ComfyUI Node: Qwen2 Run Inference
Run ComfyUI workflows without the setup
No installs, no CUDA version roulette, no GPU sitting idle on your bill. Bring a workflow and run it in the browser.
Category
Qwen2
Inputs
image IMAGE
qwen2_model QWEN2MODEL
text_input STRING
keep_model_loaded BOOLEAN
always_generate_captions BOOLEAN
max_new_tokens INT
temperature FLOAT
top_p FLOAT
min_p FLOAT
top_k INT
repetition_penalty FLOAT
min_pixels INT
max_pixels INT
Outputs
IMAGE
STRING
Extension: ComfyUI-Qwen2
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.[w/May contain bugs.]
Authored by ARZUMATA
Looking for a different node?
More nodes in ComfyUI-Qwen2
Run ComfyUI workflows without the setup
No installs, no CUDA version roulette, no GPU sitting idle on your bill. Bring a workflow and run it in the browser.