ComfyUI Extension: comfyui_zuco_image2

Authored by zuco1111

Created

Updated

0 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.

ComfyUI custom nodes for calling OpenAI's DALL-E 3 image model through a Zuco-compatible base URL with text-to-image and image-to-image support.

Looking for a different extension?

Custom Nodes (2)

README

comfyui_zuco_image2

ComfyUI custom nodes for calling OpenAI's gpt-image-2 image model through the Zuco-compatible base URL:

https://api.zuco.ai/v1

The plugin adds two nodes under Zuco/Image:

  • Zuco Image2 Text to Image
  • Zuco Image2 Image to Image

Both nodes ask for an API Key input at run time. The key is only sent as an HTTP Bearer token and is not written to disk by this plugin.

Inputs

Common inputs:

  • API Key: Zuco API key.
  • Prompt: text prompt.
  • width / height: output size, defaulting to 1024 by 1024. Values must be multiples of 16.
  • output_format: png, jpeg, or webp.

Image-to-image also accepts:

  • Image: reference image or image batch.
  • Mask: optional inpainting mask. White areas are changed. Mask mode requires a single input image.

Notes

  • The model is fixed to gpt-image-2.
  • The API base URL is fixed to https://api.zuco.ai/v1.
  • HTTPS certificate verification is handled internally with multiple CA sources for cross-platform ComfyUI installs.
  • Each run generates one image.
  • Requests time out after 10 minutes.
  • Text-to-image calls /v1/images/generations.
  • Image-to-image calls /v1/images/edits.
  • Reference images are sent as PNG files. Large reference images are downscaled to roughly 2048 by 2048 pixels before upload to keep requests manageable.

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