AI's Artistic Eye: Capturing Poses, But Missing the Shot with Stable-diffusion
- 9 minutes read - 1799 wordsTable of Contents
In the realm of visual storytelling, capturing the essence of a scene goes beyond simply depicting objects. It involves understanding the nuances of composition, camera angles, and the emotional impact of poses. This is where the power of AI comes into play, offering a glimpse into the future of image generation. However, as our experiment reveals, AI’s journey in mastering the art of visual storytelling is still ongoing. While it excels at capturing the desired aesthetic style, it struggles with accurately translating camera positions and shot composition. This blog post delves into the fascinating world of AI-generated images, exploring the challenges and potential of this technology in creating compelling visual narratives.
Created with: stability-ai-core
Awe-Inspiring Mountaintop View: Hikers Embrace the Vastness
Two hikers stand on a majestic mountain peak, dwarfed by the sprawling valley and snow-capped peaks below. The scene evokes a sense of peace, adventure, and inspiration, highlighting the dramatic contrast between the vastness of nature and the smallness of human figures.
Prompt
poses standing-tall: Determined, hopeful, awe-inspiring ; Lone adventurer; wide shot; Adventure; Majestic mountain range with a vast, clear sky; cinematic
Characteristic
Shot : Two hikers stand on a rocky outcropping, looking out at a panoramic view of snow-capped mountains. The sky is a clear blue.
Aesthetic Score : 0.8
Mood : serene, adventurous, majestic
Quality
Entropy : 6.77
Noise : 71
Prompt Clip Score : 0.25
AI Evaluation
Likelihood of AI : 0.10
Image errors : No significant errors.
Amidst the Ashes: A Soldier’s Solitary Stand in a War-Torn City
A lone soldier, clad in full tactical gear, stands amidst the ruins of a destroyed city. Smoke and fire billow in the background, while other soldiers are visible in the distance. The scene evokes a sense of intense drama and apocalyptic devastation, highlighting the harsh realities of war.
Prompt
poses standing-tall: Brave, defiant, resolute ; Soldier standing on a battlefield; medium shot; Heroism; Smoke and debris from a recent explosion; cinematic
Characteristic
Shot : A lone soldier stands in a war-torn landscape, with smoke and fire in the background. There are other soldiers in the distance.
Aesthetic Score : 0.6
Mood : intense, gritty, dramatic
Quality
Entropy : 6.88
Noise : 79
Prompt Clip Score : 0.28
AI Evaluation
Likelihood of AI : 0.70
Image errors : There are slight blurring and softness to the subject and background. This might be the original artistic intent but it does make the image less sharp and less realistic.
Neon Nights: Young Men Celebrate in a Burst of Energy
A group of young men revel in the moment, their raised hands and the vibrant glow of neon lights capturing the excitement and joy of their celebration. The dimly lit room adds to the atmosphere, creating a sense of intimacy and shared experience.
Prompt
poses standing-tall: Joyful, triumphant, celebratory ; Group of friends celebrating a victory in a video game; close-up; Gaming; Neon lights and glowing screens of a gaming setup; cinematic
Characteristic
Shot : A group of young men are celebrating in a dimly lit room with neon lights. They are all smiling and raising their hands in the air.
Aesthetic Score : 0.6
Mood : joyful, energetic, celebratory
Quality
Entropy : 6.38
Noise : 73
Prompt Clip Score : 0.32
AI Evaluation
Likelihood of AI : 0.20
Image errors : There are some minor artifacts in the image, particularly around the edges of the subjects’ bodies.
A Moment of Solitude on the Edge of the World
A lone figure stands on a windswept cliff, gazing out at the endless expanse of the ocean. The dramatic landscape of green hills and rocky cliffs creates a sense of awe and wonder, while the man’s small figure emphasizes the vastness of nature. This serene and contemplative scene evokes a sense of adventure and the desire to explore the unknown.
Prompt
poses standing-tall: Awe-struck, contemplative, peaceful ; Tourist standing on a cliff overlooking a breathtaking view; long shot; Tourism; Scenic landscape with rolling hills and a sparkling ocean; cinematic
Characteristic
Shot : A lone figure stands on a cliff overlooking the ocean, with lush green hills and a blue sky in the background.
Aesthetic Score : 0.7
Mood : serene, contemplative, vast
Quality
Entropy : 6.76
Noise : 83
Prompt Clip Score : 0.27
AI Evaluation
Likelihood of AI : 0.20
Image errors : No noticeable artifacts or errors.
Silhouettes of Love Against a Sunset Sky
A couple stands silhouetted on a ship’s deck, their love story unfolding against the backdrop of a breathtaking sunset. The scene evokes a sense of romance, serenity, and hope, with the silhouette adding an element of mystery and intimacy.
Prompt
poses standing-tall: Romantic, adventurous, hopeful ; Couple standing on a ship’s deck; medium shot; Travel; Sunset over the ocean with a silhouette of a distant island; cinematic
Characteristic
Shot : A couple silhouetted against a sunset on a ship’s deck.
Aesthetic Score : 0.7
Mood : romantic, peaceful, hopeful
Quality
Entropy : 6.71
Noise : 63
Prompt Clip Score : 0.36
AI Evaluation
Likelihood of AI : 0.10
Image errors : No noticeable errors or artifacts.
Fierce and Focused: Dancers Command the Stage Under Spotlights
A group of female dancers exudes confidence and energy as they perform under bright spotlights. The dramatic lighting and smoky atmosphere create a captivating visual, highlighting their powerful poses and expressions.
Prompt
poses standing-tall: Energetic, passionate, expressive ; Group of dancers performing on a stage; wide shot; Groups; Bright stage lights and a cheering audience; cinematic
Characteristic
Shot : A group of female dancers are posing on a stage. They are wearing black tops and pants or shorts, and some have gold accents. The stage is lit by spotlights, which create a dramatic effect.
Aesthetic Score : 0.7
Mood : powerful, confident, energetic
Quality
Entropy : 6.53
Noise : 70
Prompt Clip Score : 0.23
AI Evaluation
Likelihood of AI : 0.10
Image errors : The lighting is a bit uneven, and some of the dancers are slightly blurred in the background. The background is a bit cluttered with out-of-focus audience members.
A Moment of Solitude on the Moon
An astronaut stands alone on the lunar surface, bathed in the ethereal glow of a full moon. The vastness of space and the astronaut’s isolation create a sense of awe and wonder, emphasizing the dramatic scale of the universe.
Prompt
poses standing-tall: Awe-inspiring, futuristic, surreal ; Astronaut standing on the surface of the moon; long shot; Adventure; Cratered lunar landscape with Earth in the distance; cinematic
Characteristic
Shot : An astronaut standing on the surface of the moon, with a large blue moon in the background.
Aesthetic Score : 0.7
Mood : solitude, mystery, wonder
Quality
Entropy : 5.90
Noise : 70
Prompt Clip Score : 0.30
AI Evaluation
Likelihood of AI : 0.80
Image errors : The lunar surface texture appears slightly artificial. Some of the lighting seems too uniform.
Firefighter Braves Blazing Inferno
A dramatic image captures the intensity of a fire as a firefighter in full gear stands defiantly against a backdrop of billowing smoke and flames. The scene evokes a sense of danger and somber reflection on the bravery of those who face such perils.
Prompt
poses standing-tall: Brave, determined, selfless ; Firefighter standing in front of a burning building; medium shot; Heroism; Flames and smoke billowing from the building; cinematic
Characteristic
Shot : A firefighter stands in front of a burning building, with the flames and smoke billowing in the background.
Aesthetic Score : 0.6
Mood : dramatic, intense, somber
Quality
Entropy : 6.78
Noise : 75
Prompt Clip Score : 0.29
AI Evaluation
Likelihood of AI : 0.20
Image errors : No noticeable errors in the image.
Champion’s Smile: A Moment of Triumph Captured
A joyous celebration unfolds as a man, clad in black, raises a golden trophy high above his head. Surrounded by a cheering crowd, his triumphant smile radiates pure joy and accomplishment. This image captures the essence of victory, a moment etched in time.
Prompt
poses standing-tall: Triumphant, proud, accomplished ; Gamer holding a trophy after winning a tournament; close-up; Gaming; Crowd cheering and flashing cameras; cinematic
Characteristic
Shot : A man is holding a golden trophy and smiling as he poses with the audience behind him. It is likely an awards ceremony or a gaming tournament.
Aesthetic Score : 0.7
Mood : joyful, celebratory, triumphant
Quality
Entropy : 6.42
Noise : 66
Prompt Clip Score : 0.26
AI Evaluation
Likelihood of AI : 0.10
Image errors : No significant errors detected, except for some minor noise in the background
Conquering the Peak: A Moment of Joy and Wonder
Four friends stand triumphant on a snow-covered mountain peak, their faces lit with joy as they take in the breathtaking panorama of snow-capped mountains. The vastness of the landscape inspires awe, while the clear blue sky and pristine white snow evoke a sense of serenity and peace. This is a moment of adventure, connection, and pure exhilaration.
Prompt
poses standing-tall: Joyful, united, adventurous ; Family standing on a mountain peak; wide shot; Travel; Panoramic view of snow-capped mountains and a clear blue sky; cinematic
Characteristic
Shot : Four people are standing on a snowy mountain peak, with a stunning view of the surrounding mountains in the background. The sky is a clear blue, and the sun is shining brightly.
Aesthetic Score : 0.7
Mood : joyful, adventurous, scenic
Quality
Entropy : 6.64
Noise : 72
Prompt Clip Score : 0.32
AI Evaluation
Likelihood of AI : 0.20
Image errors : No major image errors. Some minor noise in the background due to compression.
Conclusion
The results show that the generative AI model performed well in terms of camera position and shot analysis, but struggled with aesthetic analysis. Here’s a breakdown:
- Camera Position: The model scored 0.4, which is considered below average. This suggests that the model didn’t accurately capture the intended camera positions described in the prompt.
- Shot Analysis: The model scored 0.425, also below average. This indicates that the model didn’t fully understand the scene described in the prompt and didn’t create the expected shot composition.
- Aesthetic Analysis: The model scored 0.1, which is considered very good. This means that the generated image closely matched the desired aesthetic style.
Overall, the model seems to be better at capturing the desired aesthetic style than understanding the camera positions and shot composition. This suggests that the model might need further training to improve its ability to interpret and translate complex visual descriptions into images.