Kandinsky 6.0 Video puts synchronized audio into an open diffusion model
AspireAI community · huggingface.co
Kandinsky 6.0 Video puts synchronized audio into an open diffusion model
Russia's Kandinsky Lab released Kandinsky 6.0 Video on Oct 6-7, 2026: diffusion models that generate 5-second clips with synchronized 44 kHz audio from a text prompt or input image — dialogue, ambient sound, and lip-sync that tracks the picture. Two checkpoints: Lite (3B, open weights) and Pro (29B, gated).
The architecture is a dual-stream CrossDiT: a pretrained video transformer linked to a freshly trained audio transformer through bidirectional cross-attention. Training went in stages — audio first, joint, RL post-training, then distillation. Weights and code are MIT and integrated into Diffusers, ComfyUI, vLLM-omni, SGLang, and FastVideo on day one.
Vendor human-eval says Pro beats the prior 5.0 Pro and stays competitive with closed audio-video models on speech. Single qualitative claim from the tech report — independent numbers aren't in yet.
Source:
Read the story and explore more from the AspireAI community.
Two critical PHP remote code execution flaws — one found by GPT-5.6 Sol — were patched on October 21, 2026, and OpenAI published a disclosure framework alongside the fix. Fixed versions: PHP 8.5.12, 8.4.27, 8.3.36 and 8.2.35. Both allow unauthenticated remote code execution, and PHP's advisory says risk is highest for mod_php, where a demonstrated exploit triggers before any application code runs. The CVEs are distinct failure modes. CVE-2026-109618 (OOM corruption): out-of-memory handling can interrupt PHP while internal request data is only partially initialized, and request cleanup may then treat the invalid data as valid. CVE-2026-109619 (stale global state): request-owned internal state can survive after its backing memory is freed, and a later request served by the same worker may use that stale state. OpenAI states GPT-5.6 Sol identified the first flaw through its Patch the Planet initiative, and that Wiz independently discovered and reported both vulnerabilities. PHP's maintainers led the fixes and release, with Wiz, Cloudflare and OpenAI contributing research and coordination. Wiz's write-up adds that it used GPT-5.6 Sol and Gemini 4 Argon throughout, with Gemini 4 Argon contributing to finding the vulnerability and validating the patch. OpenAI describes the gap between discovery and public exploitation as a "Defender's Window," proposes a five-stage response framework, and committed $1 billion in subsidised Daybreak model access for organizations with limited security resources. Honest caveats: these are OpenAI's and Wiz's own characterizations, and OpenAI also notes the same capabilities help attackers build offensive tooling faster. PHP 8.1 and older no longer receive updates from the PHP project.