Huhu Try-on Turbo:
The Fastest Virtual Try-On for Any Outfit on Any Person


HuHu Try-on Turbo is a timestep- and guidance-distilled Rectified Flow Transformer
that delivers high-fidelity try-on results at 1024×768 resolution in 1 second*,
without compromising visual quality.

You can not only use your own garments but also upload your own model photos for generation.
After uploading a garment image, please select the corresponding clothing type.
Please ensure that any images you upload (e.g., model photos) do not infringe third-party rights.
Upload your garment image 🧥
Select a model image 🧍
“RUN” to get results 🪄
Garment type
Examples
Examples

Key highlights driving our model's exceptional speed and fidelity include:
  • Parallel DiT architecture with 16-channel VAE, enabling maximum garment fidelity and fine detail retention
  • CFG-augmented consistency distillation, allowing generation in as few as 8 inference steps without needing CFG during inference
  • Enhanced dilated clothing-agnostic masking strategy, resulting in more accurate garment outlines
  • Trained on 1M+ proprietary garment-image pairs, spanning flatlays, model-to-model scenarios, and a wide diversity of garment types

*Please note that “1 second” refers to the try-on generation’s actual processing time. In pactice, additional pre-processing is applied to the model image with computing intermediate representations, and it may add to the overall latency.
However, these pre-processing overheads can be largely optimized with caching, and deliver a near real-time experience in applications.



Huhu Try-on Turbo examples in pairs of garment and model images
Examples
Person image Garment image Garment type Result