Gen-2 evolves video generation! New visual expressions from text and images are now possible.
Runway Research | Gen-2: Generate novel videos with text, images or video clips
Original: Runway Research | Gen-2: Generate novel videos with text, images or video clips
Importance: 新機能の追加は多くのユーザーに影響を与えるため
Summary
Runway has announced Gen-2, a new multimodal AI system that generates novel videos from text, images, or video clips. It synthesizes realistic and consistent new videos by applying styles from images or text prompts to existing video structures. Gen-2 allows users to create videos in any imagined style using just text prompts, expanding creative possibilities.
Key Points
- Generate videos from text and images
- Includes style transfer feature
- Customizable Gen-1 for better results
- New creative expression possibilities
- Meets user expectations
View developer notes (APIs, breaking changes, migration)
Gen-2 offers Text to Video and Video to Video capabilities. Users can generate videos using a driving image and a text prompt, and the style transfer feature allows any image or prompt's style to be applied to every frame. Additionally, customizing Gen-1 enhances fidelity results.
Source: https://runwayml.com/research/gen-2
Outlet: Runway
This article is an AI-generated summary (OpenAI GPT-4o-mini) of publicly available information from Anthropic, OpenAI, Google, Meta, Mistral, DeepSeek, Sakana, and other vendors. The original source URL is always provided in accordance with fair-use citation requirements. Summaries are AI-generated and may contain mistranslations or misinterpretations. Always verify details with the original source.