Extensions/ComfyUI-AMD-Qwen-Image-2.1
ComfyUI Extension

ComfyUI-AMD-Qwen-Image-2.1

Free Qwen-Image 2.1 text-to-image through the AMD gateway. Register for an API key; no local GPU required.

By wangxunx·Created 7 days ago·Updated 7 days ago· 0
wangxunx/ComfyUI-AMD-Qwen-Image-2.1
Nodes—
On cloudLocal install
Stars0
Updated7 days ago
Readme

ComfyUI-AMD-Qwen-Image-2.1

ComfyUI node for Qwen-Image 2.1 text-to-image generation through the AMD gateway.

Install

cd ComfyUI/custom_nodes
git clone https://github.com/wangxunx/ComfyUI-AMD-Qwen-Image-2.1.git

Restart ComfyUI. No extra Python dependencies are required.

Configure your API key

Register at https://h3.oneclickamd.ai to get a key, then use either method below. This is a one-time setup per machine and applies to every workflow:

  • Set the H3_GATEWAY_API_KEY environment variable
  • Or save the key to h3_gateway_api_key.txt in the ComfyUI user directory

If the key is missing, the node fails immediately and tells you the registration URL and the exact file path.

The gateway serves both its image and video models from one account, so a key already configured for ComfyUI-AMD-MiniMaxH3 works here with no further setup.

To point the node at a different gateway, set H3_GATEWAY_BASE_URL.

Node

| Node | Inputs | |---|---| | AMD Qwen Image 2.1 Text to Image | prompt, aspect_ratio (six ratios), steps (10-50) |

Qwen-Image 2.1 on this gateway generates from text only, so the node takes no reference image. A prompt is required.

Credits are charged in proportion to steps: 30 steps cost one credit, and more steps cost proportionally more.

A 1024x1024 image usually takes about 50 seconds. The first request at a resolution the backend has not served before takes noticeably longer because it compiles convolution kernels on the spot; that path is slow, not failing.

Example workflow

In ComfyUI, open the template browser from the left sidebar, scroll to the EXTENSIONS section, and pick ComfyUI-AMD-Qwen-Image-2.1. The AMD Qwen Image 2.1 Text to Image workflow runs as-is once your key is configured, and includes a note explaining the key setup.

Your API key never enters a workflow

The node deliberately has no api_key widget. Widget values are serialized into workflow JSON and embedded into output image metadata, which would leak the key as soon as a workflow or a generated image is shared. Reading the key from the environment or from a file outside the graph keeps it out of both.

License

MIT. See LICENSE.