Gen-2 is one of the commercialized text-to-video models, and this area is considered the next step in AI after image and text generation.
The video Gen-2 produces has a low frame rate, making it look like a slideshow, and the image quality also appears to be curved.
Gen-2 has a problem with understanding content, tending to stick to certain predicates in prompts and ignore others.
Runway trained its Gen-2 model on 240 million images and 6.4 million video clips.
Gen-2 passes the superficial bias test, showing slightly higher diversity
Gen-2 is currently more of a mirage or a toy than a useful tool in video workflows.
Gen-2 can actually understand a variety of styles, including animation and claymation, and can be used to create interesting pieces by linking together several clips.
In response to concerns about deepfakes, Runway claims to combine AI and human censorship to prevent users from creating videos that are pornographic, violent, or copyright-infringing.
Subscribe to 'haebom'
📚 Welcome to Haebom's archives. --- I post articles related to IT 💻, economy 💰, and humanities 🎭. If you are curious about my thoughts, perspectives or interests, please subscribe. Would you like to be notified when new articles are posted? 🔔 Yes, that means subscribe. haebom@kakao.com
