From bc48ba430837cd7f733346deeafda4c9217d11f1 Mon Sep 17 00:00:00 2001 From: iuyua9 Date: Sat, 29 Aug 2026 15:05:23 +0800 Subject: [PATCH] docs: align GFPGAN model filenames (#1910) README and models/instructions.txt named GFPGANv1.4, but the enhancer loads gfpgan-1024.onnx via onnxruntime. instructions.txt also pointed at a PyTorch .pth that the ONNX path cannot load at all, so the manual-fallback instructions were unusable. --- README.md | 2 +- models/instructions.txt | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/README.md b/README.md index f9e5aa4..afc08d2 100644 --- a/README.md +++ b/README.md @@ -156,7 +156,7 @@ cd Deep-Live-Cam **3. Download the Models** -1. [GFPGANv1.4](https://huggingface.co/hacksider/deep-live-cam/resolve/main/GFPGANv1.4.onnx) +1. [gfpgan-1024.onnx](https://huggingface.co/hacksider/deep-live-cam/resolve/main/gfpgan-1024.onnx) 2. [inswapper\_128\_fp16.onnx](https://huggingface.co/hacksider/deep-live-cam/resolve/main/inswapper_128_fp16.onnx) Place these files in the "**models**" folder. diff --git a/models/instructions.txt b/models/instructions.txt index 5235fa6..c45a3f0 100644 --- a/models/instructions.txt +++ b/models/instructions.txt @@ -1,4 +1,4 @@ just put the models in this folder - https://huggingface.co/hacksider/deep-live-cam/resolve/main/inswapper_128_fp16.onnx?download=true -https://github.com/TencentARC/GFPGAN/releases/download/v1.3.4/GFPGANv1.4.pth +https://huggingface.co/hacksider/deep-live-cam/resolve/main/gfpgan-1024.onnx?download=true