HiThis is a base SDXL text2image workflow but it has a Noise Invection in the end of generation process for making variable pictures (4 by default).And thera are Face Detailer node and becouse this wf is good for making beautiful characters.

Workflow name: Quick Face Swap[Workflow Introduction]First, upload two images, one is the base image, and the other is the image to be swapped. Through SAM detection, the face will be automatically recognized and matted, and masked. Then apply InstantlD...

Workflow name: FLUX GGUF+LoRA[Workflow introduction]After uploading an image, combine the flux1-dev-Q4 0.gguf model and the xlab_flux Realism2 lora model to perform image generation processing on the image. Since the FLUX model has excellent text unders...

Workflow name: Joy_caption reverse prompt words (Chinese and English)[Workflow introduction]This workflow is extremely simple. You only need to upload an image, and the Joy_caption node will automatically reverse the image information and write it into ...