Video Generation

Today's Stories

1. 1

   kling-4.org writer: continuity log for AI video

   A writer for the independent kling-4.org site proposed a continuity log for AI video work — three shared anchors plus a text table of settings, references and review notes. The log is meant to make comparisons less confusing when a frame changes, since it helps show whether a different reference, instruction or setting caused it, though the record does not establish causation.

   The author states the log cannot guarantee matching footage and is a proposed workflow, not a report of generation tests; the same method is said to work for text- and image-based experiments.

2. 2

   Manus 2.0 launches as a platform for video, games, personal agents

   Manus launched version 2.0, adding a Video Editor and Game Dev environment to its new Manus Studio desktop app, event-triggered automations, Computer Use on approved files and apps, and a separate app called Cue with free early access. Turning the agent into a platform means the same tool now covers video editing, hosted games, and personal agents—and users can direct their own computer remotely from a phone.

   Manus 2.0 is available now, but Cue needs an invite code for free early access, so wider use likely hinges on how quickly those invites go out. The competition is unresolved: Meta acquired Manus in late 2025, had to unwind after Beijing blocked it, and Tencent has been negotiating for the largest stake.

3. 3

   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.

4. 4

   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.

5. 5

   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.

6. 6

   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.