Kuaishou's Kling research team just previewed Omni Director, a camera-control system that extracts full camera motions—from crane shots to cuts and bullet-time effects—directly from a reference clip and applies them to a new image. It moves video generation past clunky text prompts, though code and weights aren't out yet.
Researchers open-sourced ASASR, an image super-resolution tool built on FLUX.1-dev that delivers faithful 4x upscaling while suppressing distorted hallucinated details. It uses adversarial Sobolev DPO alignment and a dual-LoRA setup to preserve true structures. Code, model weights, and a browser demo on Hugging Face Spaces are now available.
Kling just unveiled 3D Move (3DiMo), an implicit motion control technique that transfers movement from a driving video to a new character while granting full camera control. Unlike prior tools locked to the original driving angle, it keeps 3D consistency through orbit and zoom shots. It is currently detailed in a paper without a public release.
Kuaishou just rolled out advanced voice and motion controls for its Kling 2.6 video model. Users can now train custom voices to keep characters sounding consistent across multiple clips, while an upgraded motion engine handles tricky movements like martial arts and dancing with sharper hands and tighter lip sync. Why it matters: AI characters just took a major leap toward believable acting.
Kling AI just launched upgraded Motion Control in VIDEO 2.6, promising sharper, blur-free captures for fast and complex movements like dancing and martial arts. Users can now upload 3 to 30-second motion reference clips to drive character actions, while refining scenes with text prompts.
Kling AI just dropped VIDEO 2.6, its first model capable of generating native audio alongside video. The update delivers coherent visuals and matching sound in one go, turning standard video clips into complete narrative multimedia experiences.
Kuaishou's Kling AI just opened submissions for its global short film contest, dangling a $42,000 prize pool and 1.25 million generation credits. The best entries will score screenings at major industry events including MIPCOM Cannes and the Tokyo International Film Festival, with the submission window closing on October 6.
Krea AI just integrated the new Kling 2.5 video model, bringing hyper-realistic output and complex motion simulation to its platform. Trained on over 10 billion video frames, the model cuts clip generation time down under 10 seconds while handling tricky physics far better. Why it matters: High-end synthetic video is getting faster and cheaper for everyday creators.
Kling AI just rolled out a new Avatar feature, integrating an upgraded version of its popular Lip Sync tool directly into the module. The update aims to make talking-head videos look much more natural. It is rolling out with limited access for now.
Kuaishou just rolled out Kling AI 1.0 worldwide, opening its Sora competitor to anyone with an email address. Users receive 66 free daily credits for text-to-video and image-to-video generation, complete with multi-format outputs and custom camera controls. While OpenAI keeps Sora behind closed doors, Kling is giving creators real access right now.
Kwai's research team just open-sourced LivePortrait, an efficient portrait animation model that brings still human or animal photos to life using driving videos. Unlike diffusion models, it uses implicit keypoints to clock in at just 12.8ms per frame on an RTX 4090.
