ComfyUI Node: Qwen3VL 🖤 NightShift

Authored by SmokingDormouse

Created

Updated

1 stars

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

NightShift/Qwen3VL

Inputs

max_longer_edge INT
model_name
  • <no models found>
preset_system_prompt
  • — Custom —
  • 🎨 Z-Image Prompt
  • 🎬 LTX-2.3 Video Prompt
user_prompt STRING
system_prompt STRING
max_length INT
temperature FLOAT
top_p FLOAT
num_beams INT
repetition_penalty FLOAT
seed INT
tf32 BOOLEAN
attention
  • Auto
  • flash_attention_2
  • sdpa
  • eager
torch_compile BOOLEAN
keep_model_loaded BOOLEAN
video_frames INT
device
  • nvidia_gpu
  • cpu
🖼️ Image 1 IMAGE
🖼️ Image 2 IMAGE
🖼️ Image 3 IMAGE
🖼️ Image 4 IMAGE
🎥 Video IMAGE

Outputs

STRING

Extension: ComfyUI-Qwen3VL-NightShift

A ComfyUI custom node for multimodal inference with Qwen3VL vision-language models accepting text, up to 4 images, and video in one node.

Authored by SmokingDormouse

View Nodes

Looking for a different node?

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.

Learn more