jhj SDXL Workflows — v1.0

Use jhj SDXL Workflows to create images from text prompts or edit input images, with text-to-image, image-to-image, inpainting, ControlNet, and IPAdapter variants; named steps include image preview and saving.

Choose from text-to-image, image-to-image, inpainting, text-to-image ControlNet, image-to-image ControlNet, and IPAdapter workflows.

Named input steps are CLIPTextEncode and LoadImage; PreviewImage and SaveImage are named image output steps.

Version v1.0 is published by Jhj0517 and based on SDXL 1.0.

Named model files include sd_xl_base_1.0.safetensors and ip-adapter-plus-face_sdxl_vit-h.safetensors. Named node packs include ComfyUI_Comfyroll_CustomNodes (CR Apply LoRA Stack and CR Aspect Ratio), ComfyUI-Easy-Use (easy loraStack), and comfyui_controlnet_aux (AIO_Preprocessor.

Other named model files are 4x_foolhardy_Remacri.pth, sdxl-vae.safetensors, xinsircontrolnet-openpose-sdxl-1.0.safetensors, and open_clip_model.safetensors.

Additional upscale nodes are disabled by default.

For SD1.5, switch checkpoints. Pony and Illutrious are described as SDXL fine-tunes that work with this workflow.

Suggestion · not verified

For version updates, visit https://github.com/jhj0517/ComfyUI-workflows/tree/master.

Suggestion

Before choosing a variant, check that its model files and node packs are available in your ComfyUI setup.

Suggestion · not verified

No license is specified in the listing.