AI's Artistic Journey: Capturing Poses, But Missing the Mark on Camera Angles with Dall-e-3
- 9 minutes read - 1851 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 perfect accuracy in replicating specific details, like camera angles, remains a challenge. This blog post delves into the results of an experiment where a generative AI model was tasked with creating images based on detailed scene descriptions, highlighting its strengths and weaknesses in capturing the essence of a scene.
Created with: dall-e-3
Silhouetted Against the Sunset: A Hiker’s Moment of Awe
A solitary hiker stands on a mountain peak, their silhouette stark against the fiery sunset. The vast valley below is shrouded in mist, creating a scene of breathtaking serenity and inspiration. This image captures the awe-inspiring beauty of nature and the hopeful spirit of adventure.
Prompt
poses leaning-back: epic, contemplative ; A lone adventurer, silhouetted against a setting sun; wide shot; adventure; vast, rugged mountain range; cinematic
Characteristic
Shot : A lone hiker stands on a rocky outcrop, silhouetted against a fiery sunrise over a majestic mountain range. The sun’s rays pierce through the mist, illuminating the scene in a golden glow.
Aesthetic Score : 0.7
Mood : serene, inspiring, adventurous
Quality
Entropy : 6.25
Noise : 81
Prompt Clip Score : 0.26
AI Evaluation
Likelihood of AI : 0.60
Image errors : The sun rays appear overly digital and lack natural variation. The hiker’s silhouette is slightly blurred, and the mountain range in the background is slightly overexposed.
Soaring Above the City: A Superhero’s Nighttime Flight
A powerful and hopeful image captures a female superhero silhouetted against the glittering cityscape, evoking a sense of heroism and strength. The dramatic lighting and composition create a sense of awe and wonder, leaving viewers inspired by the superhero’s unwavering spirit.
Prompt
poses leaning-back: triumphant, powerful ; A superhero, cape billowing in the wind, looking down at a city skyline; medium shot; heroism; bustling cityscape; cinematic
Characteristic
Shot : A female superhero with a rainbow cape flying over a nighttime cityscape
Aesthetic Score : 0.7
Mood : powerful, inspiring, hopeful
Quality
Entropy : 6.80
Noise : 111
Prompt Clip Score : 0.21
AI Evaluation
Likelihood of AI : 0.90
Image errors : The edges of the city buildings are slightly blurry and the lighting looks a bit artificial.
Sunset Laughter on a Tropical Beach
Six friends bask in the golden glow of a sunset on a pristine beach, their laughter echoing through the air. Palm trees sway gently in the breeze, creating a picture-perfect tropical paradise. This joyful scene captures the essence of carefree summer fun.
Prompt
poses leaning-back: joyful, carefree ; A group of friends, laughing and relaxing on a beach, watching the sunset; wide shot; tourism; tropical beach with palm trees; cinematic
Characteristic
Shot : A group of friends are sitting on a beach at sunset, laughing and enjoying each other’s company. The scene is warm and inviting, with a beautiful sunset in the background.
Aesthetic Score : 0.7
Mood : happy, joyful, carefree
Quality
Entropy : 6.53
Noise : 104
Prompt Clip Score : 0.32
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image is slightly overexposed, especially in the sky and water. The colors are also slightly oversaturated, making the image look slightly artificial.
Lost in the Game: A Gamer’s World in Dimly Lit Glory
A man, immersed in a heated gaming session, sits in his dimly lit room, surrounded by gaming paraphernalia and snacks. The dramatic lighting creates a sense of depth and intensity, capturing the focused energy of a true gamer.
Prompt
poses leaning-back: intense, focused ; A gamer, eyes glued to a screen, leaning back in a gaming chair, surrounded by controllers and snacks; medium shot; gaming; dimly lit room with neon lights; cinematic
Characteristic
Shot : A young man is sitting in a gaming chair in a dimly lit room. He is wearing headphones and holding a game controller. There are several gaming consoles and accessories on the desk in front of him, as well as snacks and drinks.
Aesthetic Score : 0.7
Mood : intense, focused, dark
Quality
Entropy : 6.68
Noise : 106
Prompt Clip Score : 0.31
AI Evaluation
Likelihood of AI : 0.90
Image errors : The image is slightly blurry, and the lighting is a bit uneven. There are also some artifacts in the background.
Lost in the Landscape: A Moment of Tranquility on a Moving Train
A woman finds solace in the passing scenery, her gaze fixed on the blur of mountains and fields. The motion creates a sense of movement and a feeling of being transported to a different place, evoking a serene and contemplative mood. This image captures the beauty of travel and the power of nature to inspire reflection.
Prompt
poses leaning-back: reflective, nostalgic ; A traveler, gazing out of a train window, watching the scenery pass by; medium shot; travel; rolling hills and fields; cinematic
Characteristic
Shot : An elderly woman sits by the window of a train, gazing out at a passing landscape of mountains and fields. The train is moving quickly, blurring the scenery into a streak of color.
Aesthetic Score : 0.8
Mood : reflective, nostalgic, serene
Quality
Entropy : 6.69
Noise : 107
Prompt Clip Score : 0.26
AI Evaluation
Likelihood of AI : 0.20
Image errors : Slight color banding is visible in the blurred landscape.
Under the Spotlight: Band Ignites the Crowd with Energetic Performance
A vibrant scene unfolds as a band takes the stage, bathed in the glow of spotlights. The energy is palpable, with the crowd cheering wildly and the band feeding off the excitement. This aerial view captures the electrifying atmosphere of a live concert, showcasing the power of music to unite and inspire.
Prompt
poses leaning-back: energetic, passionate ; A group of musicians, performing on stage, bathed in spotlights; wide shot; groups; concert stage with cheering audience; cinematic
Characteristic
Shot : A band is performing on stage in front of a large audience, with bright spotlights and cheering people
Aesthetic Score : 0.7
Mood : excitement, energy, joy
Quality
Entropy : 6.69
Noise : 100
Prompt Clip Score : 0.23
AI Evaluation
Likelihood of AI : 0.50
Image errors : Slight blurriness in the crowd and the band members, likely due to motion blur.
Solitude at Sunset’s Edge
A lone figure contemplates the vast ocean at sunset, perched precariously on a cliff overlooking rocky outcrops and a distant coastline. The warm glow of the setting sun casts a dramatic and serene mood, highlighting the man’s isolation and the awe-inspiring beauty of the natural world.
Prompt
poses leaning-back: solitary, contemplative ; A lone figure, sitting on a cliff edge, looking out at a vast ocean; medium shot; adventure; dramatic coastline with crashing waves; cinematic
Characteristic
Shot : A lone figure sits on a cliff overlooking the sea, with a rocky outcrop in the distance. The sky is cloudy and the sea is choppy.
Aesthetic Score : 0.5
Mood : serene, contemplative, dramatic
Quality
Entropy : 6.60
Noise : 109
Prompt Clip Score : 0.24
AI Evaluation
Likelihood of AI : 0.80
Image errors : The image has several artifacts, including the glow around the cliff and the soft edges of the rocks. The water also appears blurry and unrealistic.
Awe-Inspiring View: Astronauts Gaze Upon Earth’s Majesty
A breathtaking scene unfolds as astronauts, bathed in the glow of a futuristic space suit, stand in awe before the radiant Earth. The planet’s vibrant blue and green hues shimmer against the backdrop of the cosmos, evoking a sense of wonder and the vastness of space.
Prompt
poses leaning-back: awe-inspiring, majestic ; A group of astronauts, floating weightlessly in space, looking out at Earth; wide shot; heroism; Earth from space with stars in the background; cinematic
Characteristic
Shot : A group of astronauts are floating in space, with Earth in the background. The astronauts are looking at the camera, and the sun is shining brightly behind them.
Aesthetic Score : 0.7
Mood : dramatic, awe-inspiring, hopeful
Quality
Entropy : 6.78
Noise : 117
Prompt Clip Score : 0.29
AI Evaluation
Likelihood of AI : 0.90
Image errors : The image has some artifacts, such as a slight blurring around the astronauts. The Earth in the background is also slightly distorted.
Campfire Companionship: A Warm and Cozy Gathering in the Woods
A group of friends share laughter and stories around a crackling campfire, bathed in the warm glow of the flames. The scene evokes a sense of intimacy and closeness, perfect for a night under the stars.
Prompt
poses leaning-back: warm, intimate ; A family, gathered around a campfire, sharing stories and laughter; medium shot; groups; forest clearing with a crackling fire; cinematic
Characteristic
Shot : A group of friends are sitting around a campfire in a forest. The light from the fire illuminates their faces, creating a warm and inviting atmosphere.
Aesthetic Score : 0.7
Mood : cozy, warm, happy
Quality
Entropy : 6.70
Noise : 97
Prompt Clip Score : 0.28
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image has a slight amount of noise, particularly in the shadows.
Soaring Above the Clouds: A Pilot’s Perspective
Experience the breathtaking beauty of a mountain range from a helicopter pilot’s point of view. The serene landscape, coupled with the pilot’s focused expression, evokes a sense of awe, adventure, and power.
Prompt
poses leaning-back: exhilarating, adventurous ; A pilot, looking out of the cockpit window, flying over a breathtaking landscape; medium shot; travel; mountains and valleys covered in clouds; cinematic
Characteristic
Shot : A helicopter pilot is flying over a mountainous landscape covered in clouds. The pilot is looking out the window at the scene.
Aesthetic Score : 0.7
Mood : serene, adventurous, powerful
Quality
Entropy : 6.75
Noise : 100
Prompt Clip Score : 0.26
AI Evaluation
Likelihood of AI : 0.80
Image errors : The image is slightly blurry in some areas. There are also some artifacts in the clouds.
Conclusion
The results show that the generative AI model performed well in terms of understanding the scene and camera position, but struggled with the aesthetic aspect. Here’s a breakdown:
- Camera Position: The model scored 0.3, indicating it’s not very good at reacting to camera positions in the prompt. This means the generated image’s camera position significantly deviates from what was requested.
- Shot Analysis: The model scored 0.39, which is slightly better than average. This suggests the model has some understanding of the scene described in the prompt, but it’s not consistently accurate.
- Aesthetic Analysis: The model scored 0.09, which is very good. This means the generated image’s aesthetic closely matches the expected aesthetic, despite the other issues.
Overall, the model shows promise in understanding the scene and achieving the desired aesthetic, but it needs improvement in accurately interpreting camera positions.
Sources:
- https://www.writerswrite.co.za/cheat-sheets-for-writing-body-language/
- https://mads3df.wordpress.com/2013/09/04/storytelling-poses/
- https://www.pinterest.com/pegasister890/character-poses/
- https://www.youtube.com/watch?v=udky6ANxWws
- https://maven.com/articles/storytelling-techniques
- https://openai.com/index/dall-e-3/