InstantID
Identity-preserving generation from a single face photo.
- Stars
- 12K
- Forks
- 891
- Open issues
- 187
- Last commit
- 2024-07-18
Live from the GitHub API · updated 2026-10-15
What is InstantID?
InstantID generates new images of a person from one reference photo without fine-tuning, combining a face embedding with a landmark ControlNet. It is popular for stylized portraits and avatars and is available as ComfyUI nodes.
Key features
- Zero-shot identity preservation from one image
- Works with SDXL checkpoints and styles
- Gradio demo and ComfyUI integration
System requirements
- Platforms
- Linux · Windows
- GPU
- NVIDIA
- VRAM
- 16 GB+ recommended for the demo
How to install InstantID
Summarized from the project’s README. Projects change quickly — check the GitHub page for the latest instructions.
Gradio demo
- 1Clone and install requirements.
git clone https://github.com/instantX-research/InstantID.git cd InstantID pip install -r gradio_demo/requirements.txt - 2Download the checkpoints listed in the README, then start the demo.
python gradio_demo/app.py
Strengths
- Strong likeness from one photo
- No training required
Limitations
- Heavy VRAM requirements
- Uses an InsightFace model with non-commercial terms
InstantID alternatives compared
| Software | Stars | License | Platforms | VRAM |
|---|---|---|---|---|
| InstantID Identity-preserving generation from a single face photo. | 12K | Apache-2.0 | 16 GB+ recommended for the demo | |
| PhotoMaker Customize realistic photos of a person from a few reference images. | 10.1K | Apache-2.0 | 11 GB+ (per README) | |
| IP-Adapter Use an image as a prompt — style and subject transfer for diffusion models. | 6.7K | Apache-2.0 | 6 GB+ | |
| ComfyUI Node-based interface for diffusion models — images, video and audio. | 137.6K | GPL-3.0 | 4 GB minimum for SD1.5; 12 GB+ recommended for FLUX and video models | |
| Stable Diffusion WebUI (AUTOMATIC1111) The classic browser UI for Stable Diffusion with a massive extension ecosystem. | 165.1K | AGPL-3.0 | 4 GB minimum (with --medvram/--lowvram), 8 GB+ recommended | |
| Stable Diffusion WebUI Forge A faster, leaner fork of the A1111 WebUI with FLUX support. | 13.1K | AGPL-3.0 | 6 GB+ (FLUX NF4/GGUF variants run on 6–8 GB) |
Related models
FAQ
Is InstantID free?
Yes — InstantID is open-source software released under the Apache-2.0 license. Check the license (and any model weight licenses) before commercial use.
Does InstantID run on Windows, Mac and Linux?
InstantID supports: Linux, Windows.
What hardware do I need for InstantID?
NVIDIA. VRAM: 16 GB+ recommended for the demo
How do I install InstantID?
1. Clone and install requirements. 2. Download the checkpoints listed in the README, then start the demo.
What are the best InstantID alternatives?
Popular alternatives include PhotoMaker, IP-Adapter, ComfyUI, Stable Diffusion WebUI (AUTOMATIC1111). See the comparison table on this page.
Can I use InstantID online without installing it?
If you just want results, AiLoft runs top image models such as GPT Image 2.5 and Nano Banana Pro in the browser — no GPU or setup required.
Skip the install — generate images in your browser
No GPU, drivers or Python needed. Use GPT Image 2.5 and Nano Banana Pro online and compare them side by side.