Runway Releases Gen-3 Alpha Extensions Feature allowing Video Length to be Extended to 40 Seconds

AIbase基地

Published inAI News · 3 min read · Sep 2, 2024

433

Runway continues to push the boundaries of AI video generation technology with its latest release, the Gen-3Alpha Extensions, garnering significant industry attention. This update extends the video generation duration to 40 seconds and is now available to all users, revolutionizing digital content creation.

The feature allows users to create complete storylines or advertising content with just simple image or text inputs. This breakthrough will have a profound impact on advertising production, short video creation, and other fields, significantly enhancing creative efficiency.

Runway has been active recently, showcasing strong innovative capabilities. In addition to launching the Gen-3Alpha Turbo version, which boosts video generation speed by seven times, the company continues to refine its product features.

Notably, Runway added start and end frame control to the Gen-3Alpha image-to-video feature in early August. Users can anchor AI-generated videos with specific images, effectively solving consistency and predictability issues in AI video creation. Creators can now more precisely control the beginning and ending frames of videos, ensuring the generated content meets expected outcomes.

These technological breakthroughs and feature upgrades are reshaping the possibilities of AI-assisted creation. Whether for professional creators or ordinary users, these tools enable rapid realization of ideas, not only improving content production efficiency but also opening new avenues for creative expression.

Product website: https://top.aibase.com/tool/runwayml

Motion Controllable! Step-Video-TI2V, an Open-Source Text-to-Video Model

Shanghai Step Star Intelligent Technology Co., Ltd. has announced the open-source release of its latest text-to-video model, Step-Video-TI2V. Trained on a 30B parameter Step-Video-T2V model, it generates 102-frame, 5-second videos at 540P resolution. Key features include controllable motion amplitude and camera movement, performing particularly well in generating anime-style videos.

Tencent Open-Sources New Image-to-Video Model: HunyuanVideo-I2V

Tencent has announced the open-sourcing of its newly developed image-to-video generation framework, HunyuanVideo-I2V. This release follows the successful open-sourcing of HunyuanVideo and aims to further advancements within the open-source community. HunyuanVideo-I2V incorporates cutting-edge video generation technology, enabling the transformation of static images into dynamic video content, offering creators expanded possibilities. HunyuanVideo-I2V leverages a pre-trained...