From 40dbda463315ef4fa30e7ef17088315c764cd3ce Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=E7=9A=93=E7=AB=A5?= Date: Thu, 13 Mar 2025 11:20:47 +0800 Subject: [PATCH] modify readme --- README.md | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/README.md b/README.md index 28f0f9f..4d42204 100644 --- a/README.md +++ b/README.md @@ -99,7 +99,13 @@ We provide a parameter to adjust the GPU memory usage. As shown in the figure be ACE_Plus_FFT_workflow_controlpreprocess.json - Controllable image-to-image translation capability. + Controllable image-to-image translation capability. To preprocess depth and contour information from images, + we use externally-provided models that are typically downloaded from the ModelScope Hub. Because download success + can vary depending on the user's environment, we offer alternatives: users can either leverage existing community + nodes (depth extration node or contour extraction node) for this task (then choosing the 'no_preprocess' option), + or users can pre-download the required models and adjust + the configuration file 'workflow/ComfyUI-ACE_Plus/config/ace_plus_fft_processor.yaml' to + specify the models' local paths. ACE_Plus_FFT_workflow_reference_generation.json