📢Need help to include Inpaint Controlnet model and Flux Guidance on this Inpaint Workflow.

#3
by ZeroCool22 - opened

This WF use the Inpaint Crop&Stitch nodes created by lquesada, basically imitates the way Inpaint work in AUTO's, where only the Inpainted region get processed making it less resource-consuming.

The main advantages of inpainting only in a masked area with these nodes are:

  • It's much faster than sampling the whole image.
  • It enables setting the right amount of context from the image for the prompt to be more accurately represented in the generated picture.
  • It enables upscaling before sampling in order to generate more detail, then stitching back in the original picture.
  • It enables downscaling before sampling if the area is too large, in order to avoid artifacts such as double heads or double bodies.
  • It enables forcing a specific resolution (e.g. 1024x1024 for SDXL models).
  • It doesn't modify the unmasked part of the image, not even passing it through VAE encode and decode.
  • The nodes take care of good blending.- It's much faster than sampling the whole image.
  • It enables setting the right amount of context from the image for the prompt to be more accurately represented in the generated picture.
  • It enables upscaling before sampling in order to generate more detail, then stitching back in the original picture.
  • It enables downscaling before sampling if the area is too large, in order to avoid artifacts such as double heads or double bodies.
  • It enables forcing a specific resolution (e.g. 1024x1024 for SDXL models).
  • It doesn't modify the unmasked part of the image, not even passing it through VAE encode and decode.
  • The nodes take care of good blending.

I just added the GGUF model and LORA.

Screenshot_8.png

Here is the WF: https://www.mediafire.com/file/jxpvqrzk8mlwt84/inpaint-cropandstitch-Modified+(FLUX).rar/file

If someone could help would be great, thx.

Sign up or log in to comment