip Score : 0.26
AI Evaluation
Likelihood of AI : 0.20
Image errors : There is no noticeable artifact or error
Escape to the Future: VR Headset Reflects Cyberpunk Cityscape
A sleek VR headset rests on a dark surface, its lenses reflecting a dazzling futuristic cityscape. The scene evokes a sense of wonder and escapism, transporting you to a world of cyberpunk possibilities.
Prompt
camera-positions Dolly shot: immersive, futuristic ; A virtual reality headset; dolly shot; gaming; a futuristic cityscape with holographic projections; cinematic
Characteristic
Shot : A VR headset lying on a dark surface with a futuristic cityscape reflected in the lenses.
Aesthetic Score : 0.8
Mood : futuristic, cyberpunk, sci-fi
Quality
Entropy : 6.62
Noise : 60
Prompt Clip Score : 0.26
AI Evaluation
Likelihood of AI : 0.90
Image errors : Slight blurriness in the reflection and some artifacts in the shadows.
Sunset Romance on the Beach
A couple strolls hand-in-hand along a sandy beach as the sun sets, casting a warm glow that creates a romantic and tranquil atmosphere. The scene evokes feelings of love, serenity, and peace.
Prompt
camera-positions Dolly shot: romantic, peaceful ; A couple walking hand-in-hand; dolly shot; tourism; a romantic sunset over a picturesque beach; cinematic
Characteristic
Shot : A couple is walking hand-in-hand along a sandy beach at sunset.
Aesthetic Score : 0.8
Mood : romantic, serene, tranquil
Quality
Entropy : 6.10
Noise : 100
Prompt Clip Score : 0.28
AI Evaluation
Likelihood of AI : 0.20
Image errors : No visible errors
The Heart of the Home: A Family Meal Filled with Joy
A heartwarming scene of a family gathered around a table, sharing a meal. The older man carving the roast, the warm lighting, and the smiles on everyone’s faces capture the essence of family togetherness and the joy of a shared experience.
Prompt
camera-positions Dolly shot: happy, heartwarming ; A family gathered around a dinner table; dolly shot; family; open world food; cinematic
Characteristic
Shot : A family is gathered around a table, enjoying a meal. An older man is carving a roast while everyone else looks on.
Aesthetic Score : 0.6
Mood : happy, warm, family
Quality
Entropy : 6.88
Noise : 96
Prompt Clip Score : 0.28
AI Evaluation
Likelihood of AI : 0.20
Image errors : No significant image errors. The colors are slightly washed out and the image is a bit blurry in the background.
Conclusion
The results show that the generative AI model performed well in understanding and implementing camera positions and shot composition, but struggled with achieving the desired aesthetic. Here’s a breakdown:
- Camera Position: The model scored 0.53, which falls within the “good” range (0.5 to 0.75). This indicates that the model was able to accurately capture the intended camera positions described in the prompt.
- Shot Analysis: The model scored 0.56, also within the “good” range. This suggests that the model understood the scene and its elements well enough to create a shot that aligns with the prompt’s description.
- Aesthetic Analysis: The model scored 0.11, which is close to the “very good” range (-0.2 to 0.1). This indicates that the generated image’s aesthetic deviated slightly from the expected aesthetic described in the prompt.
Overall, the model demonstrates a good understanding of camera positions and shot composition, but needs improvement in achieving the desired aesthetic.