fix misc bug

README.md

@@ -27,11 +27,14 @@ Hugging Face: 🤗 [catvton-flux-alpha](https://huggingface.co/xiaozaa/catvton-f
 The model weights are trained on the [VITON-HD](https://github.com/shadow2496/VITON-HD) dataset.
 
 ## Prerequisites
+Make sure you are runing the code with VRAM >= 40GB. (I run all my experiments on a 80GB GPU, lower VRAM will cause OOM error. Will support lower VRAM in the future.)
+
 ```bash
 bash
 conda create -n flux python=3.10
 conda activate flux
 pip install -r requirements.txt
+huggingface-cli login
 ```
 
 ## Usage
@@ -49,7 +52,10 @@ Run the following command to start a gradio demo:
 ```bash
 python app.py
 ```
+Gradio demo:
 
+<!-- Option 2: Using a thumbnail linked to the video -->
+[![Demo](example/github.jpg)](example/github.mp4)
 
 ## TODO:
 - [x] Release the FID score

requirements.txt

@@ -24,7 +24,6 @@ fsspec==2024.6.1
 gitdb==4.0.11
 GitPython==3.1.43
 hjson==3.1.0
-huggingface-hub==0.24.5
 humanfriendly==10.0
 idna==3.7
 importlib_metadata==8.2.0
@@ -97,4 +96,5 @@ bitsandbytes==0.44.1
 gradio==5.6.0
 gradio_client==1.4.3
 prodigyopt
+huggingface-hub
 git+https://github.com/huggingface/diffusers.git

tryon_inference.py

@@ -104,8 +104,6 @@ def main():
         image_path=args.image,
         mask_path=args.mask,
         garment_path=args.garment,
-        output_garment_path=args.output_garment,
-        output_tryon_path=args.output_tryon,
         num_steps=args.steps,
         guidance_scale=args.guidance_scale,
         seed=args.seed,