Meituan's LongCat team shipped a quiet but meaningful update to its open-source talking-avatar stack: version 1.5 swaps the audio encoder, distills sampling down to 8 steps, and adds an INT8 path to fit the model on tighter GPUs. Here's what actually changed under the hood, and which flags you now have to pass.
LongCat-Video-Avatar 1.5: DMD2 distillation, Wav2Vec2 replacement, and INT8 offloading
LongCat-Video-Avatar 1.5 is an audio-driven talking-avatar generator that turns one portrait plus an audio clip into a lip-synced video with head motion, expression, and body dynamics. Released May 21, 2026, it is an avatar head built on the 13.6-billion-parameter dense LongCat-Video diffusion transformer [base model, Oct 2025]. The headline change: v1.5 replaces the Wav2Vec2 audio encoder used in v1.0 (Dec 16, 2025) with Whisper-Large-v3, which the team attributes to smoother, more natural lip dynamics.
Three new flags define the v1.5 workflow, none of which exist in v1.0:
| Flag | What it does | Notes |
|---|---|---|
--use_distill |
Enables DMD2-based step distillation, collapsing generation to 8 NFE | Mandatory for v1.5 — omitting it falls back to the full-chain v1.0 sampling schedule, not an 8-step path |
--use_int8 |
Loads the 13.6B dense DiT in INT8 to cut VRAM pressure | Main lever for consumer GPUs |
--resolution |
Selects 480P or 720P output | New in 1.5 |
Under the hood, the technique report describes Cross-Chunk Latent Stitching, which removes redundant VAE decode/encode cycles between autoregressive chunks, enabling seamless minutes-long generation without re-encoding overhead [arXiv:2605.26486]. That matters for long-form output where earlier tools drift or stutter at chunk boundaries.
One caveat worth flagging before you invest a GPU-hour: Meituan claims parity-or-better results versus HeyGen, Kling Avatar 2.0, and OmniHuman-1.5 across 508 image-audio pairs, 770 crowdsourced evaluators, and 13,240 judgments [human-eval benchmark]. That evaluation is entirely author-controlled and reported as win-rates; no independent leaderboard corroborates the superiority claim yet. Treat it as vendor evidence, not a settled result. Credit to the source video that surfaced this release: YouTube walkthrough.
Preparing your environment for LongCat-Video-Avatar 1.5: PyTorch 2.6.0, CUDA 12.4, FlashAttention-2
Setup begins by cloning the base repository — the avatar is a head on top of the LongCat-Video foundation model, so you install that first and add the avatar layer on top. Create a Python 3.10 virtual environment before anything else; the pinned FlashAttention-2 wheel is not tested against 3.11+, and version drift there is a common early failure.
The dependency the setup most often breaks on is FlashAttention-2 v2.7.4.post1, a hard requirement . Install it from the wheel that matches CUDA 12.4 against PyTorch 2.6.0 — a CUDA mismatch with the default pip build is the single most frequent install error. Then install both requirements files: requirements.txt for the base model and requirements_avatar.txt for the avatar path, which pulls librosa and expects ffmpeg on the system .
Pull the weights with huggingface-cli download meituan-longcat/LongCat-Video-Avatar-1.5 . Note the DMD2 distill LoRA — roughly 1.26 GB in the Comfy-packaged form — is a separate artifact and is required for the 8-NFE distilled path, not an optional extra.
The reference launch uses torchrun --nproc_per_node=2 with --context_parallel_size=2, i.e. two GPUs in context-parallel . Single-GPU runs are feasible by adding --use_int8 to cut VRAM on the 13.6B dense base, but that is not the configuration the official docs test — expect to tune offloading yourself.
Producing a talking-head avatar with LongCat-Video-Avatar 1.5: torchrun, AT2V, and DMD2
LongCat-Video-Avatar 1.5 exposes four task modes, and picking the right one decides how tightly identity is preserved. AT2V (Audio-Text-to-Video) generates a talking clip from an audio track plus a text prompt with no reference image. ATI2V/AI2V add a portrait (Audio-Text-Image or Audio-Image-to-Video), which routes through Reference Skip Attention to hold the face steady without copy-paste artifacts or identity drift . Prefer ATI2V or AI2V when you have a source photo and care about consistency. The fourth mode is audio-conditioned continuation, covered below.
A single-speaker AT2V run looks like this — the snippet is verified and prints the exact upstream CLI it wraps rather than executing the model:
"""Minimal LongCat-Video-Avatar 1.5 8-step inference demo.
This prints the distilled inference settings and the matching upstream CLI.
Running the real model requires downloading the weights and LongCat-Video repo.
"""
MODEL = "meituan-longcat/LongCat-Video-Avatar-1.5"
def main():
steps = 8
command = [
"torchrun",
"--nproc_per_node=2",
"run_demo_avatar_single_audio_to_video.py",
"--context_parallel_size=2",
"--checkpoint_dir=./weights/LongCat-Video-Avatar-1.5",
"--stage_1=at2v",
"--input_json=assets/avatar/single_example_1.json",
"--use_distill",
"--model_type=avatar-v1.5",
"--use_int8",
]
print(f"{MODEL} uses distilled inference: {steps} steps")
print(" ".join(command))
if __name__ == "__main__":
main()
Both --use_distill and --model_type avatar-v1.5 are mandatory for the 8-step (8-NFE) distilled path . Set Audio CFG in the 3–5 range per the official docs: below 3 under-animates the mouth, above 5 over-exaggerates it .
For two speakers, run run_demo_avatar_multi_audio_to_video.py. Use --audio_type para for equal-length clips (parallel merge, summed) or --audio_type add for unequal clips sequenced with silence padding; person1/person2 ordering is positional . In parallel-merge mode, L-ROPE-based audio-visual binding supplies spatial speaker separation so voices do not bleed identity between the two faces .
Video continuation feeds a reference clip plus new audio to extend an existing segment. Here Cross-Chunk Latent Stitching removes the redundant VAE decode/encode cycle between autoregressive chunks, so the boundary seam stays clean without a re-encode step .
ComfyUI packaging and workarounds for LongCat-Video-Avatar 1.5
If the raw torchrun path is too heavy, two community ComfyUI routes wrap LongCat-Video-Avatar 1.5 — neither maintained by Meituan. The dedicated smthemex/ComfyUI_LongCat_Avatar node clones into ComfyUI/custom_nodes and pulls the INT8 DiT, a umt5_xxl_fp8_e4m3fn_scaled text encoder, the Whisper-large-v3 audio encoder, the LongCat_Avatar_1.5_vae, a distill LoRA, and a Kim_Vocal_2.onnx vocal separator; it is tested for single- and dual-person scenarios . The second route is Kijai's ComfyUI-WanVideoWrapper, whose LongCat model folder ships a LongCat-Avatar-15_bf16.safetensors at 31.7 GB plus a 1.26 GB distill LoRA.
Watch for packaging churn. Older tutorials point at a longcat_avatar branch of WanVideoWrapper, while current v1.5 support has moved to the main branch — always check a guide's commit date before following it. On licensing, the MIT terms cover weights and code but explicitly exclude trademark and patent rights to the "Meituan" and "LongCat" names : commercial use of the model is allowed; using the brand names is not.
Two gaps remain before production. There is no hosted inference provider on Hugging Face — roughly 1,581 downloads last month and 44 community Spaces — so a local GPU is mandatory; HeyGen at $0.05/sec for a 720p Photo Avatar stays the zero-GPU alternative. And the project ships no consent workflow, rights management, or brand-kit tooling — governance for generated likenesses must be built entirely outside it. The concrete takeaway: LongCat-Video-Avatar 1.5 gives you open, inspectable, multi-person avatar generation for the cost of a GPU, but you own every guardrail it doesn't provide.
Frequently asked questions
What GPU do I need to run LongCat-Video-Avatar 1.5?
The reference configuration is multi-GPU: the official avatar command launches with torchrun --nproc_per_node=2 and --context_parallel_size=2. Because the base is a 13.6-billion-parameter dense diffusion transformer and Kijai's bf16 build weighs about 31.7 GB, a realistic floor is two 24 GB cards or a single 40 GB+ card with --use_int8. A single consumer GPU with INT8 quantization and offloading is possible, but it sits outside the officially tested two-GPU config, so expect slower runs and manual tuning.
What changed between LongCat-Video-Avatar v1.0 and v1.5?
v1.0 shipped December 16, 2025 with a Wav2Vec2 audio encoder; v1.5 landed May 21, 2026. The substantive changes: the audio encoder moves from Wav2Vec2 to Whisper-Large-v3 for smoother lip dynamics, DMD2-based step distillation collapses inference to 8 steps via the --use_distill flag, INT8 loading arrives through --use_int8 to cut VRAM, --resolution exposes 480P/720P output, and Cross-Chunk Latent Stitching improves long-video temporal stability.
What does the --use_distill flag do and why is it required for v1.5?
--use_distill activates the DMD2 distillation LoRA that collapses diffusion sampling to 8 NFE (8 steps). Without it, the v1.5 weights fall back to the full-chain sampling schedule inherited from v1.0 — significantly slower and not the intended v1.5 inference path. The flag is why the distilled route is 8 steps rather than the dozens a standard diffusion schedule would run, so it belongs in every v1.5 avatar command.
Is LongCat-Video-Avatar MIT-licensed for commercial use?
Yes. The weights, code, and contributions are distributed under the MIT license, which permits commercial use of the model itself. The one carve-out is that the MIT terms explicitly exclude trademark and patent rights to the "Meituan" and "LongCat" names — so you can build commercial products on the model, but you cannot use those brand names as your own. As always, verify the license text against your specific deployment before shipping.
How does LongCat-Video-Avatar 1.5 compare to HeyGen for talking avatars?
LongCat is self-hosted and MIT-licensed, costs $0 per video once you own the GPU, and natively supports dual-speaker scenes and audio-conditioned video continuation. HeyGen is turnkey SaaS priced around $0.05/sec for a 720p Photo Avatar, with a consent video required for every video-based Digital Twin and production governance built in. LongCat ships none of that tooling — no consent workflow, rights management, captions, or brand kits. Choose LongCat for control, privacy, and marginal cost; choose HeyGen for governance, reliability, and support.
Top comments (0)