Today, multimodal AI company Higgsfield announced the release of Diffuse 2.0, a host of AI video generation features that "remove the burden of production and reduce personal storytelling to minutes instead of days."

Diffuse touts itself as an entertainment app that specializes in generating meaningful stories and videos using AI to convert text into video Diffuse 2.0 combines TikTok's self-discovery capabilities with the choices and episodes found in It builds on top of this framework by combining storytelling content to help create more dynamic videos. Along with this new design are several new and upgraded features.

Selfie Animator is a full-featured photo animation tool that preserves the subject's face, clothing, and background. New video templates add life and movement, and the Stories feature places the user in a scripted story with AI visuals.

Diffuse 2.0 also includes a feature called Video Snacks, which uses user-provided details to create personalized vignettes or video-to-video stylizations that can turn a video into several different styles In other words, you can use Diffuse 2.0 to create a video that is more than just a video. In other words, Diffuse 2.0 finally features a text-to-video builder, making it easier than ever to create AI videos from scratch.

The tool may not be on everyone's radar yet, but since its launch in 2024, it has gained 1 million followers, 50% of whom share content with others.

"Video accounts for 80% of web traffic and has become the de facto way people express themselves," commented Alex Mashalbov, creator of Higgsfield AI.

"But creating high-quality videos is difficult, costly, and time-consuming.

Currently, Diffuse is available for both iOS and Android, but requires a subscription for continued use.13]

For image generation enthusiasts, there is a great list of the best AI image generators available today, as well as the best AI tools and 2024 devices, with a comprehensive list of the best AI tools and devices available.