Picture published by the creator on Hugging Face.

Make images about 5x faster with a distilled Qwen model

Made by Viggle AI

Viggle’s turbo build is a distilled, faster version of Qwen-Image-2.1, the open image model: where the original takes 40 passes to render a picture, this one takes about six, which Viggle reports makes it roughly five times faster from prompt to finished image.

It handles both text-to-image and instruction-based editing with reference images, and ships as small adapter files that layer onto the base model inside Diffusers or ComfyUI. Viggle says quality is very close to the original on most prompts, with small dense text the clearest remaining gap. You still need a graphics card and the base Qwen-Image-2.1 weights underneath.

Can I use this?

Runs in Diffusers or ComfyUI with a GPU

You'll need A GPU, Diffusers or ComfyUI, and the base Qwen-Image-2.1 weights · Setup needed

Worth knowing The 5x speedup and quality claims are Viggle’s own, measured against the base model on its own example prompts. It is an adapter, not a standalone model — it does nothing without the base weights. BuildTube has not run or verified this model.

Why it's here

481 people have liked it on Hugging Face.
It was downloaded 217,638 times in the last 30 days.

Numbers from the snapshot taken 1 October 2026; not refreshed since.

Behind it

See the code on Hugging Face

BuildTube has not run or verified this project. Everything above is written from what the creator published.

Made this?