torch numpy pillow huggingface_hub decord accelerate qwen-vl-utils[decord] auto-gptq transformers>=4.45.0


Qwen2 Nodes for ComfyUI.
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.
Qwen2ModelLoader
Qwen2ModelRunInference
Single image
Batch images
Clone this repository to ComfyUI/custom_nodes directory.
And, for all ComfyUI custom node developers