Kandinsky Lab open-sourced Kandinsky 6.0 Video on Oct 6: Lite (3B) and Pro (29B) text/image-to-audio-video diffusion models that generate 5-second clips with synchronized 44 kHz audio including lip-sync, plus built-in super-resolution to 1080p. Dual-stream CrossDiT; code, weights and Diffusers integration under MIT. The report claims it beats open LTX 2.5 on most VABench metrics and is competitive with proprietary systems on speech quality.
Key Takeaways
- ✓Scale: Lite 3B / Pro 29B; Pro = 19B video stream + 5B audio stream + 5B cross-attention (report)
- ✓Output: 5 s clips with synchronized 44 kHz audio incl. lip-sync, T2AV and I2AV, built-in SR to 1920×1080
- ✓Evals: beats open LTX 2.5 on most VABench metrics; trades wins with Veo 3.1 Fast (better artifacts/camera motion, behind on speech/sync); behind MiniMax H3 and Seedance 2.0 on visuals
- ✓Speed: distilled to 10 NFE with 51% vs 49% human preference vs full model; non-distilled Pro Full HD ≈402 s on H100, ≈1247 s on RTX 4090
- ✓Deploy: block offload cuts Pro SD peak memory 72.8 → 21.7 GiB, 16 GB preset; Diffusers, ComfyUI and vLLM-Omni support; MIT license

Turn your technical choice into a development budget
Compare 40 dev plans & simulate token costs vs $20/mo subscriptions
Project Links & Resources
Direct AccessIn-Depth Technical Analysis
Background
Joint audio-video generation (dialogue, sound effects and lip-sync in one pass) has been dominated by closed systems such as Veo 3.1 and Sora 2. Kandinsky Lab's Kandinsky 6.0 Video open-sources the full stack under MIT: Lite (3B) and Pro (29B) models generating 5-second clips with synchronized 44 kHz audio in T2AV and I2AV modes, with a built-in super-resolution model up to 1920×1080.
Architecture
A dual-stream CrossDiT reuses the Kandinsky 5.0 video stream and adds a newly trained audio stream, connected blockwise by bidirectional cross-attention (3D RoPE for video, 1D RoPE for audio). Pro splits into 19B video + 5B audio + 5B cross-attention. Training: audio stream pretrained alone, then joint audio-video training, SFT, RL post-training and two-stage distillation to 10 function evaluations.
Benchmarks
Per the technical report: beats open LTX 2.5 on most VABench metrics; clearly beats Kandinsky 5.0 Pro in human SBS; trades wins with Veo 3.1 Fast (significantly better artifacts and camera motion, behind on speech and sync); behind MiniMax H3 and Seedance 2.0 on visuals while competitive on speech. Distilled vs full model preference is 51% vs 49%. All numbers are self-reported.
Getting started
NVIDIA GPU + Python 3.13/3.14, then just setup, just download pro-distill, just generate "a cat on a mat". Block offload cuts Pro SD peak memory from 72.8 to 21.7 GiB, with a 16 GB preset; non-distilled Pro Full HD takes ~402 s on H100. Try the HF Space, the ComfyUI node or the Diffusers collection.
This story is not about one specific product. Compare leading models side by side, or see which coding plan fits your team.
Discussion & Comments
0Sign in to join the discussion
Connect with AI developers to exchange benchmark insights.