Avatars

Hallo

A series of audio-driven talking portraits: from short clips to hour-long 4K videos. Hallo-Live is built for real-time use.

Developer
Fudan University, China
First release
Jun 2024
Latest release
Apr 2026
Sizes
about 1B – 5B
License
Commercial use allowedMIT
Running
On your own serverNeeds a GPU
Industries
Education, Media and production
Deploy on your server Hugging Face GitHub

What it does

  • Presenter video from a photo and audio
  • Long training videos
  • Live avatar

Where it is used

EducationMediaCorporate training

Hardware requirements

LaptopLaptop or regular PC, up to 8 GB of VRAM — smaller versions
no versions
1 GPUOne GPU with 16–80 GB — mid-size versions
fits
ClusterServer with several GPUs — flagship versions
no versions

Versions

  1. Hallo-Live
  2. Hallo4
  3. Hallo3
  4. Hallo2
  5. Hallo

How to run it

On your own serverWeights are downloaded from Hugging Face and served with vLLM (load and API) or llama.cpp (modest hardware). The model then runs in a closed network with no per-request fees.Hugging Face
How much hardware you needCalculate the VRAM for the model size, context length and number of concurrent requests.Open the hardware calculator

I can set this up end to end: pick the model size, deploy it on your server and connect it to your systems.

Frequently asked questions

Can Hallo be used in a commercial project?

Yes. License: MIT. It allows commercial use, but it is still worth having a lawyer review the license before launch.

What hardware does Hallo need?

At minimum: One GPU with 16–80 GB — mid-size versions. Without a GPU the model is not practical. You can calculate the exact VRAM for your model size and context in the hardware calculator.

Does Hallo support Russian?

Language does not matter for this model: it does not work with text.

Where can I download Hallo and what does it cost?

The Hallo weights are open and free to download. You only pay for the hardware it runs on and for the setup. Source links are at the bottom of this page.

How I deploy it for clients

  1. SelectionI pick the model size for your task and hardware and test it on your examples.
  2. DeploymentI deploy it on your server or in a closed network and provide an API.
  3. Fine-tuningI fine-tune it on your data (LoRA) or connect a knowledge base — whichever is cheaper for the task.
  4. IntegrationI connect it to your CRM, ERP, bot, website or team chat and set up monitoring.

Similar models

AvatarsEchoMimicAnt Group · ChinaCommercial use allowed

Ant Group's talking avatars: the face and, from V2, hand gestures. V3-Flash produces video in 8 steps and fits into 12 GB of GPU memory.

DetailsAvatarsMultiTalk / InfiniteTalkMeituan · ChinaCommercial use allowed

Dubbing and talking characters built on Wan: MultiTalk handles dialogue between several people, InfiniteTalk re-dubs videos of any length with facial and body motion.

DetailsAvatarsMuseTalkTencent Music (Lyra Lab) · ChinaCommercial use allowed

Real-time lip sync: matches the mouth in a video to new audio. Suits video translation and live avatars.

Details

Source: huggingface.co/fudan-generative-ai/Hallo-Live. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.