AI's Pride Parade: A Colorful Journey with Mixed Results with Freepik
- 9 minutes read - 1840 wordsTable of Contents
The world of AI is rapidly evolving, with impressive advancements in image generation. However, capturing the nuances of human emotion and artistic expression remains a challenge. This blog post delves into a case study where an AI model was tasked with generating images of Pride celebrations, showcasing the limitations of current AI technology in accurately depicting the vibrant spirit and emotional depth of these events. We’ll explore the model’s performance in terms of camera position, shot analysis, and aesthetic analysis, highlighting the areas where AI needs improvement to truly capture the essence of human experience.
Created with: freepik
A Moment of Joy and Celebration at Pride
A young woman beams with happiness as confetti falls around her at a vibrant Pride event. The scene captures the spirit of joy, hope, and celebration that fills the air, with rainbow flags waving proudly in the background.
Prompt
facial-expressions Pride: Joyful, confident, celebratory ; A single person; eye-level; Single Persons; A bustling Pride parade with rainbow flags and confetti; cinematic
Characteristic
Shot : A young woman is smiling brightly, looking up at something off-camera, in a crowd of people holding rainbow pride flags. Confetti is falling around her.
Aesthetic Score : 0.8
Mood : joyful, celebratory, hopeful
Quality
Entropy : 6.66
Noise : 60
Prompt Clip Score : 0.23
AI Evaluation
Likelihood of AI : 0.20
Image errors : There are some minor artifacts in the image, particularly around the woman’s hair. There is a slight blur in the image, but it is not distracting.
Pride Flag Flies High, Hope Shines Bright
A young woman radiates joy and hope as she holds a rainbow pride flag amidst a cheering crowd. The vibrant scene captures the spirit of celebration and unity, with the woman’s dramatic expression adding a powerful touch of optimism.
Prompt
facial-expressions Pride: Empowered, defiant, hopeful ; A person holding a rainbow flag high; eye-level; Single Persons; A crowd of people at a Pride rally; cinematic
Characteristic
Shot : A crowd of people are holding rainbow flags at a pride celebration. The focus is on a woman with a bright smile and long hair who is looking up at a flag.
Aesthetic Score : 0.7
Mood : joyful, hopeful, celebratory
Quality
Entropy : 6.80
Noise : 60
Prompt Clip Score : 0.22
AI Evaluation
Likelihood of AI : 0.10
Image errors : The image is slightly out of focus. The woman’s hair is slightly blurred in some areas.
Hope Takes Flight: Superhero Stands Tall Against the Cityscape
A powerful image of a superhero, clad in vibrant colors and a flowing rainbow cape, stands confidently on a rooftop overlooking a sprawling city. The wind whips her cape, creating a sense of dynamic energy and determination. This scene evokes a feeling of hope and resilience, as the superhero gazes towards the sky, ready to face whatever challenges lie ahead.
Prompt
facial-expressions Pride: Powerful, inspiring, hopeful ; A superhero in a rainbow costume; eye-level; Heroes; A cityscape with a Pride flag flying in the background; cinematic
Characteristic
Shot : A woman dressed as a superhero, with a rainbow cape, stands on a rooftop overlooking a city skyline.
Aesthetic Score : 0.7
Mood : powerful, hopeful, empowering
Quality
Entropy : 6.86
Noise : 58
Prompt Clip Score : 0.26
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image has some minor artifacts in the background, particularly in the buildings, which appear slightly blurry.
Lost in the Music: A Moment of Pure Joy at the Concert
A young woman’s infectious laughter and upward gaze capture the vibrant energy of a crowded concert venue. Her joy is palpable, drawing the viewer into the heart of the lively atmosphere.
Prompt
facial-expressions Pride: Joyful, carefree, celebratory ; A group of people dancing in a club; eye-level; Normal People; A brightly lit dance floor with rainbow lights; cinematic
Characteristic
Shot : A young woman is laughing excitedly in a crowded concert venue with colorful lights in the background, captured from a low angle perspective.
Aesthetic Score : 0.7
Mood : joyful, vibrant, energetic
Quality
Entropy : 6.87
Noise : 63
Prompt Clip Score : 0.25
AI Evaluation
Likelihood of AI : 0.20
Image errors : Some noise in the background and minor blurriness in the edges.
Love Wins: Two Women Walk Hand-in-Hand Down Rainbow Street
A joyous celebration of LGBTQ+ pride, this image captures two women walking hand-in-hand down a street painted with vibrant rainbow stripes. Surrounded by a cheering crowd and a rainbow flag waving in the background, the scene radiates hope, optimism, and the power of love and acceptance.
Prompt
facial-expressions Pride: Loving, peaceful, accepting ; A couple holding hands and walking down the street; eye-level; Normal People; A quiet, residential street with rainbow flags on display; cinematic
Characteristic
Shot : Two women walking hand-in-hand on a rainbow crosswalk, surrounded by a crowd of people during a pride parade, looking happy and in love.
Aesthetic Score : 0.7
Mood : joyful, celebratory, loving
Quality
Entropy : 6.80
Noise : 70
Prompt Clip Score : 0.26
AI Evaluation
Likelihood of AI : 0.20
Image errors : No significant image errors.
Gamer Girl Vibes: Pink Hair, Bright Lights, and Focused Play
This image captures the energy and excitement of a young woman fully immersed in her video game. Her pink and purple hair, bright surroundings, and focused expression create a vibrant and playful mood. The multiple screens in the background hint at a world of digital adventures waiting to be explored.
Prompt
facial-expressions Pride: Fun, playful, inclusive ; A gamer playing a video game with rainbow-themed characters; eye-level; Gamer; A brightly lit gaming room with posters of LGBTQ+ characters; cinematic
Characteristic
Shot : A young woman with pink and blue hair is playing a video game, wearing headphones. The background is a brightly colored room with rainbow decorations.
Aesthetic Score : 0.7
Mood : focused, playful, colorful
Quality
Entropy : 6.92
Noise : 52
Prompt Clip Score : 0.31
AI Evaluation
Likelihood of AI : 0.10
Image errors : The image is slightly blurry, which could be due to camera shake. The lighting is a bit uneven, creating some harsh shadows.
A Silent Cry for Change: One Woman’s Message Echoes Through the Crowd
A young woman, her face obscured by a sign reading ‘Tu Vif Adjante Fuve,’ stands at the heart of a vibrant protest. The blurred background of the crowd emphasizes the power of her message, conveying a sense of hope and determination in the face of adversity.
Prompt
facial-expressions Pride: Determined, hopeful, powerful ; A person holding a sign with a message of acceptance; eye-level; Single Persons; A crowd of people at a Pride protest; cinematic
Characteristic
Shot : A person is holding a rainbow-colored sign with the text ‘Tu Vief Adianthe Live’ in front of their face at a protest, the crowd is blurry in the background.
Aesthetic Score : 0.6
Mood : intense, passionate, hopeful
Quality
Entropy : 6.75
Noise : 59
Prompt Clip Score : 0.20
AI Evaluation
Likelihood of AI : 0.00
Image errors : The image has some noise, especially in the background. The sign is slightly out of focus.
Friends Gather for a Night of Laughter and Joy
A group of friends share smiles and laughter, capturing the essence of a fun and celebratory gathering. The warm atmosphere and genuine connection radiate through the image, evoking a sense of happiness and camaraderie.
Prompt
facial-expressions Pride: Joyful, celebratory, inclusive ; A group of friends celebrating at a Pride party; eye-level; Normal People; A brightly decorated room with rainbow decorations; cinematic
Characteristic
Shot : A group of young adults are laughing and smiling at a party, most likely a birthday party.
Aesthetic Score : 0.7
Mood : joyful, happy, celebratory
Quality
Entropy : 6.86
Noise : 62
Prompt Clip Score : 0.30
AI Evaluation
Likelihood of AI : 0.10
Image errors : Some minor noise is present in the image, particularly in the background, and some minor chromatic aberration is noticeable in the edges of the image.
A Rainbow of Hope: Capturing the Joy of Pride
This close-up portrait captures the spirit of pride, with a young woman gazing upwards, her rainbow headband a symbol of celebration and hope. The image evokes a sense of anticipation and wonder, reflecting the optimistic mood of the event.
Prompt
facial-expressions Pride: Awe, inspiration, hope ; A person looking out at a Pride parade with a sense of wonder; eye-level; Single Persons; A vibrant parade with colorful floats and music; cinematic
Characteristic
Shot : A close-up portrait of a young woman with short brown hair wearing a rainbow headband and looking upwards in a crowd of people. The background is blurred, suggesting a public gathering.
Aesthetic Score : 0.7
Mood : hopeful, determined, celebratory
Quality
Entropy : 6.76
Noise : 60
Prompt Clip Score : 0.23
AI Evaluation
Likelihood of AI : 0.10
Image errors : The image has some slight imperfections in the sharpness, likely due to the blurred background. The color saturation is also slightly high.
Rainbow Hair, Focused Mind: Gamer Girl in the Zone
A young woman with vibrant rainbow hair is fully immersed in her gaming world, headphones on, eyes glued to the screen. The colorful lighting and dynamic scene capture the energy and focus of a dedicated gamer.
Prompt
facial-expressions Pride: Creative, playful, inclusive ; A gamer creating a rainbow-themed character in a video game; eye-level; Gamer; A computer screen with a character creation menu; cinematic
Characteristic
Shot : A young woman with colorful hair sits at a computer desk with her headphones on, looking intently at the screen.
Aesthetic Score : 0.6
Mood : focused, playful, techy
Quality
Entropy : 6.80
Noise : 61
Prompt Clip Score : 0.27
AI Evaluation
Likelihood of AI : 0.20
Image errors : No major artifacts or errors visible.
Conclusion
The analysis shows that the generative AI model performed okay in terms of camera position and shot analysis, but not so well in terms of aesthetic analysis. Here’s a breakdown:
- Camera Position: The model scored 0.15, which is below the “good” range of 0.5 to 0.75. This suggests that the model didn’t quite capture the intended camera positions described in the prompt.
- Shot Analysis: The model scored 0.625, which falls within the “good” range. This indicates that the model was able to understand the scene in the prompt reasonably well, but could be better.
- Aesthetic Analysis: The model scored 0.03, which is far from the “very good” range of -0.2 to 0.1. This means the generated image’s aesthetic deviated significantly from the expected aesthetic described in the prompt.
Overall, the model needs improvement in its ability to accurately interpret and translate camera positions and aesthetic preferences from the prompt into the generated image.
Sources:
- https://dramaresource.com/storytelling/
- https://seedsoftellers.eu/resources/the-body-language-for-young-tellers/
- https://digitalcollections.sit.edu/cgi/viewcontent.cgi?article=1288&context=sandanona&filename=1&type=additional
- https://citeseerx.ist.psu.edu/document?doi=7f842882e9bb1fa2c0e96939bc8d2c37e34e17c0&repid=rep1&type=pdf
- https://www.twinkl.co.uk/search?q=drama+facial+expression
- https://www.freepik.com