AIAny
AI Model2026
Icon for item

LongCat-Video-Avatar 1.6

Generates single- and multi-person avatar videos from speech with image or text inputs, and can continue existing video. Its post-training improvements target natural lip motion and identity consistency in sequences exceeding 10 minutes.

Introduction

Long avatar clips expose a problem that short demos can hide: small motion and appearance errors compound as generation continues. The central advance here is not just more expressive animation, but a training and inference pipeline designed to keep speech-driven motion and character appearance coherent over extended sequences.

Key Capabilities
  • Long-form continuation: The model is designed to generate videos exceeding 10 minutes while reducing autoregressive error accumulation. This makes it more relevant to extended narration than systems evaluated only on short clips.
  • More controlled speech animation: Its post-training refinements target strained mouth shapes, lip–audio alignment, and mismatches between speech and facial expression, while also improving coordination between facial, head, and body motion.
  • A modular generation setup: It supports audio-driven generation from image or text inputs, single- and multi-person animation, and video continuation. Separate DMD and OPSD LoRA adapters allow different stages of the distilled generation process to be combined.
  • Promising, but not a universal win: In a human-preference study with 33,051 votes across six systems, it ranked second, behind OmniHuman-2.0. The report also notes that human-likeness scores for animated inputs fell compared with version 1.5, so the headline ranking does not imply equal performance across content types.
Who It Suits—and the Trade-off

A good fit for teams prototyping long-form talking avatars that need identity preservation, coordinated motion, and speech-conditioned continuation. Look elsewhere if the target is primarily animated characters or if a hosted, turnkey service is required: the released package is a model for self-managed inference, and the reported evaluation identifies weaker generalization on animated inputs.

Information

  • Websitehuggingface.co
  • OrganizationsMeituan LongCat Team, Meituan
  • Published date2026/11/13

More Items

Hugging Face
AI Model2026

A 4B reasoning model with refusal behavior modified using Heretic, built on a student distilled from DeepSeek-V4-Pro. Its model card reports 5 refusals in a 100-prompt test, compared with 99 for the original.

Hugging Face
AI Model2026

Handles text and image inputs and generates text, with a context window of up to 1 million tokens. Its hybrid sparse and sliding-window attention supports long-context work, while the MoE design activates about 12B parameters per token.

Hugging Face
AI Model2026

Generates 480p video with two-step autoregressive diffusion, reaching about 45 ms per frame on eight B200 GPUs. Distilled from Wan2.1-14B, it targets interactive generation but needs a multi-GPU setup for that speed.