Share
Sign In
🌐 AI Video Showdown 🎬⚔️
Tokyo Walk (Sora, Original Video 2024.02)
Sora | A stylish woman walks down a Tokyo street filled with warm glowing neon and animated city signage. She wears a black leather jacket, a long red dress, and black boots, and carries a black purse. She wears sunglasses and red lipstick. She walks confidently and casually. The street is damp and reflective, creating a mirror effect of the colorful lights. Many pedestrians walk about. | Sora AI interprets a six-sentence prompt to generate a consistent and complete one-minute professional-level video. Directs a Tokyo street scene with long takes from various angles, with the subject, background, and crowds on the street. From the composition that focuses on the person in the center of the building and the runway, to the realistic gait, the reality of the wet neon street and the reflections on sunglasses, the maintenance of consistent color tones and mood, the detail of skin and shadows, and the description of specific props such as bags and earrings. A case where everything from story making to professional camera direction, shooting, and cut-editing was done by AI under the simple direction of the user. Tokyo walk, re-mastered by mintbear |
Tokyo Walk (I2V)
I created by below Midjourney Image and Text Prompt(Sora)
A stylish woman walks down a Tokyo street filled with warm glowing neon and animated city signage.
She wears a black leather jacket, a long red dress, and black boots, and carries a black purse.
She wears sunglasses and red lipstick. She walks confidently and casually.
The street is damp and reflective, creating a mirror effect of the colorful lights. Many pedestrians walk about.
She wears a black leather jacket, a long red dress, and black boots, and carries a black purse.
She wears sunglasses and red lipstick. She walks confidently and casually.
The street is damp and reflective, creating a mirror effect of the colorful lights. Many pedestrians walk about.
Gen-3 Alpha 🌟🌟🌟🌟🌟 | Kling 1.5 🌟🌟🌟🌟 |
Luma 1.6 🌟🌟🌟 | Vidu 🌟🌟🌟 |
Tokyo Walk (T2V)
Use only Text Prompt
Gen-3 Alpha 🌟🌟🌟 | 🌟🌟🌟🌟🌟 Kling 1.5 🌟🌟🌟🌟🌟 |
Luma 1.6 🌟🌟🌟 | Vidu 🌟 |
Minimax 🌟 |
Jelly Fish (T2V)
🌟🌟🌟🌟🌟 VEO original video 🌟🌟🌟🌟🌟
Use only Text Prompt
Gen-3 Alpha 🌟🌟🌟 | 🌟🌟🌟🌟🌟 Kling 1.5 🌟🌟🌟🌟🌟 |
Luma 1.6 🌟🌟🌟 | Vidu 🌟 |
Minimax 🌟 |
It is difficult to evaluate in batches because the learning data varies depending on the tool.
Each tool produces different images in different areas.
The interpretation and presentation of text prompts and images are all different.
The recommended grammar for prompts varies for each tool.
However, in general, Gen3 and Kling have the best video quality.
Sora and Kling's prompt grammar interpretation and usage seem very similar (fit well)