AI's Artistic Journey: Capturing Poses, But Missing the Essence with Scenario
- 10 minutes read - 2017 wordsTable of Contents
Dramatic poses are a powerful tool in visual storytelling, conveying emotions and narratives through body language. From the heroic stance of a knight to the awe-struck gaze of a tourist, these poses evoke specific feelings and draw the viewer into the scene. In this experiment, we tasked an AI model with generating images based on various poses and scenes, aiming to understand its ability to capture the essence of these dramatic postures. While the model demonstrated proficiency in shot composition, it fell short in capturing the desired aesthetic and camera angles, highlighting the ongoing challenges in AI’s artistic journey.
Created with: scenario
A Knight’s Contemplation at Sunset
A female knight, clad in shining armor, stands on a rocky cliff, her cloak billowing in the wind as she gazes out at a vast, rolling landscape bathed in the golden hues of sunset. The dramatic lighting and her powerful pose evoke a sense of strength and contemplation, capturing the epic spirit of a warrior at peace.
Prompt
poses three-quarter-pose: determined, resolute, heroic ; A lone knight, standing tall on a windswept hilltop; three-quarter pose; Heroism; a vast, stormy landscape with a distant castle in the background; cinematic
Characteristic
Shot : A female knight in full armor stands on a rocky outcropping, gazing out over a vast, rolling landscape. The sun is setting, casting a warm glow over the scene.
Aesthetic Score : 0.7
Mood : epic, powerful, dramatic
Quality
Entropy : 6.79
Noise : 89
Prompt Clip Score : 0.25
AI Evaluation
Likelihood of AI : 0.70
Image errors : There are some minor artifacts in the background, particularly around the edges of the hills.
Hope Amidst the Ruins: A Woman’s Journey into the Unknown
A solitary figure stands in a lush jungle, her gaze fixed on the distant horizon. The setting sun casts long shadows, illuminating ancient ruins that whisper tales of forgotten civilizations. Her hopeful expression contrasts with the mysterious and potentially dangerous surroundings, creating a sense of adventure and anticipation. This captivating scene evokes a mood of exploration, mystery, and the promise of new beginnings.
Prompt
poses three-quarter-pose: adventurous, curious, hopeful ; An intrepid explorer, silhouetted against the setting sun, holding a map; three-quarter pose; Adventure; a dense jungle with ancient ruins in the distance; cinematic
Characteristic
Shot : A woman explorer in a jungle, holding a map in her hands, looking to the horizon, at sunset.
Aesthetic Score : 0.8
Mood : adventurous, mysterious, hopeful
Quality
Entropy : 6.84
Noise : 97
Prompt Clip Score : 0.27
AI Evaluation
Likelihood of AI : 0.80
Image errors : The woman’s hand holding the map is a bit blurry.
Lost in the Neon Dreams: A Cyberpunk Vision of the Future
A young woman, immersed in a futuristic headset, gazes out at a vibrant, glowing cityscape. The scene, bathed in soft pink and purple hues, evokes a dreamy, cyberpunk aesthetic. Her focused expression and the captivating backdrop create a sense of wonder and anticipation for what lies ahead in this technologically advanced world.
Prompt
poses three-quarter-pose: focused, intense, exhilarated ; A gamer, eyes glued to the screen, fingers flying across the keyboard; three-quarter pose; Gaming; a brightly lit gaming room with neon lights and a futuristic cityscape projected on the wall; cinematic
Characteristic
Shot : A woman wearing futuristic glasses sits at a computer desk looking at the screen. Behind her is a futuristic city and a pink sunset.
Aesthetic Score : 0.7
Mood : futuristic, cyberpunk, mysterious
Quality
Entropy : 6.78
Noise : 86
Prompt Clip Score : 0.30
AI Evaluation
Likelihood of AI : 0.90
Image errors : The woman’s hair appears to be slightly blurry and the background is slightly out of focus.
A Romantic Rendezvous in Paris: A Woman’s Dreamy Adventure
Experience the enchanting allure of Paris as a woman in a brown coat stands amidst its bustling streets, with the iconic Eiffel Tower gracing the background. The scene is set with a romantic and dreamy mood, as bicycles line the roadside and buildings tower above. This dramatic image captures the essence of a Parisian adventure, perfect for those seeking a touch of European charm.
Prompt
poses three-quarter-pose: amazed, joyful, curious ; A tourist, gazing in awe at the Eiffel Tower, camera in hand; three-quarter pose; Tourism; a bustling Parisian street with cafes and shops lining the sidewalk; cinematic
Characteristic
Shot : A woman in a brown coat walks down a cobblestone street in Paris, with the Eiffel Tower in the background.
Aesthetic Score : 0.8
Mood : romantic, charming, Parisian
Quality
Entropy : 6.84
Noise : 101
Prompt Clip Score : 0.27
AI Evaluation
Likelihood of AI : 0.10
Image errors : The image is slightly overexposed and the colors are a little bit washed out.
Conquering the Peak: A Moment of Triumph and Serenity
A lone hiker stands victorious on a snow-covered mountaintop, arms outstretched, taking in the breathtaking panorama of snow-capped peaks and a misty valley. The scene evokes a sense of adventure, freedom, and awe, capturing the essence of a triumphant moment in nature.
Prompt
poses three-quarter-pose: free, exhilarated, adventurous ; A backpacker, standing on a mountain peak, arms outstretched, enjoying the view; three-quarter pose; Travel; a breathtaking panorama of snow-capped mountains and valleys; cinematic
Characteristic
Shot : A lone hiker stands on a snowy mountain peak with arms raised in victory, overlooking a valley filled with fog and snow-capped mountains in the distance.
Aesthetic Score : 0.8
Mood : triumphant, serene, inspiring
Quality
Entropy : 6.62
Noise : 87
Prompt Clip Score : 0.27
AI Evaluation
Likelihood of AI : 0.10
Image errors : No visible artifacts or errors.
Campfire Magic Under a Starry Sky
Four friends gather around a crackling campfire, bathed in the warm glow of the flames and the ethereal light of a million stars. The cozy scene evokes a sense of friendship, warmth, and wonder, with a tent nestled in the background, promising a night of adventure under the open sky.
Prompt
poses three-quarter-pose: happy, relaxed, connected ; A group of friends, laughing and sharing stories around a campfire; three-quarter pose; Groups; a serene forest clearing with stars twinkling in the night sky; cinematic
Characteristic
Shot : A group of three friends are sitting around a campfire in a forest, under a starry night sky. A tent is pitched behind them, and a lake can be seen in the background.
Aesthetic Score : 0.8
Mood : cozy, friendly, nostalgic
Quality
Entropy : 6.57
Noise : 100
Prompt Clip Score : 0.29
AI Evaluation
Likelihood of AI : 0.80
Image errors : The image has some minor artifacts, such as the slightly blurry leaves in the background. Some of the details in the background are not as well-defined as they could be.
Captain Marvel Stands Tall Amidst the Chaos
A powerful image captures Captain Marvel on a rooftop, overlooking a city engulfed in smoke. Her confident stance and determined gaze convey her strength and unwavering resolve in the face of danger.
Prompt
poses three-quarter-pose: powerful, victorious, confident ; A superhero, standing triumphantly over a defeated villain; three-quarter pose; Heroism; a cityscape with smoke and debris in the background; cinematic
Characteristic
Shot : A female superhero, Captain Marvel, stands on a rooftop overlooking a cityscape with a large cloud of smoke in the background.
Aesthetic Score : 0.7
Mood : powerful, determined, hopeful
Quality
Entropy : 6.89
Noise : 86
Prompt Clip Score : 0.28
AI Evaluation
Likelihood of AI : 0.50
Image errors : The smoke cloud in the background looks a bit artificial and the lighting on the superhero seems a little off.
Three Women Embark on a Snowy Mountain Adventure
A trio of determined hikers traverse a breathtaking snowy landscape, their backs to the viewer as they journey towards an unknown destination. The bright blue sky and snow-capped peaks create a sense of adventure and hope, capturing the spirit of exploration.
Prompt
poses three-quarter-pose: determined, focused, adventurous ; A group of adventurers, navigating a treacherous mountain path; three-quarter pose; Adventure; a rugged mountain range with snow-covered peaks and a deep valley below; cinematic
Characteristic
Shot : Three women are hiking through a snowy mountain range. The women are wearing winter gear, including backpacks and hiking poles. The mountains are majestic and the scene is peaceful and serene.
Aesthetic Score : 0.7
Mood : peaceful, adventurous, serene
Quality
Entropy : 6.59
Noise : 95
Prompt Clip Score : 0.26
AI Evaluation
Likelihood of AI : 0.80
Image errors : The image quality is good, but there are a few minor artifacts, such as the slight blur around the edges of the women’s figures. The mountain range in the background appears somewhat artificial, particularly the lack of detail in the snow and mountains.
Pizza, Cards, and City Lights: A Night of Fun with Friends
A group of six young adults gather around a table, enjoying pizza, playing cards, and sharing laughter in a dimly lit room with a stunning cityscape view. The warm lighting and casual setting create a sense of intimacy and comfort, capturing the essence of a fun and playful night with friends.
Prompt
poses three-quarter-pose: focused, competitive, excited ; A group of gamers, huddled around a table, strategizing their next move; three-quarter pose; Gaming; a dimly lit room with flickering computer screens and a stack of pizza boxes; cinematic
Characteristic
Shot : A group of young people are gathered around a table, enjoying a pizza together. The scene is warm and inviting, with soft lighting and a casual atmosphere.
Aesthetic Score : 0.7
Mood : friendly, casual, warm
Quality
Entropy : 6.70
Noise : 92
Prompt Clip Score : 0.22
AI Evaluation
Likelihood of AI : 0.80
Image errors : The image is well-composed and there are no obvious technical errors. The lighting is slightly unnatural and the shadows are not very realistic.
Family Joy in Front of a Majestic Building
A heartwarming image captures a family of three, radiating happiness as they stand before a grand, ornate structure. The father’s arm around the mother, who holds their son, symbolizes their bond and love. The scene evokes a sense of joy, togetherness, and the beauty of family moments.
Prompt
poses three-quarter-pose: happy, joyful, memorable ; A family, standing in front of a famous landmark, smiling for a photo; three-quarter pose; Tourism; a vibrant city square with colorful buildings and street performers; cinematic
Characteristic
Shot : A family of three, a man, a woman, and their young son, are standing in front of St. Basil’s Cathedral in Moscow, Russia. The man is wearing a light blue shirt and khaki pants, the woman is wearing a blue floral dress, and the boy is wearing a light blue shirt and gray pants.
Aesthetic Score : 0.7
Mood : happy, joyful, touristy
Quality
Entropy : 6.71
Noise : 91
Prompt Clip Score : 0.25
AI Evaluation
Likelihood of AI : 0.10
Image errors : There are no noticeable errors in the image.
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 0.4, 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 0.58, which is considered good. This indicates the generated image’s shot composition was fairly close to what was described in the prompt.
- Aesthetic Analysis: The model scored 0.26, which is considered okay. This means the generated image’s aesthetic was somewhat different from what was expected based on the prompt.
Overall, the model seems to be better at understanding and implementing shot composition than camera position or aesthetic. It might need further training to improve its ability to accurately capture the desired aesthetic and camera angles.
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://www.scenario.com