PhotoMaker
Customize realistic photos of a person from a few reference images.
- Stars
- 10.1K
- Forks
- 808
- Open issues
- 159
- Last commit
- 2024-10-31
Live from the GitHub API · updated 2026-10-15
What is PhotoMaker?
PhotoMaker by Tencent ARC encodes one or more photos of a person into an ID embedding, then generates new photos or stylized images of them from a text prompt — no LoRA training required.
Key features
- Stacks multiple reference photos for better identity
- Realistic and stylized modes
- SDXL-based with Gradio demo
System requirements
- Platforms
- Linux · Windows
- GPU
- NVIDIA
- VRAM
- 11 GB+ (per README)
How to install PhotoMaker
Summarized from the project’s README. Projects change quickly — check the GitHub page for the latest instructions.
Gradio demo
- 1Clone and install.
git clone https://github.com/TencentARC/PhotoMaker.git cd PhotoMaker pip install -r requirements.txt - 2Launch the local demo.
python gradio_demo/app.py
Strengths
- Fast identity customization
- Good realism
Limitations
- Research-grade setup
PhotoMaker alternatives compared
| Software | Stars | License | Platforms | VRAM |
|---|---|---|---|---|
| PhotoMaker Customize realistic photos of a person from a few reference images. | 10.1K | Apache-2.0 | 11 GB+ (per README) | |
| InstantID Identity-preserving generation from a single face photo. | 12K | Apache-2.0 | 16 GB+ recommended for the demo | |
| 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 PhotoMaker free?
Yes — PhotoMaker is open-source software released under the Apache-2.0 license. Check the license (and any model weight licenses) before commercial use.
Does PhotoMaker run on Windows, Mac and Linux?
PhotoMaker supports: Linux, Windows.
What hardware do I need for PhotoMaker?
NVIDIA. VRAM: 11 GB+ (per README)
How do I install PhotoMaker?
1. Clone and install. 2. Launch the local demo.
What are the best PhotoMaker alternatives?
Popular alternatives include InstantID, IP-Adapter, ComfyUI, Stable Diffusion WebUI (AUTOMATIC1111). See the comparison table on this page.
Can I use PhotoMaker 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.