AITodayYour daily AI briefing

Video Generation

Sep 29, 2026

Video Generation

The Gist

Amazon Web Services is now offering compact video-generation models FLUX.2-klein-4B and Wan2.1-VACE-1.3B through SageMaker AI, while Runway's new GWM Worlds 2 generates real-time interactive worlds from text prompts. Synthesia has created the first journalist avatar trained on a single story, and Runway's AI film course is feeding a talent pipeline to studios as Chinese cities court AI filmmaker Zhu Zhili.

Today's Stories

  1. 1

    AWS shows FLUX.2-klein-4B and Wan2.1-VACE-1.3B on SageMaker AI

    AWS published a code sample deploying a real-time endpoint for FLUX.2-klein-4B image generation and an asynchronous endpoint for Wan2.1-VACE-1.3B video generation from one AWS vLLM-Omni DLC on SageMaker AI. Sharing one container across both models could simplify updates and consistency for teams running generative media, while separate endpoints let each model use the instance type and inference option that fits.

    The numbers AWS reports are single-run checkpoints, not benchmarks, so real throughput and latency will depend on prompts and instance availability. Watch the default 17 frames and 30 diffusion steps, and the note that four steps did not preserve source composition.

  2. 2

    Synthesia builds first journalist avatar, trained on one story

    Synthesia, a digital avatar startup valued at $4 billion, made an interactive avatar for a TechCrunch reporter at its New York office. It is trained only on her venture fraud story. The avatar answers press questions and runs on Synthesia's video, voice, and language models, pointing to a future where AI clones handle corporate communication and possibly journalism tasks.

    Whether avatar use spreads in corporate America hinges on trust and acceptance. The reporter predicts her Gen Z peers likely won't get used to digital twins.

  3. 3

    Runway's AI film course spawns talent pipeline for studios

    Runway launched its first AI filmmaking course in 2024 at NYU’s Martin Scorsese Virtual Production Center, and its tool training is now offered at USC, RISD, MIT, and Harvard. Studios find it easier to hire graduates who already know the tools than to train their own teams, so these courses are becoming a hiring pipeline.

    The value of this pipeline hinges on whether AI filmmaking skills become a standard requirement for production roles. Watch whether more schools adopt similar courses.

  4. 4

    Japan dethrone China in Asian Games men's team final as Wen Ruibo falls

    Japan beat China 3-2 in the Asian Games men's team final, as Sora Matsushima defeated Wen Ruibo in the decisive match, ending China's gold run since 1994. The result ended a streak that had lasted at every Games since 1994, a run one player described as proof the team had lacked confidence before.

    Whether the result holds as a turning point hinges on China's depth, which one player said used to mean six or seven strong players, while Japan now has two in the world top five.

  5. 5

    China's cities court AI filmmaker Zhu Zhili

    AI filmmaker Zhu Zhili, who picked Shenzhen for his AI film studio two years ago, says cities and industrial parks across China now call him daily to pitch relocating there. The pitches suggest local governments are competing to host AI film businesses, a shift for a filmmaker who once saw only one clear base.

    Whether any city's offer actually moves Zhu's studio is unclear; the article names no deal, subsidy or timeline, so the courtship remains just that.

  6. 6

    Runway's GWM Worlds 2 lets you prompt real-time worlds

    Runway released GWM Worlds 2, a research preview that turns video and audio generation into real-time interactive simulation, featuring WorldPrompt for setting the first frame and adding timestamped actions in real time. Runway is reportedly valued at $5.3 billion after a $315 million fund raise in February, and WorldPrompt helps differentiate it from Google DeepMind's Genie 3, Odyssey-2 Pro, and World Labs' RTFM.

    CTO Kamil Sindi says more training plus scaling data and models is resulting in better following, but the research preview has flaws and long-term memory remains an open research problem.

What to Watch

For everyday viewers, the real test is whether these early demos turn into reliable tools: watch whether AI video quality holds up beyond cherry-picked examples, especially around frame counts, motion steps, and long-term memory. Also keep an eye on whether AI filmmaking courses spread to more schools, whether digital avatars win trust at work, and whether China and Japan's studio rivalries, city wooing of top talent, and new model upgrades shift who leads next.

Sources

Share this with a friend

Send today's roundup to anyone who wants to keep up.

Get daily AI news free with AIToday

Today's AI, for Today's work. Email / LINE / Slack.

Sign up free