OpenWeightsTerminal
Models

Qwen-Image-2.1

Qwen · image

Text-to-image and edit. Diffusers and ComfyUI from day one. No tok/s.

Params

7B visual

Fastest decode

—

Refusal

Official

Setups

0

Runs on

Quoted one-stream decode on real boxes.

View all

No quoted pair yet.

Get it running

  • 1. Install the toolsOn the computer that will draw.
    pip install "torch>=2.4" "transformers>=5.17" accelerate pillow
  • 2. Install DiffusersThis is the version that knows this model.
    pip install git+https://github.com/huggingface/diffusers
  • Open the weightsHugging Face ↗

More from Qwen