AI's Artistic Journey: Capturing Poses, But Missing the Mood with Flux-dev

The world of AI is rapidly evolving, with models capable of generating impressive images based on text prompts. However, capturing the nuances of human expression and artistic intent remains a challenge. This blog post delves into the results of an experiment where an AI model was tasked with generating images based on specific poses and scenes, revealing both its strengths and limitations in capturing the desired aesthetic.

Created with: flux-dev

Silhouetted in Gold: A Moment of Power and Mystery

A woman, cloaked in a flowing dress and wielding a sword, stands with her back to the camera, facing the setting sun. The soft, golden light and hazy atmosphere create a dramatic and ethereal scene, evoking a sense of power, freedom, and the embrace of the unknown.

Prompt

poses dancing: triumphant, powerful ; A lone warrior; wide shot; heroism; a battlefield littered with fallen enemies; cinematic

Characteristic

Shot : A woman in a flowing dress is silhouetted against a sunset, holding a sword aloft. She appears to be walking or dancing towards the viewer, with the sun setting behind her, creating a golden glow. The background features a hazy, dusty atmosphere, with silhouettes of people and trees in the distance.

Aesthetic Score : 0.7

Mood : dramatic, ethereal, hopeful

Quality

Entropy : 6.40

Noise : 58

Prompt Clip Score : 0.24

AI Evaluation

Likelihood of AI : 0.20

Image errors : The image has a slight blur, possibly due to motion blur, and the background is slightly out of focus. There is also some graininess in the image. These issues could be due to the lighting or the camera used.

Silhouettes of Hope: A Journey into the Unknown

Affiliate Links

Stable Diffusion with Python

Master Stable Diffusion for AI image generation using Python. Control and customize your creations.

Mastering Midjourney: AI Art Guide

Unlock Midjourney V6 features and create exceptional AI art.

Midjourney Prompt Book: AI Image Generation

Master Midjourney with this comprehensive guide for beginners and pros.

Three figures, shrouded in mystery, walk away from a grand stone structure towards a hazy, sun-drenched horizon. Their silhouettes, bathed in golden light, evoke a sense of adventure and hope, leaving the viewer to ponder their destination and the secrets that lie ahead.

Prompt

poses dancing: excited, adventurous ; A group of explorers; medium shot; adventure; a dense jungle with ancient ruins in the background; cinematic

Characteristic

Shot : Three people silhouetted against a backdrop of lush foliage and a partially visible ancient temple.

Aesthetic Score : 0.6

Mood : mysterious, adventurous, hopeful

Quality

Entropy : 6.58

Noise : 105

Prompt Clip Score : 0.33

AI Evaluation

Likelihood of AI : 0.20

Image errors : The image has a slight blur and the colors are slightly muted.

Lost in the Game: A Gamer’s World of Focus and Intensity

A young man, headphones on, sits in a dimly lit room, his eyes glued to a blurry city landscape on his computer screen. The intensity of his focus is palpable as he navigates the virtual world, creating a sense of immersion that draws the viewer into his gaming experience.

Prompt

poses dancing: intense, focused ; A gamer; close-up; gaming; a brightly lit gaming setup with a screen displaying a virtual world; cinematic

Characteristic

Shot : A person wearing headphones is sitting in front of a computer screen and using a keyboard.

Aesthetic Score : 0.6

Mood : focused, serious, intense

Quality

Entropy : 6.49

Noise : 64

Prompt Clip Score : 0.21

AI Evaluation

Likelihood of AI : 0.20

Image errors : No significant errors

Silhouettes of Love in the Golden Hour

A couple dances in the warm glow of the setting sun, their silhouettes framed against the narrow street. The scene evokes a romantic and dreamy mood, with a touch of playful intimacy.

Prompt

poses dancing: joyful, romantic ; A couple; medium shot; tourism; a bustling marketplace with vibrant colors and exotic goods; cinematic

Characteristic

Shot : A couple is dancing in the street, surrounded by buildings and other people. The woman is wearing a long, flowing dress and the man is wearing a white shirt and pants.

Aesthetic Score : 0.8

Mood : romantic, whimsical, playful

Quality

Entropy : 6.50

Noise : 90

Prompt Clip Score : 0.27

AI Evaluation

Likelihood of AI : 0.10

Image errors : There are no significant errors in the image.

Silhouetted Serenity: A Moment of Contemplation at Sunset

A lone figure, cloaked in mystery, stands against the fiery backdrop of a setting sun. Their outstretched arms and the vast, empty landscape evoke a sense of serenity and spiritual contemplation. The silhouette, bathed in golden light, creates a dramatic effect, leaving the viewer to ponder the figure’s thoughts and the meaning behind their gesture.

Prompt

poses dancing: reflective, contemplative ; A traveler; long shot; travel; a vast desert landscape with a setting sun; cinematic

Characteristic

Shot : A single person stands with arms outstretched against a bright orange sunset, silhouetted against the sky. The person is wearing a long robe-like garment.

Aesthetic Score : 0.7

Mood : peaceful, hopeful, serene

Quality

Entropy : 6.38

Noise : 35

Prompt Clip Score : 0.24

AI Evaluation

Likelihood of AI : 0.20

Image errors : No visible image errors

Silhouettes of Joy: Friends Celebrate Against a Cityscape Sunset

Five friends stand on a rooftop, their silhouettes outlined against a vibrant sunset and the twinkling city lights. Their raised arms and joyful pose capture a moment of carefree celebration, while the silhouette effect adds a touch of mystery and drama to the scene.

Prompt

poses dancing: happy, carefree ; A group of friends; medium shot; groups; a rooftop overlooking a city skyline at night; cinematic

Characteristic

Shot : Five young women stand on a rooftop overlooking a city skyline at sunset. They are silhouetted against the light, making it difficult to see their facial expressions.

Aesthetic Score : 0.6

Mood : youthful, carefree, mysterious

Quality

Entropy : 6.68

Noise : 66

Prompt Clip Score : 0.29

AI Evaluation

Likelihood of AI : 0.20

Image errors : The image is slightly grainy and there is some noise in the shadows.

Silhouette of Mystery: A Dancer’s Alluring Night

A captivating silhouette of a woman in a flowing dress dances under the glow of streetlights, shrouded in a veil of fog. The scene evokes a sense of mystery and allure, leaving you wanting to unravel the story behind the dance.

Prompt

poses dancing: determined, defiant ; A lone dancer; close-up; heroism; a dark alleyway with flickering streetlights; cinematic

Characteristic

Shot : A woman in a silhouette is dancing in a dark alleyway with a few streetlights in the background.

Aesthetic Score : 0.7

Mood : mysterious, dramatic, alluring

Quality

Entropy : 6.68

Noise : 75

Prompt Clip Score : 0.30

AI Evaluation

Likelihood of AI : 0.30

Image errors : No visible artifacts or errors.

Summit Celebration: A Moment of Joy and Triumph Against the Majestic Mountains

Five friends stand triumphantly on a mountain peak, their arms raised in celebration. The breathtaking backdrop of the mountain range and the clear blue sky create a sense of awe and accomplishment. This image captures the joy and adventure of reaching a summit, a moment to cherish forever.

Prompt

poses dancing: exhilarated, free ; A group of adventurers; wide shot; adventure; a breathtaking mountain range with a clear blue sky; cinematic

Characteristic

Shot : Five people are silhouetted against a mountain range, their arms raised in the air, suggesting a sense of freedom and accomplishment. The clear blue sky and bright sun add to the sense of openness and possibility.

Aesthetic Score : 0.6

Mood : optimistic, uplifting, adventurous

Quality

Entropy : 6.85

Noise : 73

Prompt Clip Score : 0.25

AI Evaluation

Likelihood of AI : 0.20

Image errors : No notable image errors.

Immersed in the Game: A Gamer’s Focus Under Neon Lights

A dimly lit room bathed in pink and blue hues sets the stage for intense gaming. The player, headphones on, is fully absorbed in the action unfolding on their computer screen, showcasing the focused energy of a true gamer.

Prompt

poses dancing: focused, strategic ; A gamer; close-up; gaming; a dimly lit room with a computer screen displaying a competitive game; cinematic

Characteristic

Shot : A person is playing a video game on a computer with neon lights in the background.

Aesthetic Score : 0.6

Mood : focused, intense, futuristic

Quality

Entropy : 6.55

Noise : 61

Prompt Clip Score : 0.23

AI Evaluation

Likelihood of AI : 0.20

Image errors : There are no obvious image errors.

Tropical Beach Bliss: Friends Celebrate Summer Fun

Capture the carefree joy of summer with this vibrant image of three friends high-fiving on a tropical beach. The dynamic poses and bright, sunny background create a sense of pure happiness and emphasize the beauty of the moment.

Prompt

poses dancing: relaxed, joyful ; A family; medium shot; travel; a picturesque beach with turquoise water and white sand; cinematic

Characteristic

Shot : Three friends are playing on a beach on a bright sunny day. They are standing in shallow water and are about to high five.

Aesthetic Score : 0.7

Mood : happy, carefree, summery

Quality

Entropy : 6.31

Noise : 65

Prompt Clip Score : 0.27

AI Evaluation

Likelihood of AI : 0.10

Image errors : The image is sharp and well-exposed. There are no obvious artifacts or errors.

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 0.5, which falls within the “good” range (0.5 to 0.75). This indicates that the model was able to accurately capture the camera position described in the prompt.
• Shot Analysis: The model scored 0.66, also within the “good” range. This suggests that the model understood the scene described in the prompt and was able to create an image that reflected that understanding.
• Aesthetic Analysis: The model scored 0.12, which is significantly lower than the “very good” range (-0.2 to 0.1). This indicates that the generated image did not match the expected aesthetic as closely as it did with the camera position and shot analysis.

Overall, the model demonstrates a good understanding of camera position and shot composition, but needs improvement in capturing the desired aesthetic.