Higgsfield takes AI video from 1 minute to over 10
· Source: OpenAI Blog
Higgsfield has announced a suite of upgrades that expand the capabilities of AI‑driven audiovisual content creation. The company is rolling out the GPT‑6 Astra model, which lets users produce longer videos—moving from the typical one‑minute format to over ten minutes—while maintaining narrative coherence. In addition, GPT‑Image‑2.5 is introduced as a tool focused on generating images with greater precision and detail, resulting in visuals that more accurately reflect the creator’s instructions. Finally, Higgsfield unveils GPT‑Live, a solution that enables voice‑based film production, converting spoken scripts into visual material without the need for traditional filming equipment. These innovations aim to streamline the creative process, reduce reliance on technical resources, and open new opportunities for creators who want to produce more extensive and visually engaging content with less effort.
The story is significant because it illustrates how AI is democratizing audiovisual production, allowing a broader audience to generate professional‑quality material and potentially reshaping the dynamics of the digital content market.
Read the original article on OpenAI Blog
This summary is an informational synthesis produced by dataqbs.com. All rights to the original content belong to its author and the cited media outlet. We act solely as curators of technology news and claim no authorship.