AI Captures the Scene, But Struggles with the Pose with Bfl-flux-pro
- 9 minutes read - 1806 wordsTable of Contents
Dramatic poses are a powerful tool in visual storytelling, adding depth and emotion to images. They are often used in photography, film, and art to convey a specific mood or message. For example, a superhero standing with their arms outstretched can evoke a sense of power and heroism, while a figure slumped over in despair can convey sadness and defeat. In this blog post, we explore the challenges of generating dramatic poses using AI image generation models.
Created with: flux-pro
A Solitary Figure Contemplates the Majesty of the Mountains
A lone adventurer stands on a cliff, silhouetted against the fiery sunset. The vast, mist-shrouded mountains create a breathtaking panorama, emphasizing the figure’s small scale and the awe-inspiring grandeur of nature. This epic scene evokes a sense of adventure and contemplation, inviting viewers to imagine the stories unfolding within this majestic landscape.
Prompt
poses looking-at-each-other: determined, awe-inspired ; A lone adventurer, standing on a mountain peak; wide shot; adventure; a vast, breathtaking landscape with clouds swirling below; cinematic
Characteristic
Shot : A lone figure stands on a cliff overlooking a majestic mountain range. The sky is filled with clouds, and the sun is setting in the distance, casting a golden glow over the landscape.
Aesthetic Score : 0.7
Mood : epic, majestic, contemplative
Quality
Entropy : 6.81
Noise : 90
Prompt Clip Score : 0.30
AI Evaluation
Likelihood of AI : 0.70
Image errors : The clouds and mountain ranges seem to be slightly blurry, which may be due to over-sharpening or AI generation.
Clash of Titans: A Moment of Suspense in the Sunlit Battlefield
Two soldiers, silhouetted against a hazy, sunlit background, stand locked in a tense confrontation. One holds a shield, a symbol of defense against the unknown. The dramatic lighting and composition create a palpable sense of anticipation and intensity, hinting at the unfolding battle.
Prompt
poses looking-at-each-other: tense, hopeful ; Two soldiers, one injured, the other holding a shield; medium shot; heroism; a battlefield with smoke and fire in the background; cinematic
Characteristic
Shot : Two men in military attire are facing each other, one holding a shield. The background is blurry and suggests an outdoor setting with a hazy, late afternoon sky.
Aesthetic Score : 0.7
Mood : dramatic, intense, serious
Quality
Entropy : 6.71
Noise : 69
Prompt Clip Score : 0.29
AI Evaluation
Likelihood of AI : 0.20
Image errors : Some slight blurriness is present in the background, potentially due to shallow depth of field or motion blur.
Intimate Moment: A Mysterious Encounter in Red-Orange Hues
Experience the captivating allure of this close-up portrait featuring a young couple lost in each other’s gaze. The man, donning headphones, and the woman, with her hair cascading down, share an intense connection against a red-orange backlight. The scene exudes intimacy, romance, and an air of mystery, as the dramatic lighting sets the stage for their enchanting encounter.
Prompt
poses looking-at-each-other: intense, focused ; Two gamers, heads bent over a screen; close-up; gaming; a dimly lit room with neon lights reflecting on their faces; cinematic
Characteristic
Shot : A couple is looking at each other with a romantic expression, the man is wearing headphones and the woman has her hair down.
Aesthetic Score : 0.6
Mood : romantic, intimate, playful
Quality
Entropy : 6.36
Noise : 56
Prompt Clip Score : 0.33
AI Evaluation
Likelihood of AI : 0.10
Image errors : The image appears to be slightly overexposed and the colors are a bit too saturated.
Joyful Juggling at the Eiffel Tower
A casual, urban scene unfolds as a group strolls past the iconic Eiffel Tower. A touch of playful surprise is added by a woman juggling red balls, creating a moment of lighthearted joy.
Prompt
poses looking-at-each-other: excited, curious ; A group of tourists, standing in front of a famous landmark; medium shot; tourism; a bustling city street with people and vehicles passing by; cinematic
Characteristic
Shot : A woman in red is juggling in front of the Eiffel Tower with a group of people in the background.
Aesthetic Score : 0.6
Mood : casual, playful, touristy
Quality
Entropy : 6.93
Noise : 72
Prompt Clip Score : 0.23
AI Evaluation
Likelihood of AI : 0.10
Image errors : The image is slightly blurry and there are some minor artifacts.
A Moment of Peaceful Intimacy
Two young adults share a quiet moment by a window, gazing out at a serene rural landscape. The soft, warm lighting enhances the romantic and contemplative mood, as they seem to yearn for something beyond their view.
Prompt
poses looking-at-each-other: reflective, nostalgic ; Two friends, sitting on a train, looking out the window; medium shot; travel; a scenic landscape with rolling hills and fields; cinematic
Characteristic
Shot : Two young people sit by a window looking out at a green rolling landscape. The window is inside an old wooden structure. The scene is bathed in warm sunlight.
Aesthetic Score : 0.6
Mood : romantic, cozy, melancholic
Quality
Entropy : 6.09
Noise : 79
Prompt Clip Score : 0.32
AI Evaluation
Likelihood of AI : 0.20
Image errors : No visible errors
Campfire Companionship: A Cozy Gathering Under the Stars
A group of friends huddle around a crackling campfire, their faces illuminated by the warm glow. The scene exudes a cozy and friendly atmosphere, perfect for sharing stories and laughter under the open sky.
Prompt
poses looking-at-each-other: warm, intimate ; A group of friends, huddled together around a campfire; close-up; groups; a dark forest with stars twinkling in the sky; cinematic
Characteristic
Shot : A group of friends gathered around a campfire in the woods, lit by the fire and the glow of the night sky.
Aesthetic Score : 0.7
Mood : cozy, friendly, adventurous
Quality
Entropy : 6.34
Noise : 80
Prompt Clip Score : 0.27
AI Evaluation
Likelihood of AI : 0.20
Image errors : Slight blurriness in the background.
Silhouettes of Solitude: A Woman Walks into the Sunset
A poignant image captures a woman in a long coat walking along a tranquil beach at sunset. The soft blue and orange hues of the sky create a melancholic mood, while the silhouette of the woman against the setting sun evokes a sense of drama and loneliness. This peaceful scene invites contemplation and introspection.
Prompt
poses looking-at-each-other: melancholy, contemplative ; A lone figure, standing on a deserted beach; wide shot; adventure; a vast ocean with crashing waves and a setting sun; cinematic
Characteristic
Shot : A woman in a long coat walks on the beach at sunset. The sun is setting behind her, and the water is calm.
Aesthetic Score : 0.8
Mood : melancholy, contemplative, peaceful
Quality
Entropy : 6.41
Noise : 67
Prompt Clip Score : 0.28
AI Evaluation
Likelihood of AI : 0.10
Image errors : There are no visible artifacts or errors in the image.
A New Frontier: Astronauts Embark on a Mission of Discovery
Two astronauts, silhouetted against the breathtaking backdrop of Earth, stand poised for adventure. The image evokes a sense of wonder and optimism, capturing the boundless possibilities of space exploration.
Prompt
poses looking-at-each-other: awe-inspired, hopeful ; Two astronauts, floating in space; medium shot; heroism; a view of Earth from space with stars and galaxies in the background; cinematic
Characteristic
Shot : Two astronauts in white spacesuits are floating in space against a backdrop of a blue and green planet.
Aesthetic Score : 0.7
Mood : futuristic, hopeful, adventurous
Quality
Entropy : 6.90
Noise : 83
Prompt Clip Score : 0.25
AI Evaluation
Likelihood of AI : 0.80
Image errors : The image appears to be slightly compressed, resulting in some slight artifacts around the edges of the astronauts.
Adventure Awaits: Three Friends Explore a Mysterious Jungle Temple
A trio of young adventurers stand in a lush jungle clearing, their eyes drawn to a massive stone building shrouded in mystery. The scene exudes a sense of relaxed curiosity, hinting at the exciting discoveries that lie ahead. The balanced composition, with the figures forming a triangle in the foreground, adds to the intrigue and invites viewers to join their journey.
Prompt
poses looking-at-each-other: curious, adventurous ; A group of explorers, standing in a jungle clearing; medium shot; adventure; lush greenery with sunlight filtering through the leaves; cinematic
Characteristic
Shot : Three people, a man and two women, standing in a jungle setting with a large building in the background.
Aesthetic Score : 0.7
Mood : mysterious, adventurous, enigmatic
Quality
Entropy : 6.76
Noise : 86
Prompt Clip Score : 0.32
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image has some slight blurriness, particularly in the background.
A Romantic Embrace on the Illuminated Bridge
Experience the intimacy of a couple’s embrace on a bridge, beautifully lit by street lights against the backdrop of a stunning city skyline. The reflections in the water below add a touch of magic to this romantic scene, creating a perfect blend of love and cityscapes.
Prompt
poses looking-at-each-other: romantic, intimate ; Two lovers, standing on a bridge overlooking a city; medium shot; tourism; a cityscape with twinkling lights and a river flowing below; cinematic
Characteristic
Shot : A couple is embracing on a bridge with a city skyline in the background. The bridge is illuminated by street lights and reflections are visible in the water below.
Aesthetic Score : 0.7
Mood : romantic, intimate, cityscapes
Quality
Entropy : 6.79
Noise : 90
Prompt Clip Score : 0.30
AI Evaluation
Likelihood of AI : 0.20
Image errors : There is some noise in the image, particularly in the shadows.
Conclusion
The results show that the generative AI model performed well in understanding the scene and camera position, but struggled with the aesthetic aspect. Here’s a breakdown:
- Camera Position: The model scored 0.38, which is below the “good” range of 0.5 to 0.75. This suggests that the model didn’t fully capture the intended camera position described in the prompt.
- Shot Analysis: The model scored 0.58, which falls within the “good” range. This indicates that the model was able to understand the scene described in the prompt and create an image that reflects it reasonably well.
- Aesthetic Analysis: The model scored 0.01, which is within the “very good” range of -0.2 to 0.1. This means that the generated image’s aesthetic closely matched the expected aesthetic described in the prompt.
Overall, the model demonstrated a good understanding of the scene and shot composition, but needs improvement in accurately capturing the intended camera position. The aesthetic of the generated image was very close to the expected 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://api.bfl.ml/docs#/util/get_result_v1_get_result_get