ComfyUI Workflow

4 months ago


Workflow Information

=== How to prompt this workflow in other prompt modes than "simple" ===

Main Prompt

The subject of the image in natural language

  • Example: a cat with a hat in a grass field

Secondary Prompt

A keyword/tag list version of the main prompts

  • Example: cat with hat, in grass field

Style and References Prompt

A description of the style of the image, the main style should be the first word

  • Example: ~~oil painting~~ in the style of [artist name], vibrant colors

Negative Prompt

Subjects that should not appear in the image

  • Example: jpeg artifacts, noise

Negative Style Prompt

Styles and concepts that should not be used to generate the image

  • Example: photograph, anime

    === In "simple" prompt mode only the main and negative prompts are used ===

    === In "3 prompts" prompt mode it's main, secondary, and negative prompts ===

Workflow Information

 Improved Searge SDXL "Reborn" workflows for SDXL 1.0   |   Version 3.4 updated on Aug 08, 2023


1024 x 1024, 1152 x 896, 896 x 1152, 1216 x 832, 832 x 1216, 1344 x 768, 768 x 1344, 1536 x 640, 640 x 1536

NOTE: All upscale factors are applied to the image size from generation parameters, not the actual image size

Off by default for performance reasons

              Connect this "jumper" to enable UPSCALING
                  (this is NOT related to hires fix)
  (when it's disconnected ignore the warnings printed to the console)


  • Model Loading
  • Prompt Parsing
  • Prompt Processing
  • Image Generation
  • HiRes Fix
  • Upscaling
  • User Interface
  • Image 2 Image and Inpainting
  • Experimental Prompt Post-Processing