I needed to run Qwen2 on ComfyUI to use it in my workflow for batching images and captioning and none of the implementations I found on the web worked the way I wanted.

[!CAUTION] May contain bugs.

Nodes list

Qwen2ModelLoader

Qwen2ModelRunInference

Preview

<details> <summary>Single image</summary>

Preview

</details> <details> <summary>Batch images</summary>

Preview

</details>

Installation

Clone this repository to ComfyUI/custom_nodes directory.

Docs and Credit

Qwen2

And, for all ComfyUI custom node developers