AI Captures Poses, But Struggles with Aesthetics with Scenario

In the realm of AI image generation, capturing the essence of a scene goes beyond simply replicating the elements described. It involves understanding the nuances of composition, lighting, and overall aesthetic. This blog post delves into the performance of a generative AI model in capturing poses and scenes, highlighting its strengths and weaknesses in achieving a desired aesthetic.

Created with: scenario

Hope in the Desert: A Woman’s Journey

A solitary figure in a flowing white dress walks through a vast, sun-drenched desert. The wind whips her hair back, creating a sense of movement and power. The setting sun casts a warm glow, hinting at both melancholy and hope. This dramatic scene evokes a powerful sense of resilience and the beauty found in unexpected places.

Prompt

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

Characteristic

Shot : A woman in a long, flowing white robe walks through a desert landscape. The sun is setting, casting long shadows.

Aesthetic Score : 0.7

Mode : mysterious, ethereal, cinematic

Quality

Entropy : 6.31

Noise : 90

Prompt Clip Score : 0.21

AI Evaluation

Likelihood of AI : 0.20

Image errors : The image is slightly overexposed, but this does not detract significantly from the overall quality. The composition is good, and the colors are well-balanced. However, the lighting could be more dramatic and the shadows more defined.

Lost in the Jungle: A Journey of Hope and Mystery

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.

Four adventurers race through a dense jungle, their destination an ancient ruin shrouded in mystery. The dramatic lighting and composition evoke a sense of hope and adventure, hinting at the challenges and discoveries 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 : A group of four people are running through a jungle towards a large stone building. The woman in the foreground is smiling and seems to be leading the group.

Aesthetic Score : 0.7

Mode : adventure, tropical, hopeful

Quality

Entropy : 6.52

Noise : 96

Prompt Clip Score : 0.29

AI Evaluation

Likelihood of AI : 0.30

Image errors : The image has some slight blurriness and some artifacts in the background.

Lost in the Glow: A Moment of Focus and Intrigue

A young woman, headphones on, sits bathed in colorful light, her gaze fixed on something unseen. The dimly lit room and her intense focus create an atmosphere of mystery and playful intensity. What is she looking at? What secrets does the screen hold?

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 young woman wearing a headset and a white shirt is sitting in front of a computer screen. She is pointing at the screen with her right hand and is looking at it intently. The scene is dimly lit, with a pink light emanating from the computer desk and a monitor on the wall behind her.

Aesthetic Score : 0.6

Mode : focused, intense, curious

Quality

Entropy : 6.78

Noise : 84

Prompt Clip Score : 0.24

AI Evaluation

Likelihood of AI : 0.20

Image errors : The image is slightly blurry. The colors are a bit oversaturated.

A Dance of Love in a Vibrant Street Market

In the heart of a bustling street market, a couple dances with joy and love. The scene is alive with vibrant colors and textures, while the couple remains the focal point, softly blurring the lively background. The side lighting creates a dramatic contrast, highlighting their happiness and the romance in the air.

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 a European city setting. They are surrounded by colorful buildings and market stalls.

Aesthetic Score : 0.8

Mode : romantic, playful, happy

Quality

Entropy : 6.83

Noise : 91

Prompt Clip Score : 0.29

AI Evaluation

Likelihood of AI : 0.10

Image errors : No noticeable image errors

A Serene Sunset Walk Through the Desert

A woman in a flowing white dress walks through a golden desert landscape at sunset. The soft orange and pink sky creates a serene and ethereal mood, while the contrast of the dress against the rugged dunes adds a touch of romantic drama.

Prompt

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

Characteristic

Shot : A woman in a flowing dress walks across a desert landscape at sunset.

Aesthetic Score : 0.75

Mode : serene, tranquil, dreamy

Quality

Entropy : 6.38

Noise : 84

Prompt Clip Score : 0.26

AI Evaluation

Likelihood of AI : 0.10

Image errors : No visible errors in the image

Rooftop Revelry: Capturing the Joy of Friendship

A vibrant rooftop party at twilight, where four friends celebrate with laughter and carefree energy. The woman in the center, twirling with a radiant smile, embodies the pure joy of the moment. The cityscape backdrop adds a touch of excitement and occasion to this candid capture of friendship.

Prompt

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

Characteristic

Shot : A group of friends are having fun on a rooftop party in the city at dusk.

Aesthetic Score : 0.7

Mode : joyful, carefree, celebratory

Quality

Entropy : 6.78

Noise : 88

Prompt Clip Score : 0.27

AI Evaluation

Likelihood of AI : 0.10

Image errors : No noticeable errors.

A Dance of Shadows: Elegance and Mystery in the City Streets

A captivating image of a woman in a black dress, dancing with dramatic flair in a narrow city street. The perspective and her pose create a sense of motion and excitement, while the surrounding buildings add an air of mystery and intrigue. This photograph captures the essence of elegance and drama, leaving a lasting impression.

Prompt

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

Characteristic

Shot : A young woman in a black dress is dancing in the middle of an empty alleyway. The scene is lit by a soft, warm light from the top of the image.

Aesthetic Score : 0.7

Mode : romantic, mysterious, elegant

Quality

Entropy : 6.82

Noise : 114

Prompt Clip Score : 0.24

AI Evaluation

Likelihood of AI : 0.80

Image errors : There is some evidence of smoothing and blurring, especially on the woman’s hair and skin. Some of the brickwork on the buildings appears artificial.

Laughter Echoes Through the Mountains: A Day of Joy and Adventure

Three friends embrace the thrill of the open trail, their laughter echoing through the crisp mountain air. A vibrant, sunny day sets the stage for a carefree adventure, with a snow-capped peak serving as a breathtaking backdrop. This image captures the pure joy and energy of exploring the great outdoors.

Prompt

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

Characteristic

Shot : Three young women are running and laughing on a mountaintop, with a dramatic backdrop of snow-capped mountains.

Aesthetic Score : 0.7

Mode : joyful, adventurous, carefree

Quality

Entropy : 6.45

Noise : 98

Prompt Clip Score : 0.30

AI Evaluation

Likelihood of AI : 0.20

Image errors : There are no visible artifacts or errors in the image.

Confident and Focused: A Moment of Productivity

This image captures a woman at her desk, radiating confidence and focus. The soft, warm lighting and blurred background create a sense of intimacy and depth, highlighting her concentration. The image evokes a feeling of relaxed productivity and inspires a sense of calm and determination.

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 woman with short brown hair is sitting in front of a computer, looking directly at the viewer.

Aesthetic Score : 0.7

Mode : intrigued, confident, focused

Quality

Entropy : 6.78

Noise : 90

Prompt Clip Score : 0.23

AI Evaluation

Likelihood of AI : 0.40

Image errors : No visible errors or artifacts.

Summer Bliss on a Pristine Beach

A carefree woman strolls along a stunning white sand beach, turquoise waters lapping at her feet. Palm trees sway in the background, creating a picture-perfect summer scene. The vibrant colors and warm light evoke a sense of joy and relaxation, capturing the essence of a perfect vacation.

Prompt

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

Characteristic

Shot : A young woman in a white tank top and denim shorts walks on a white sand beach towards the turquoise water. There are palm trees in the background.

Aesthetic Score : 0.7

Mode : happy, carefree, summery

Quality

Entropy : 6.50

Noise : 78

Prompt Clip Score : 0.26

AI Evaluation

Likelihood of AI : 0.20

Image errors : The image is slightly overexposed, resulting in a washed-out look.

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 0.51, which falls within the “good” range (0.5 to 0.75). This indicates that the model was able to accurately capture the camera positions described in the prompt.
• Shot Analysis: The model scored 0.62, 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 the intended shot composition.
• Aesthetic Analysis: The model scored 0.05, which is significantly lower than the “very good” range (-0.2 to 0.1). This indicates that the generated image’s aesthetic deviated from the expected aesthetic described in the prompt.

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