In the realm of artificial intelligence, the ability to generate images based on text prompts has become increasingly sophisticated. However, capturing the nuances of artistic expression, particularly in conveying the desired aesthetic, remains a challenge. This blog post delves into the performance of a generative AI model in generating images based on poses and scenes, showcasing its strengths and limitations in capturing the intended artistic vision.
Created with: flux-pro
Lost in the Storm: A Solitary Figure in a Desolate Landscape
A lone figure, shrouded in a long cloak, traverses a barren, sandy expanse under a tempestuous sky. The scene evokes a sense of mystery, loneliness, and dramatic despair, highlighting the figure’s isolation amidst the vast emptiness.
Prompt
poses running: determined, hopeful ; A lone figure in a tattered cloak; wide shot; Heroism; a desolate wasteland with a storm brewing in the distance; cinematic
Characteristic
Shot : A lone figure in a long, flowing cloak walks through a desolate, sandy landscape under a stormy sky.
Aesthetic Score : 0.8
Mood : dramatic, melancholic, mysterious
Quality
Entropy : 6.29
Noise : 59
Prompt Clip Score : 0.31
AI Evaluation
Likelihood of AI : 0.10
Image errors : No visible image errors
Lost in the Jungle: A Young Explorer’s Journey Begins
A young man, confident and ready for adventure, stands amidst the vibrant greenery of a lush jungle. His gaze, fixed on the unknown, hints at a mysterious journey ahead. The image captures the thrill of exploration and the allure of the wild.
Prompt
poses running: excited, curious ; A young adventurer with a backpack; medium shot; Adventure; a lush jungle with ancient ruins in the background; cinematic
Characteristic
Shot : A young man is standing in a jungle setting, wearing a backpack and looking to the side.
Aesthetic Score : 0.6
Mood : adventurous, confident, rugged
Quality
Entropy : 6.87
Noise : 80
Prompt Clip Score : 0.33
AI Evaluation
Likelihood of AI : 0.20
Image errors : There are no visible image errors.
Focused on the Task at Hand
A close-up shot of a hand navigating a computer mouse, the screen displaying a warm, abstract background. The image conveys a sense of focus and intention, but lacks depth and detail, leaving a slightly sterile impression.
Prompt
poses running: intense, focused ; A gamer’s hands on a keyboard and mouse; close-up; Gaming; a brightly lit gaming room with a monitor displaying a virtual world; cinematic
Characteristic
Shot : A person’s hand is shown using a computer mouse in front of a blurred computer screen. The screen shows an abstract background of a landscape with an orange and blue sky.
Aesthetic Score : 0.4
Mood : focused, intense, digital
Quality
Entropy : 6.92
Noise : 63
Prompt Clip Score : 0.25
AI Evaluation
Likelihood of AI : 0.30
Image errors : There is some blurriness in the background, particularly around the edges of the computer screen. The lighting is slightly uneven, causing some areas to be slightly overexposed.
Pink Hatted Photographer Captures the Joy of European Streets
A vibrant scene unfolds as a group of young adults stroll through a European city. The woman in the pink hat, radiating happiness, stands out with her camera, capturing the energy and carefree spirit of the moment.
Prompt
poses running: energetic, joyful ; A group of tourists running through a bustling marketplace; long shot; Tourism; a vibrant marketplace with colorful stalls and vendors; cinematic
Characteristic
Shot : A group of people, mostly young adults, are walking down a street in a city. The woman in the pink hat is the focal point of the image, and she is looking at the camera with a smile. The background is blurred, and the overall atmosphere is bright and cheerful.
Aesthetic Score : 0.7
Mood : happy, vibrant, playful
Quality
Entropy : 6.80
Noise : 76
Prompt Clip Score : 0.32
AI Evaluation
Likelihood of AI : 0.20
Image errors : None
Sun-Kissed Romance on the Beach
A couple strolls hand-in-hand along a sandy shore, their smiles reflecting the warmth of the sun. The scene evokes a sense of happiness, romance, and carefree joy.
Prompt
poses running: romantic, carefree ; A couple running hand-in-hand along a beach; medium shot; Travel; a beautiful beach with turquoise water and white sand; cinematic
Characteristic
Shot : A couple is running on a beach with the ocean in the background. There are palm trees on the right side of the image.
Aesthetic Score : 0.7
Mood : romantic, playful, carefree
Quality
Entropy : 6.67
Noise : 79
Prompt Clip Score : 0.32
AI Evaluation
Likelihood of AI : 0.10
Image errors : The image appears to be slightly overexposed, leading to a washed-out appearance.
Sun-Kissed Laughter: Friends Embrace the Joy of a Perfect Day
Five young adults radiate pure joy as they run through a vibrant park, their laughter echoing the carefree spirit of youth. This image captures the essence of friendship, energy, and the simple pleasures of a sunny day.
Prompt
poses running: happy, playful ; A group of friends running through a park; wide shot; Groups; a sunny park with green grass and trees; cinematic
Characteristic
Shot : A group of five young adults are running through a park on a sunny day. The light is soft and warm, and the trees are green and lush.
Aesthetic Score : 0.7
Mood : happy, carefree, youthful
Quality
Entropy : 6.63
Noise : 86
Prompt Clip Score : 0.33
AI Evaluation
Likelihood of AI : 0.30
Image errors : There are no visible artifacts or errors in the image.
Superhero Stands Tall, Ready for Action
A dramatic portrait of a superhero, arms crossed, bathed in focused light against a city backdrop. The pose and lighting exude confidence and heroism, capturing the essence of a true champion.
Prompt
poses running: powerful, confident ; A superhero in a bright costume; close-up; Heroism; a city skyline with skyscrapers and flashing lights; cinematic
Characteristic
Shot : A man dressed as a superhero stands in an urban setting, looking up. The lighting is colorful and dramatic. There are blurry people in the background.
Aesthetic Score : 0.6
Mood : heroic, determined, confident
Quality
Entropy : 6.81
Noise : 76
Prompt Clip Score : 0.27
AI Evaluation
Likelihood of AI : 0.30
Image errors : The image appears to be slightly overexposed, and there is some noise in the background.
A Solitary Figure Against the Majesty of the Mountains
A woman hikes a snow-covered path, dwarfed by the towering peaks of a majestic mountain range. The setting sun casts a warm glow, creating a serene and adventurous atmosphere. This breathtaking scene evokes a sense of awe and hope, reminding us of the beauty and wonder that nature holds.
Prompt
poses running: determined, adventurous ; A lone explorer running through a snow-covered mountain pass; long shot; Adventure; a majestic mountain range with snow-capped peaks; cinematic
Characteristic
Shot : A young woman is hiking in a snowy mountainous terrain. She is wearing a backpack and a jacket and is smiling at the camera as she walks on a path.
Aesthetic Score : 0.7
Mood : happy, adventurous, optimistic
Quality
Entropy : 6.55
Noise : 84
Prompt Clip Score : 0.28
AI Evaluation
Likelihood of AI : 0.10
Image errors : No visible errors
A Dreamy Journey Through a Fantastical Forest
A young woman embarks on an adventurous quest, running through a whimsical forest filled with giant mushrooms towards a distant castle. The scene evokes a sense of wonder and excitement, capturing the essence of a dreamy escape.
Prompt
poses running: immersive, exciting ; A gamer’s avatar running through a virtual world; close-up; Gaming; a vibrant and detailed virtual world with fantastical creatures; cinematic
Characteristic
Shot : A woman is running through a fantastical forest with mushrooms and a distant castle in the background
Aesthetic Score : 0.7
Mood : whimsical, adventurous, magical
Quality
Entropy : 6.62
Noise : 90
Prompt Clip Score : 0.30
AI Evaluation
Likelihood of AI : 0.90
Image errors : The lighting and shadows in the image appear slightly unnatural. The mushrooms in the foreground seem to have a slight bluriness, suggesting possible over-sharpening.
A Family’s Joyful Stroll Through a Picturesque Village
Capture the essence of rural bliss with this heartwarming scene. A family of three walks down a charming path, surrounded by a quaint village, rolling hills, and a vibrant blue sky. The warm colors and pleasing composition evoke a sense of happiness and contentment, making this image a perfect representation of idyllic living.
Prompt
poses running: happy, carefree ; A family running along a scenic road; medium shot; Travel; a winding road with rolling hills and a picturesque countryside; cinematic
Characteristic
Shot : A family of three walks down a path in a countryside setting with a church in the background, a blue sky with fluffy clouds overhead and a lot of greenery on the hillsides. The path is winding and the family is smiling and happy.
Aesthetic Score : 0.7
Mood : happy, idyllic, cheerful
Quality
Entropy : 6.38
Noise : 84
Prompt Clip Score : 0.30
AI Evaluation
Likelihood of AI : 0.80
Image errors : The image has a slightly blurry effect, particularly in the background, this could be caused by the image being upscaled, or by a post processing filter that was applied to the image.
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 0.45, which is considered okay. This means the generated image’s camera position was somewhat different from what was requested in the prompt.
- Shot Analysis: The model scored 0.545, which is also considered okay. This indicates that the generated image’s shot composition was somewhat different from what was expected based on the prompt.
- Aesthetic Analysis: The model scored 0.11, which is considered pretty good. This means the generated image’s aesthetic was fairly close to what was expected, although it could be better.
Overall, the model seems to be better at understanding the scene and shot composition than it is at capturing the desired aesthetic.