AI's Artistic Journey: Capturing Poses, But Missing the Essence with Scenario
- 9 minutes read - 1729 wordsTable of Contents
In the realm of artificial intelligence, the ability to generate images with specific poses and aesthetics is a fascinating area of exploration. This blog post examines a case study where an AI model was tasked with creating images based on various scenarios and poses. While the model demonstrated proficiency in understanding and executing camera positions and shot composition, it struggled to achieve the desired aesthetic. This raises questions about the limitations of AI in capturing the nuances of artistic expression. We will delve into the factors contributing to this discrepancy and explore the potential of AI in artistic expression.
Created with: scenario
Amidst the Chaos, She Stands Strong
A female soldier marches forward in a desolate desert landscape, the echoes of a massive explosion reverberating behind her. The scene is tense, dramatic, and action-packed, highlighting the soldier’s unwavering determination in the face of danger.
Prompt
poses standing-in-a-row: determined, courageous, hopeful ; A group of soldiers; wide shot; heroism; a battlefield with smoke and explosions in the background; cinematic
Characteristic
Shot : A group of soldiers, including a female soldier in the foreground, are walking in a desert environment, with a large explosion or fire in the background. The scene seems to be set in a war zone or battlefield.
Aesthetic Score : 0.6
Mood : intense, dramatic, serious
Quality
Entropy : 6.81
Noise : 93
Prompt Clip Score : 0.29
AI Evaluation
Likelihood of AI : 0.80
Image errors : Slight blurriness and noise in the background. Some of the soldiers in the background appear to be slightly pixelated.
Uncharted Territory: A Journey Begins
Four adventurers stand on the precipice of discovery, their eyes fixed on a mysterious ancient structure hidden deep within the lush jungle. Sunlight filters through the canopy, casting a warm glow on their faces as they prepare to unravel the secrets that lie ahead. This image captures the essence of adventure, mystery, and hope, promising an unforgettable journey into the unknown.
Prompt
poses standing-in-a-row: excited, curious, adventurous ; A team of explorers; medium shot; adventure; a lush jungle with ancient ruins in the distance; cinematic
Characteristic
Shot : A group of four adventurers, three women and one man, standing in a lush jungle, looking up at something off-screen, perhaps a hidden temple.
Aesthetic Score : 0.7
Mood : adventurous, mysterious, hopeful
Quality
Entropy : 6.82
Noise : 101
Prompt Clip Score : 0.34
AI Evaluation
Likelihood of AI : 0.70
Image errors : The background foliage looks a bit artificial and lacks depth. The light source in the background looks artificial and slightly distracting.
Confident Gaze, Mysterious Aura: A Portrait in Neon
A captivating portrait of a young woman with long dark hair, radiating confidence and allure. The soft focus background, vibrant neon lights, and her delicate necklace create a sense of intimacy and mystery, drawing the viewer into her world.
Prompt
poses standing-in-a-row: focused, competitive, passionate ; A group of gamers; close-up shot; gaming; a brightly lit esports arena with cheering fans; cinematic
Characteristic
Shot : A young woman with a serious expression, looking directly at the camera, in front of a blurred background of two men in a dimly lit room.
Aesthetic Score : 0.8
Mood : serious, confident, determined
Quality
Entropy : 6.74
Noise : 71
Prompt Clip Score : 0.28
AI Evaluation
Likelihood of AI : 0.70
Image errors : There are minor artifacts and noise in the background, particularly around the blurred edges of the men.
Family Adventure: Capturing Joy Against Majestic Peaks
A heartwarming scene of a family of four, beaming with happiness, stands against a breathtaking mountain backdrop. The vibrant sunset sky and towering peaks create a dramatic contrast, highlighting the joy and adventure of their journey.
Prompt
poses standing-in-a-row: happy, relaxed, joyful ; A family of tourists; long shot; tourism; a breathtaking view of a mountain range with a clear blue sky; cinematic
Characteristic
Shot : A family of four is standing in front of a mountain range, the woman is holding their youngest child in her arms. The two eldest children are standing beside their parents, all smiling at the camera.
Aesthetic Score : 0.7
Mood : happy, relaxed, adventurous
Quality
Entropy : 6.73
Noise : 88
Prompt Clip Score : 0.33
AI Evaluation
Likelihood of AI : 0.30
Image errors : No visible image errors or artifacts.
Palm-Lined Path to Adventure
Four friends embark on a carefree journey along a sun-drenched dirt road, framed by swaying palm trees. The narrow perspective adds depth and scale, capturing the essence of their adventurous spirit.
Prompt
poses standing-in-a-row: free-spirited, adventurous, optimistic ; A group of backpackers; medium shot; travel; a dusty road leading to a distant village with palm trees; cinematic
Characteristic
Shot : Four friends are walking down a dirt road in a tropical landscape, surrounded by palm trees. The sunlight creates a warm and inviting atmosphere.
Aesthetic Score : 0.7
Mood : happy, adventurous, carefree
Quality
Entropy : 6.60
Noise : 96
Prompt Clip Score : 0.32
AI Evaluation
Likelihood of AI : 0.20
Image errors : No noticeable errors.
Leading with Confidence: A Moment of Hope and Elegance
A woman in a white striped shirt commands attention as she sits before a crowd of women, bathed in warm light. Her confident expression and posture, combined with the blurred background, create a sense of focus and importance, suggesting a moment of leadership and hope.
Prompt
poses standing-in-a-row: harmonious, powerful, emotional ; A choir singing in harmony; close-up shot; groups; a dimly lit stage with spotlights; cinematic
Characteristic
Shot : A woman in a white shirt stands in front of a large group of women, likely a choir, in an auditorium-like space. The woman is smiling at the camera.
Aesthetic Score : 0.7
Mood : joyful, confident, celebratory
Quality
Entropy : 6.67
Noise : 90
Prompt Clip Score : 0.28
AI Evaluation
Likelihood of AI : 0.10
Image errors : No notable artifacts or errors.
Rainbow Rhythms: A Celebration of Color and Joy
Capture the vibrant energy of a group of women dancing on stage, adorned in colorful outfits against a dazzling rainbow backdrop. This scene exudes joy, playfulness, and a captivating visual aesthetic.
Prompt
poses standing-in-a-row: energetic, synchronized, joyful ; A line of dancers; wide shot; groups; a brightly lit stage with colorful costumes; cinematic
Characteristic
Shot : A group of women in colorful costumes are dancing on a stage with a rainbow backdrop.
Aesthetic Score : 0.7
Mood : energetic, playful, joyful
Quality
Entropy : 6.74
Noise : 99
Prompt Clip Score : 0.26
AI Evaluation
Likelihood of AI : 0.10
Image errors : There is some noise in the image, particularly in the shadows.
Sunset Smiles: Friends Capture the Joy of Summer
A group of six young friends bask in the golden glow of a sunset on the beach, their smiles radiating pure happiness. The warm lighting creates a sense of joy and carefree summer vibes.
Prompt
poses standing-in-a-row: relaxed, happy, nostalgic ; A group of friends; medium shot; groups; a sunset over a beach with waves crashing in the background; cinematic
Characteristic
Shot : Group of friends posing on a beach at sunset
Aesthetic Score : 0.7
Mood : happy, carefree, summery
Quality
Entropy : 6.73
Noise : 92
Prompt Clip Score : 0.31
AI Evaluation
Likelihood of AI : 0.20
Image errors : No visible errors
The Future is Now: A Glimpse into a Cutting-Edge Lab
A confident woman in a white lab coat stands amidst a futuristic laboratory, surrounded by high-tech equipment and glowing blue displays. Her gaze invites you to explore the mysteries and possibilities of this advanced scientific environment.
Prompt
poses standing-in-a-row: focused, determined, innovative ; A team of scientists; close-up shot; groups; a laboratory with complex machinery and glowing screens; cinematic
Characteristic
Shot : A woman in a white lab coat stands in a futuristic laboratory, looking off to the side, with computer screens showing digital data in the background.
Aesthetic Score : 0.7
Mood : professional, confident, futuristic
Quality
Entropy : 6.69
Noise : 76
Prompt Clip Score : 0.25
AI Evaluation
Likelihood of AI : 0.20
Image errors : No significant artifacts or errors are visible in the image.
One Woman, One Stand: A Symbol of Hope in the Face of Protest
A woman, clad in black, stands resolute amidst a crowd of protesters, her determined expression and posture radiating strength and hope. The scene captures the raw emotion and unwavering spirit of those fighting for change.
Prompt
poses standing-in-a-row: determined, passionate, hopeful ; A group of protesters; long shot; groups; a city street with banners and signs; cinematic
Characteristic
Shot : A woman in a black coat stands in the middle of a street, surrounded by people holding signs. There are buildings in the background.
Aesthetic Score : 0.7
Mood : serious, pensive, contemplative
Quality
Entropy : 6.59
Noise : 84
Prompt Clip Score : 0.22
AI Evaluation
Likelihood of AI : 0.10
Image errors : There are some minor artifacts in the image, particularly in the background. The shadows and highlights are slightly blown out.
Conclusion
The results show that the generative AI model performed well in understanding and executing camera positions and shot composition, but struggled with achieving the desired aesthetic. Here’s a breakdown:
- Camera Position: The model scored 0.51, indicating a good understanding of the camera position specified in the prompt. This means the generated image’s camera position was fairly close to what was intended.
- Shot Analysis: The model scored 0.59, also indicating good performance in understanding the shot composition. This suggests the generated image’s shot type (e.g., close-up, wide shot) was fairly close to what was intended.
- Aesthetic Analysis: The model scored 0.05, which is considered very good in this context. This means the generated image’s aesthetic was very close to the expected aesthetic, despite the low score.
Overall: The model demonstrates a good ability to interpret and execute camera positions and shot composition. However, it seems to struggle with achieving the desired aesthetic, which could be due to factors like the complexity of the prompt or the model’s limitations.
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://www.scenario.com