AI Captures the Moment: A Look at Generative AI's Shot Composition Skills with Flux-schnell
- 9 minutes read - 1885 wordsTable of Contents
Dramatic style poses are a powerful tool in visual storytelling, used to convey emotion, action, and character. They are often employed in film, photography, and even video games to create impactful and memorable scenes. For example, a lone figure standing on a clifftop with their arms outstretched can evoke a sense of power and isolation, while a group of people running through a bustling marketplace can convey a sense of energy and excitement. Generative AI is now being used to create these dramatic poses, with impressive results.
Created with: flux-schnell
Lost in the Grey: A Solitary Figure in a Desolate Landscape
A lone figure, shrouded in a grey cloak, traverses a barren desert under a cloudy, grey sky. The vastness of the landscape and the figure’s small size evoke a profound sense of isolation and loneliness. This image captures a mood of desolation and mystery, leaving the viewer to ponder the figure’s journey and the secrets hidden within the desolate expanse.
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 walks across a vast, desolate desert landscape under a cloudy sky. The figure is dressed in a dark, hooded garment, and they appear to be carrying a long, thin object.
Aesthetic Score : 0.6
Mood : lonely, mysterious, desolate
Quality
Entropy : 6.55
Noise : 82
Prompt Clip Score : 0.26
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image is slightly blurry, particularly in the background.
Young Explorer on a Path to Adventure
A young boy, backpack in tow, walks confidently towards the camera on a winding path. The majestic temple in the background hints at the wonders that await him. This image captures the spirit of adventure, curiosity, and hope, as the boy embarks on a journey of discovery.
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 boy, wearing a backpack, walks towards the camera on a dirt path in front of a large, ancient stone temple. Lush greenery surrounds the scene.
Aesthetic Score : 0.7
Mood : adventurous, hopeful, curious
Quality
Entropy : 6.68
Noise : 121
Prompt Clip Score : 0.33
AI Evaluation
Likelihood of AI : 0.20
Image errors : No visible errors
The Intensity of Focus in Dim Light
A close-up shot captures the focused hand of a person typing on a keyboard, bathed in the soft glow of a few lights. The dimly lit scene creates a sense of drama and suspense, highlighting the intensity of their concentration.
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 is sitting at a computer desk, typing on a keyboard. The scene is lit by warm and cool lighting, creating a contrast and a sense of depth.
Aesthetic Score : 0.6
Mood : focused, techy, casual
Quality
Entropy : 6.76
Noise : 58
Prompt Clip Score : 0.27
AI Evaluation
Likelihood of AI : 0.10
Image errors : The image has a few minor artifacts, such as some graininess in the shadows and a slight blur around the edges.
Capturing the Buzz: A Vibrant Market Through a Lens of Motion
This image bursts with energy, capturing the joyful atmosphere of a bustling market. The motion blur and shallow depth of field create a dynamic sense of movement, highlighting the vibrant colors and delicious food on display. It’s a snapshot of youthful energy and the excitement of exploring a new place.
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 young people walking through a bustling market with colorful stalls and decorations.
Aesthetic Score : 0.7
Mood : happy, vibrant, energetic
Quality
Entropy : 6.90
Noise : 111
Prompt Clip Score : 0.33
AI Evaluation
Likelihood of AI : 0.10
Image errors : Minor motion blur and some minor noise in the background.
Love Story on the Beach: A Moment of Freedom and Mystery
A couple strolls hand-in-hand along a pristine white sand beach, their silhouettes disappearing into the azure waters. The image captures a sense of carefree joy and romantic connection, leaving the viewer to imagine their story unfolding.
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 walking on a beach, the man is facing forward and the woman is looking back at the camera, they are both wearing casual summer clothing.
Aesthetic Score : 0.7
Mood : happy, carefree, romantic
Quality
Entropy : 6.48
Noise : 54
Prompt Clip Score : 0.31
AI Evaluation
Likelihood of AI : 0.30
Image errors : The image has some noise and grain, especially in the shadows.
Sun-Kissed Smiles and Laughter: Friends Enjoy a Carefree Day in the Park
Capture the joy of friendship with this vibrant image of six young people strolling through a picturesque park. Their infectious smiles and carefree energy radiate happiness, creating a mood that’s both uplifting and inspiring. The sun-drenched setting adds to the sense of warmth and vibrancy, making this a perfect snapshot of a beautiful 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, three women and two men, are walking in a park. The men are wearing casual clothes, the women are wearing casual clothes, The group is walking in a relaxed manner. The park is a bright and sunny setting.
Aesthetic Score : 0.7
Mood : happy, youthful, cheerful
Quality
Entropy : 6.74
Noise : 115
Prompt Clip Score : 0.29
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image has a mild amount of blur, especially in the background. It is possible that the blur may be caused by a deliberate choice in the camera settings, to create motion blur. There are no visible signs of compression artifacts.
Superhero in Motion: A City’s Hope Takes Flight
A determined superhero, clad in vibrant orange and yellow, races through a city shrouded in a stormy sky. His focused expression and the blurred cityscape create a sense of intense action and heroic purpose. This image captures the raw energy of a hero in motion, leaving viewers eager to witness the unfolding story.
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 superhero in an orange costume running through a city skyline.
Aesthetic Score : 0.6
Mood : heroic, action, dramatic
Quality
Entropy : 6.63
Noise : 66
Prompt Clip Score : 0.29
AI Evaluation
Likelihood of AI : 0.10
Image errors : No significant errors
Tiny Figure, Mighty Spirit: A Hiker Conquers the Snowy Peaks
A lone hiker races down a snow-covered mountain path, their small figure dwarfed by the towering peaks. The scene evokes a sense of adventure, hope, and determination, as the hiker embraces the vastness of the wilderness.
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 lone hiker is running through a snowy mountain pass towards a vast, majestic mountain range. The sun is shining brightly in the clear sky.
Aesthetic Score : 0.7
Mood : determined, adventurous, serene
Quality
Entropy : 6.81
Noise : 72
Prompt Clip Score : 0.28
AI Evaluation
Likelihood of AI : 0.10
Image errors : No visible errors
Silhouetted Escape: A Lone Runner Fleeing the Unknown
A solitary figure, backpack in tow, races across a surreal, alien landscape as the sun sets. The dramatic silhouette and mysterious surroundings evoke a sense of adventure, hope, and a touch of danger.
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 lone figure, wearing a backpack and a hat, runs towards the sunset in a fantasy landscape. Giant tree-like structures and other fantastical creatures populate the background.
Aesthetic Score : 0.6
Mood : mysterious, adventurous, hopeful
Quality
Entropy : 6.81
Noise : 73
Prompt Clip Score : 0.28
AI Evaluation
Likelihood of AI : 0.90
Image errors : The image suffers from some blurring and softness, particularly in the background. Some unnatural textures and color banding are noticeable.
Family Fun in the Sun: A Day of Joy and Togetherness
A heartwarming scene of a family of four strolling down a dirt road, bathed in warm sunlight. Their smiles and carefree laughter capture the essence of a happy day spent together in the beautiful countryside.
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 four walking on a road in the countryside. The sun is setting in the background and there are hills in the distance.
Aesthetic Score : 0.7
Mood : happy, joyful, adventurous
Quality
Entropy : 6.73
Noise : 89
Prompt Clip Score : 0.29
AI Evaluation
Likelihood of AI : 0.20
Image errors : None
Conclusion
The results show that the generative AI model performed well in understanding and executing camera positions and shot composition, but struggled with achieving the desired aesthetic. Here’s a breakdown:
- Camera Position: The model scored 0.51, indicating a good understanding of the camera positions specified in the prompt. This suggests the model is able to accurately translate the intended camera angles and perspectives into the generated image.
- Shot Analysis: The model scored 0.57, also indicating good performance in understanding and executing the shot composition described in the prompt. This suggests the model is able to capture the intended framing, focus, and overall visual structure of the scene.
- Aesthetic Analysis: The model scored 0.13, which falls within the very good range for aesthetic analysis. This suggests that the generated image’s aesthetic is quite close to the expected aesthetic, although there might be some minor discrepancies.
Overall, the model demonstrates a strong ability to interpret and execute camera positions and shot composition, but it could benefit from further development in achieving the desired aesthetic.
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/schnell/api