FacesImage generation

IP-Adapter-FaceID

One of the first adapters that transfer a face from a photo into a generated image. The SD 1.5 versions run on low-end cards, but the weights are non-commercial.

The last open version came out in Apr 2024. The family has not been updated for a long time: the model still works, but do not expect fixes or new sizes.

Developer
Tencent AI Lab (h94), China
First release
Dec 2023
Latest release
Apr 2024
Sizes
adapters for SD 1.5 and SDXL
License
Non-commercial onlyResearch and non-commercial use only (due to the InsightFace weights)
Running
On your own serverNeeds a GPU
Industries
Marketing and content, Media and production
Deploy on your server Hugging Face GitHub

What it does

  • Portraits from a photo in different styles
  • Image series with one character
  • Avatar experiments

Where it is used

ResearchDesign (for testing)

Hardware requirements

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

Versions

  1. FaceID-Portrait (SD 1.5 и SDXL)
  2. FaceID-SDXL и PlusV2-SDXL
  3. FaceID-Plus и PlusV2
  4. IP-Adapter-FaceID для SD 1.5

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 IP-Adapter-FaceID be used in a commercial project?

No. License: Research and non-commercial use only (due to the InsightFace weights). A commercial product needs a different model or a separate agreement with the rights holder.

What hardware does IP-Adapter-FaceID need?

At minimum: Laptop or regular PC, up to 8 GB of VRAM — smaller 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 IP-Adapter-FaceID support Russian?

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

Where can I download IP-Adapter-FaceID and what does it cost?

The IP-Adapter-FaceID 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

FacesInstantIDInstantX (Xiaohongshu) · ChinaNon-commercial only

Generates images with a specific person's face from a single photo, without fine-tuning. Popular in ComfyUI, but the weights are for research only.

DetailsFacesPuLIDByteDance · ChinaCommercial use with conditions

Preserves a person's face when generating images from one photo, with less damage to style and background. Versions exist for SDXL and FLUX; the latter runs on a 16 GB card.

DetailsImage generationStable DiffusionStability AI · UKCommercial use with conditions

The model that started open image generation. A huge ecosystem of fine-tunes, styles and plugins; runs even on a home PC. The popular SDXL-Lightning and Hyper-SD accelerators were made by ByteDance.

Details

Source: huggingface.co/h94/IP-Adapter-FaceID. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.