AI Captures Pride's Spirit, But Struggles with Camera Angles with Flux-pro
- 9 minutes read - 1813 wordsTable of Contents
The world of AI image generation is constantly evolving, pushing the boundaries of what’s possible in visual storytelling. This experiment aimed to explore AI’s ability to capture the spirit of Pride events, focusing on the diverse scenes and emotions associated with these celebrations. The results reveal a fascinating interplay between AI’s strengths and limitations, highlighting its potential while also revealing areas for improvement. For example, the AI model struggled to accurately portray camera angles, suggesting a need for further development in understanding spatial relationships and perspective. However, the model excelled at capturing the vibrant energy and aesthetic of Pride events, demonstrating its ability to translate abstract concepts into visual representations. This exploration sheds light on the evolving landscape of AI image generation and its potential to contribute to a more inclusive and representative visual narrative.
Created with: flux-pro
Man Smiles Brightly at Pride Parade, Embracing Joy and Celebration
A man with a beard beams with happiness for the camera, surrounded by the vibrant energy of a Pride parade. The rainbow flag and cheering crowd in the background amplify the sense of joy and optimism in this heartwarming moment.
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 man smiling at the camera, surrounded by a blurry background of people and rainbow flags.
Aesthetic Score : 0.7
Mood : joyful, happy, celebratory
Quality
Entropy : 6.84
Noise : 74
Prompt Clip Score : 0.23
AI Evaluation
Likelihood of AI : 0.10
Image errors : There are no noticeable errors in the image. The colors are vibrant and the focus is sharp.
Pride Parade Joy: Woman Celebrates with Rainbow Flag
A woman radiates happiness as she waves a rainbow pride flag at a bustling parade. The blurred background adds a sense of depth and captures the celebratory atmosphere of the event.
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 young woman is holding a rainbow pride flag above her head with a crowd of people in the background. She is smiling and seems happy. The sun is shining and the day is beautiful.
Aesthetic Score : 0.7
Mood : joyful, celebratory, colorful
Quality
Entropy : 6.57
Noise : 63
Prompt Clip Score : 0.20
AI Evaluation
Likelihood of AI : 0.10
Image errors : There are some distracting elements in the background, such as the blurry person in the left middle of the image and a large blurry red object in the right side background. The image is also slightly overexposed, with a halo effect around the woman’s head.
Superman Stands for Hope, Bathed in Rainbow Light
A powerful image captures the essence of hope and heroism. Superman, clad in his iconic dark suit, stands proudly before a vibrant rainbow flag, the contrasting colors creating a dramatic visual. The mood is serious, heroic, and hopeful, suggesting a message of unity and acceptance.
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 man dressed as Superman stands in front of a rainbow flag, in an urban setting.
Aesthetic Score : 0.6
Mood : heroic, dramatic, hopeful
Quality
Entropy : 6.79
Noise : 63
Prompt Clip Score : 0.29
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image has some minor artifacts, such as graininess in the background.
Friends Celebrate with Unbridled Joy
A group of friends dance the night away at a lively party, their laughter and smiles captured in a dynamic low-angle shot. Backlighting adds a touch of drama, highlighting their infectious energy and celebratory mood.
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 group of friends are at a party, laughing and having fun. The lighting is dim and there are colorful lights in the background.
Aesthetic Score : 0.7
Mood : joyful, energetic, vibrant
Quality
Entropy : 6.50
Noise : 77
Prompt Clip Score : 0.24
AI Evaluation
Likelihood of AI : 0.20
Image errors : There are some minor artifacts around the edges of the image. The image also appears to be slightly overexposed.
Sunset Stroll: A Couple’s Intimate Moment in the City
A warm, golden light bathes a couple as they walk hand-in-hand down a city street lined with trees and flags. The soft lighting and simple composition create a sense of intimacy and connection, capturing a peaceful and romantic moment.
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 : A couple is walking down a city street on a sunny day. There are trees lining the street and flags hanging from the buildings.
Aesthetic Score : 0.6
Mood : romantic, warm, city
Quality
Entropy : 6.76
Noise : 80
Prompt Clip Score : 0.27
AI Evaluation
Likelihood of AI : 0.10
Image errors : Some blurring and noise in the background
Lost in the Game: A Moment of Immersive Focus
A young gamer, headphones on, is fully engrossed in the digital world. The lighting and composition draw you into their experience, highlighting the intensity and joy of gaming.
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 person is sitting in a gaming chair wearing headphones and looking at a monitor. The monitor is displaying an image of three people, two of whom are female. The young person appears to be playing a video game.
Aesthetic Score : 0.6
Mood : focused, relaxed, playful
Quality
Entropy : 6.91
Noise : 71
Prompt Clip Score : 0.27
AI Evaluation
Likelihood of AI : 0.30
Image errors : There are some slight artifacts in the background, but they are not very noticeable.
Provocative Protest: Woman’s Sign Sparks Tension in the Crowd
A young woman, her face etched with determination, holds a sign with a defiant message, igniting a sense of rebellion and tension within a bustling crowd. The scene is charged with a provocative energy, leaving viewers questioning the message and its impact.
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 young woman is holding a sign with a message about being the only one in the world. There are other people in the background, some are blurry and others are out of focus.
Aesthetic Score : 0.4
Mood : serious, determined, defiant
Quality
Entropy : 6.62
Noise : 74
Prompt Clip Score : 0.23
AI Evaluation
Likelihood of AI : 0.10
Image errors : No major errors but the image is slightly blurry in some areas.
Laughter and Lights: Capturing the Joy of a Party
A young woman with long brown hair radiates joy as she laughs amidst a vibrant party scene. Colorful lights illuminate the room, creating a festive atmosphere and capturing the spirit of celebration.
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 young woman is laughing and enjoying a party with friends, the scene is filled with lights and a festive atmosphere.
Aesthetic Score : 0.7
Mood : joyful, festive, vibrant
Quality
Entropy : 6.77
Noise : 69
Prompt Clip Score : 0.28
AI Evaluation
Likelihood of AI : 0.10
Image errors : Minor noise and compression artifacts in the background are visible.
Hopeful Gazes and Rainbow Flags: A Moment of Celebration and Anticipation
A young man stands amidst a vibrant crowd, his gaze fixed on something unseen, reflecting the hopeful and celebratory mood of a pride parade or rally. The rainbow flags in the background add a layer of optimism and anticipation to the scene.
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 young man with a backpack standing in a crowd of people, possibly at a pride parade, looking up at the sky with a thoughtful expression. There are rainbow flags in the background.
Aesthetic Score : 0.5
Mood : pensive, hopeful, celebratory
Quality
Entropy : 6.91
Noise : 76
Prompt Clip Score : 0.20
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image is slightly blurry, especially in the background.
Neon Dreams: A Young Gamer’s World
A vibrant scene captures the energy and focus of a young person immersed in their digital world. Neon lights illuminate their rainbow shirt as they engage with online content, creating a playful and energetic atmosphere.
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 child wearing headphones, illuminated with a rainbow light, sitting in front of a computer screen.
Aesthetic Score : 0.6
Mood : playful, hopeful, curious
Quality
Entropy : 6.93
Noise : 69
Prompt Clip Score : 0.20
AI Evaluation
Likelihood of AI : 0.30
Image errors : The image is slightly blurry, and there’s a slight noise reduction artifact around the child’s head.
Conclusion
The results show that the generative AI model performed well in understanding the scene and camera position, but struggled with the aesthetic aspect. Here’s a breakdown:
- Camera Position: The model scored 0.15, indicating a poor performance in reacting to camera positions. This suggests the generated image didn’t accurately reflect the camera position described in the prompt.
- Shot Analysis: The model scored 0.6, indicating a good performance in understanding the scene. This means the generated image captured the scene elements described in the prompt fairly well.
- Aesthetic Analysis: The model scored 0.09, indicating a very good performance in achieving the desired aesthetic. This means the generated image closely matched the expected aesthetic style.
Overall, the model seems to be better at understanding the scene and achieving the desired aesthetic than accurately reflecting the camera position.
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://fal.ai/models/fal-ai/flux-pro/api