From d1ee553f099902c74fd03603ac97d0e1b6fb2786 Mon Sep 17 00:00:00 2001 From: pythongosssss <125205205+pythongosssss@users.noreply.github.com> Date: Wed, 22 Mar 2023 14:36:03 +0000 Subject: [PATCH] Update README.md --- wd14-tagger/README.md | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) diff --git a/wd14-tagger/README.md b/wd14-tagger/README.md index bd36b06..d90ee87 100644 --- a/wd14-tagger/README.md +++ b/wd14-tagger/README.md @@ -1,17 +1,17 @@ -Based on https://huggingface.co/spaces/SmilingWolf/wd-v1-4-tags +Based on https://huggingface.co/spaces/SmilingWolf/wd-v1-4-tags This requires onnxruntime or onnxruntime-gpu to run, so pip install it -Links to the models are found at the top of the url above -Follow the link to one, e.g. convnextv2, go to Files -Download model.onnx + selected_tags.csv -Rename the model.onnx + csv the same thing, e.g. convnextv2.onnx + convnextv2.csv -Place them in comfy_extras/wd14_models +Links to the models are found at the top of the url above +Follow the link to one, e.g. convnextv2, go to Files +Download model.onnx + selected_tags.csv +Rename the model.onnx + csv the same thing, e.g. convnextv2.onnx + convnextv2.csv +Place them in comfy_extras/wd14_models Place wd14tagger.py in custom_nodes -This currently requires this branch of ComfyUI to be of any use: +This currently requires this branch of ComfyUI to be of any use: https://github.com/pythongosssss/ComfyUI/tree/custom-ws-messages -You can right click the CLIPTextEncode node -convert text to input +You can right click the CLIPTextEncode node +convert text to input then feed the results of this node into the text encode