AI's Artistic Eye: Capturing Poses, But Missing the Shot with Flux-dev
- 9 minutes read - 1888 wordsTable of Contents
In the realm of artificial intelligence, image generation has become a fascinating area of exploration. Generative AI models are capable of creating stunning visuals based on text prompts, but their ability to accurately capture specific artistic elements remains a challenge. This blog post examines the performance of a generative AI model in creating images based on various poses and scenes, highlighting its strengths and weaknesses in capturing camera positions, shot compositions, and aesthetic elements. We’ll delve into the concept of dramatic style poses, exploring their use in different contexts and providing examples of how they are employed to enhance storytelling and visual impact.
Created with: flux-dev
Silhouettes of War: Soldiers Face the Inferno
A line of soldiers, silhouetted against a fiery explosion, stand in a field, their backs to the camera. The scene evokes a sense of urgency and danger, capturing the dramatic intensity of war.
Prompt
poses standing-in-a-row: determined, courageous, hopeful ; A group of soldiers; wide shot; heroism; a battlefield with smoke and explosions in the background; cinematic
Characteristic
Shot : A line of soldiers in uniform, facing away from the camera, walking towards a burning building in the distance, the image is taken during sunset.
Aesthetic Score : 0.6
Mood : dramatic, somber, wartime
Quality
Entropy : 6.52
Noise : 59
Prompt Clip Score : 0.30
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image is slightly overexposed and some artifacts are present on the soldiers’ uniforms, especially around the head.
Unveiling the Secrets of the Ancient Temple
A group of adventurers stand before a majestic, ancient temple, its long staircase beckoning them towards the unknown. Lush jungle surrounds them, hinting at the mysteries that lie within. The scene evokes a sense of wonder, adventure, and contemplation, inviting viewers to imagine the stories hidden within the temple’s walls.
Prompt
poses standing-in-a-row: excited, curious, adventurous ; A team of explorers; medium shot; adventure; a lush jungle with ancient ruins in the distance; cinematic
Characteristic
Shot : A group of people are standing in front of a temple, they are looking at the camera, the temple is made of stone and has a lot of steps, there is a lot of green foliage around the temple.
Aesthetic Score : 0.6
Mood : mysterious, adventurous, serene
Quality
Entropy : 6.69
Noise : 115
Prompt Clip Score : 0.31
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image is slightly blurry, especially the people in the foreground, the resolution is also not very high, the colors are a little washed out.
The Focus of Competition: Gamers Immersed in the Game
A group of gamers, heads down and focused, are locked in a competitive battle. The intensity of their concentration is palpable, highlighted by the dramatic lighting and composition. This image captures the essence of competitive gaming, where every move matters.
Prompt
poses standing-in-a-row: focused, competitive, passionate ; A group of gamers; close-up shot; gaming; a brightly lit esports arena with cheering fans; cinematic
Characteristic
Shot : A group of young men are sitting in front of a computer screen wearing headphones and are focused on a game. The room is lit with pink and blue lights, creating a vibrant and dynamic atmosphere.
Aesthetic Score : 0.6
Mood : focused, energetic, competitive
Quality
Entropy : 6.50
Noise : 61
Prompt Clip Score : 0.27
AI Evaluation
Likelihood of AI : 0.20
Image errors : Some minor noise is visible in the image. This is likely due to the low-light conditions in the scene.
Friends Embracing the Vastness on a Sunny Hike
Four friends stand atop a hill, their backpacks hinting at a day of adventure. The wide valley below stretches out, bathed in sunshine, creating a serene and tranquil atmosphere. Their smiles and shared moment capture the essence of friendship and exploration.
Prompt
poses standing-in-a-row: happy, relaxed, joyful ; A family of tourists; long shot; tourism; a breathtaking view of a mountain range with a clear blue sky; cinematic
Characteristic
Shot : Four people, two men and two women, are standing on a mountaintop with their backs to the camera, looking at the view. They are wearing backpacks and casual clothing. The scene is backlit by the sun, creating a warm and inviting atmosphere.
Aesthetic Score : 0.7
Mood : tranquil, adventurous, hopeful
Quality
Entropy : 6.59
Noise : 73
Prompt Clip Score : 0.27
AI Evaluation
Likelihood of AI : 0.30
Image errors : No artifacts or errors are visible in the image.
Sunset Adventure: Friends Embark on a Journey of Hope
Six friends, silhouetted against a vibrant sunset, walk along a dirt road, their backpacks hinting at an exciting adventure ahead. The warm lighting and serene mood evoke a sense of hope and camaraderie, capturing the essence of friendship and exploration.
Prompt
poses standing-in-a-row: free-spirited, adventurous, optimistic ; A group of backpackers; medium shot; travel; a dusty road leading to a distant village with palm trees; cinematic
Characteristic
Shot : A group of six young adults are walking along a dirt path, likely on a hiking trail. They are all wearing backpacks and casual clothing. The sun is setting in the background, casting a warm glow on the scene. There are trees and bushes on either side of the path.
Aesthetic Score : 0.6
Mood : tranquil, adventurous, hopeful
Quality
Entropy : 6.32
Noise : 73
Prompt Clip Score : 0.32
AI Evaluation
Likelihood of AI : 0.10
Image errors : No significant image errors or artifacts are present.
Silhouettes in the Shadows: A Moment of Anticipation
A group of women stand in a dimly lit room, their faces obscured by the shadows. Spotlights illuminate their silhouettes, creating a sense of mystery and anticipation. The mood is solemn, hinting at a dramatic event about to unfold.
Prompt
poses standing-in-a-row: harmonious, powerful, emotional ; A choir singing in harmony; close-up shot; groups; a dimly lit stage with spotlights; cinematic
Characteristic
Shot : A group of people are standing in a dimly lit space with spotlights overhead, their backs are turned to the camera.
Aesthetic Score : 0.5
Mood : mysterious, dark, contemplative
Quality
Entropy : 5.89
Noise : 32
Prompt Clip Score : 0.29
AI Evaluation
Likelihood of AI : 0.20
Image errors : No noticeable errors, although the image is slightly grainy and the lighting is a bit flat.
Red and Pink: A Symphony of Dance Under the Spotlight
Capture the vibrant energy and artistic grace of dancers in red and pink dresses as they perform under the dramatic glow of stage lights. This scene exudes joy, energy, and a touch of artistic flair.
Prompt
poses standing-in-a-row: energetic, synchronized, joyful ; A line of dancers; wide shot; groups; a brightly lit stage with colorful costumes; cinematic
Characteristic
Shot : A group of dancers in red and pink dresses performing on stage under colorful lights.
Aesthetic Score : 0.7
Mood : joyful, energetic, celebratory
Quality
Entropy : 6.78
Noise : 80
Prompt Clip Score : 0.23
AI Evaluation
Likelihood of AI : 0.20
Image errors : There are some minor artifacts in the image, such as the slight blurring of the dancers’ bodies. These artifacts are not very noticeable and do not detract from the overall image.
Silhouettes of Friendship Against a Golden Sunset
A group of friends stand together, their figures outlined against a breathtaking sunset on the beach. The scene evokes a sense of calm, peace, and nostalgia, with the dramatic backdrop of the setting sun adding a touch of beauty and reflection.
Prompt
poses standing-in-a-row: relaxed, happy, nostalgic ; A group of friends; medium shot; groups; a sunset over a beach with waves crashing in the background; cinematic
Characteristic
Shot : A group of friends is standing on a beach facing the sunset, creating silhouettes against the golden sky. The ocean is calm and the sand appears soft.
Aesthetic Score : 0.7
Mood : tranquil, peaceful, contemplative
Quality
Entropy : 6.32
Noise : 63
Prompt Clip Score : 0.31
AI Evaluation
Likelihood of AI : 0.10
Image errors : No significant image errors.
A Team of Experts on the Brink of a Breakthrough
A group of dedicated professionals, likely doctors or scientists, stand poised in a sterile clinical setting. The determined expression of the central figure hints at an important mission about to unfold, leaving a sense of mystery and anticipation in the air.
Prompt
poses standing-in-a-row: focused, determined, innovative ; A team of scientists; close-up shot; groups; a laboratory with complex machinery and glowing screens; cinematic
Characteristic
Shot : A group of people in white lab coats are standing in a room. The person in the center of the image is the subject of the picture and has their arms crossed. There is a large screen on the wall behind the people.
Aesthetic Score : 0.6
Mood : serious, formal, determined
Quality
Entropy : 6.86
Noise : 80
Prompt Clip Score : 0.26
AI Evaluation
Likelihood of AI : 0.10
Image errors : The image is slightly blurry, particularly the background.
Sun-Drenched Street: A Moment of Everyday Mystery
A bustling city street bathed in sunlight, with a crowd of people walking by. The sun’s rays create a sense of anonymity, highlighting the everyday moments of life in a city.
Prompt
poses standing-in-a-row: determined, passionate, hopeful ; A group of protesters; long shot; groups; a city street with banners and signs; cinematic
Characteristic
Shot : A crowd of people walking down a city street. The sun is shining brightly and there is a lot of light in the scene. The people are all blurred and out of focus, and the city buildings in the background are also blurred.
Aesthetic Score : 0.4
Mood : busy, hopeful, bright
Quality
Entropy : 6.72
Noise : 72
Prompt Clip Score : 0.22
AI Evaluation
Likelihood of AI : 0.10
Image errors : The image is slightly overexposed, which is causing the highlights to be blown out. The image is also a little bit blurry.
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 0.56, 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 0.16, which is considered pretty good. This means the generated image’s aesthetic was fairly close to what was expected based on the prompt.
Overall, the model seems to be better at understanding and implementing aesthetic elements than it is at accurately capturing camera positions and shot compositions.
Sources:
- https://www.writerswrite.co.za/cheat-sheets-for-writing-body-language/
- https://mads3df.wordpress.com/2013/09/04/storytelling-poses/
- https://www.pinterest.com/pegasister890/character-poses/
- https://www.youtube.com/watch?v=udky6ANxWws
- https://maven.com/articles/storytelling-techniques
- https://fal.ai/models/fal-ai/flux/dev/api