Higgsfield AI（在新窗口中打开） 的使命是让任何有创意的人都能进行专业视频和图像创作。在 GPT‑6 Astra 之前，这些视频最长只有大约一分钟。如今，首席执行官兼联合创始人 Alex Mashrabov 表示，用户可以创建超过 10 分钟的视频。
更长的视频只是 Higgsfield AI 帮助小型创意团队承担更宏大工作的一种方式。据 Alex 称，借助 GPT‑6 Astra 和 GPT‑Image‑2.5 等模型，单个创作者现在可以从头到尾执行高端时尚活动。
“对我们 Higgsfield 来说，最重要的是看到小型创意团队现在借助 GPT-6 Astra 和 GPT-Image-2.5 等模型的力量，实际上可以更加成功。”
—Alex Mashrabov，Higgsfield AI 首席执行官兼联合创始人
借助 GPT‑6 Astra 实现更长的视频
Higgsfield AI 的创意代理承担重复性的制作任务，例如为同一个镜头创建多个变体。借助 GPT‑6 Astra，这些代理还可以调用外部工具来处理 3D 建模中复杂的手动工作。Alex 表示，这一能力有助于解决创意 AI 最困难的问题之一：在更长视频中保持一致性。
证据可以在 Higgsfield AI 自己的 YouTube 频道上看到，Alex 称该频道拥有近 50 万订阅者。该频道教创意人士如何使用 AI 模型和工作流程。过去，Higgsfield AI 制作这些内容需要大量人工投入。但借助 GPT‑6 Astra，团队构建了一个工作流程，使用 AI 生成超过 10 分钟的教学视频。
能够创建更长的教学视频对 Alex 个人也很重要。他支持哈萨克斯坦的乡村学校，并描述了早期利用 GPT‑6 Astra 的视觉理解来识别学生可能遇到困难的主题，并创建针对他们学习需求定制的视频。
借助 GPT‑Image‑2.5 为小企业提供更精确的图像
对于创建宣传内容的小企业来说，可读文本和精确信息图可能与图像本身同样重要。Alex 表示，GPT‑Image‑2.5 让没有大额制作预算的企业也能制作这类内容。
“GPT‑Image‑2.5 是最先进的，也是同类模型中第一个能够在图像之上可靠呈现文本和信息图的模型，”他说。
借助 Codex 实现从创意到产品的更快路径
Higgsfield AI 通过约 200 名创意人员和 100 名工程师之间的紧密协作来构建其产品。Alex 分享说，Codex 赋予创意团队“一名真正强大软件工程师的能力”。
创意人员使用 Codex 将他们的想法转化为软件原型。此前，将这些原型投入生产需要前端和后端工程师的大量参与。现在，Alex 表示 GPT‑6 Astra 减少了将这些想法带入产品所需的工作。
“GPT-6 Astra 可以交付生产就绪的代码，这在以前从未可能。”
—Alex Mashrabov，Higgsfield AI 首席执行官兼联合创始人
Alex 表示，随着原型制作和生产之间的摩擦减少，Higgsfield AI 可以更快地开发和交付更好的产品。
展望借助 GPT‑Live‑1 实现语音到视频
接下来，Higgsfield AI 希望创作者能够描述一个想法，并在他们说话时看到它成形。Alex 将这一愿景称为“语音到电影”，即 AI 理解创作者的口头意图并实时呈现他们的愿景。
他认为 OpenAI 在规划、工具调用、图像生成和语音方面的进步正在让这种体验更接近现实。他将该公司的语音模型描述为“在语音理解以及日常交流方面都是同类最佳”。
对 Higgsfield AI 来说，其目标是让创作一部电影更像是在描述一个想法，由 AI 处理中间更多的工作。
Higgsfield AI(opens in a new window) is on a mission to make professional video and image creation accessible to anyone with an idea. Before GPT‑6 Astra, those videos topped out at around one minute. Now, says CEO and co-founder Alex Mashrabov, users can create videos over 10 minutes long.
Longer videos are just one way Higgsfield AI helps smaller creative teams take on more ambitious work. According to Alex, with models like GPT‑6 Astra and GPT‑Image‑2.5, it’s now possible for a single creator to execute high-end fashion campaigns from start to finish.
“What’s most important for us at Higgsfield is to see that smaller creative teams can actually be more successful now with the power of models like GPT-6 Astra and GPT-Image-2.5.”
—Alex Mashrabov, CEO and co-founder, Higgsfield AI
Making longer videos possible with GPT‑6 Astra
Higgsfield AI’s creative agents take on repetitive production tasks, such as creating multiple variations of a shot. With GPT‑6 Astra, those agents can also call external tools to handle complex, manual work in 3D modeling. Alex says that capability helps address one of creative AI’s hardest problems: maintaining consistency across longer videos.
The evidence can be seen on Higgsfield AI’s own YouTube channel, which Alex says has almost half a million subscribers. The channel teaches creatives how to use AI models and workflows. It used to require considerable manual effort for Higgsfield AI to produce that content. But with GPT‑6 Astra, the team has built a workflow that uses AI to generate instructional videos over 10 minutes long.
Being able to create longer instructional videos also matters to Alex personally. He supports rural schools in Kazakhstan and describes an early effort using GPT‑6 Astra’s visual understanding to identify topics students may be struggling with and create videos tailored to what they need to learn.
More precise images for small businesses with GPT‑Image‑2.5
For small businesses creating promotional content, having readable text and precise infographics can be just as important as the image itself. GPT‑Image‑2.5 makes that kind of content possible for businesses without large production budgets, Alex says.
“GPT‑Image‑2.5 is state of the art and the first model of its kind that can reliably render the text and infographics on top of the imagery,” he says.
Enabling a faster path from creative idea to product with Codex
Higgsfield AI builds its product through close collaboration between around 200 creatives and 100 engineers. Codex gives the creative team “the power of a really strong software engineer,” shares Alex.
Creatives use Codex to turn their ideas into software prototypes. Previously, bringing those prototypes into production required heavy involvement from front-end and back-end engineers. Now, Alex says GPT‑6 Astra reduces the work needed to bring those ideas into the product.
“GPT-6 Astra can ship production-ready code, which was never possible before.”
—Alex Mashrabov, CEO and co-founder, Higgsfield AI
With less friction between prototyping and production, Alex says Higgsfield AI can develop and ship better products faster.
Looking ahead to voice-to-video with GPT‑Live‑1
Next, Higgsfield AI wants creators to be able to describe an idea and see it take shape as they talk. Alex calls that vision “voice to movie,” with AI understanding a creator’s spoken intention and rendering their vision in real time.
He sees OpenAI’s advances in planning, tool calling, image generation, and voice bringing that experience closer. He describes its voice model as “best in class for voice understanding and just for regular communication.”
For Higgsfield AI, the ambition is to make creating a film feel more like describing an idea, with AI handling more of the work in between.
本文内容采集自官方网站，排版和翻译可能与原页面存在差异。
阅读官方全文