ComfyUI Node: ModelScope-Vision 图生文节点

Authored by hujuying

Created

Updated

66 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

ModelScopeAPI

Inputs

image IMAGE
prompt STRING
api_token STRING
model
  • stepfun-ai/step3
  • Qwen/Qwen2.5-VL-7B-Instruct
  • Qwen/Qwen2.5-VL-72B-Instruct
  • Qwen/Qwen2.5-VL-3B-Instruct
  • Qwen/Qwen2.5-VL-32B-Instruct
  • Qwen/Qwen2-VL-7B-Instruct
  • Qwen/QVQ-72B-Preview
  • PaddlePaddle/ERNIE-4.5-VL-28B-A3B-PT
max_tokens INT
temperature FLOAT

Outputs

STRING

Extension: ComfyUI ModelScope API Node

This is a universal custom node for ComfyUI that supports both Text-to-Image and Image-to-Image generation by calling various models via the official ModelScope API.

Authored by hujuying

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