ื—ื‘ืจื• ืืช OpenTG ืœ-ChatGPT ืื• ืœ-Claude ืชื•ืš 60 ืฉื ื™ื•ืช

ื ืกื• ืื•ืชื•

๐ŸŽฌ Kandinsky 6.

NeuralZone | AI Apps

NeuralZone | AI Apps

@NeuralZone

@NeuralZone โ€“ Curated, hand-picked AI tools and services that are actually useful. Buy ads: https://telega.io/c/NeuralZone contact us via @photofixer

369,167 ืžื ื•ื™ื™ื
ืคืชื— ื‘ื˜ืœื’ืจื
๐ŸŽฌ Kandinsky 6.0 Video โ€” create videos with sound in Full HD!

An open-source lineup of models โ€” the flagship Pro (29B) and the lightweight Lite (3B) โ€” generates clips with synchronized speech, music, and ambient sounds. No special skills needed.

๐Ÿ”ฅ Key features:
โ€ข Videos up to 5 seconds with audio
โ€ข Lip-sync: character's lips move with speech
โ€ข Sound quality: 44 kHz (streaming standard)
โ€ข Realistic physics of movement
โ€ข Resolutions: SD, HD, Full HD

๐Ÿ“Š Performance:
โ€ข Pro: clearly outperforms Kandinsky 5.0 across all criteria
โ€ข Pro beats Veo 3.1 Fast in image animation
โ€ข Pro beats LTX 2.5 in visual quality and speech
โ€ข Lite runs on consumer GPUs (RTX 5060 Tiโ€“5090, from 16 GB VRAM)

๐Ÿ›  For developers:
Open-source under MIT license. Available on Diffusers, FastVideo, ComfyUI, SGLang, vLLM-omni

Anton Frolov, Sber: "Anyone can build their own services on top of it โ€” free of charge and without restrictions."

๐Ÿ”—Hugging Face
ืคืชื— ืืช ื”ืคื•ืกื˜ ื‘ื˜ืœื’ืจื