Update README

README.md

@@ -1,5 +1,4 @@
 ---
-license: apache-2.0
 language:
   - en
 tags:
@@ -134,38 +133,6 @@ LoomVideo supports **four** unified video generation and editing tasks within a
 
 # 🔧 Preparation
 
-## Step 1: Clone the Repository
-
-```bash
-git clone TODO
-cd LoomVideo
-```
-
-## Step 2: Install Dependencies
-
-We recommend using [uv](https://github.com/astral-sh/uv) for a fast and fully reproducible environment setup.
-
-```bash
-uv sync
-source .venv/bin/activate
-
-# (Optional) Include evaluation dependencies
-uv sync --extra eval
-```
-
-Additionally, install [Flash Attention](https://github.com/Dao-AILab/flash-attention) for faster inference and reduced GPU memory consumption. (for reference, our environment uses v2.7.4)
-
-## Step 3: Download Model Weights
-
-Download the pretrained LoomVideo checkpoint from [Hugging Face](TODO) and place it under `checkpoints/LoomVideo/`:
-
-```
-checkpoints/LoomVideo/
-└── gen_model.pth
-```
-
-You can also specify a custom path via the `--ckpt_path` argument at inference time.
-
 
 # 🎬 Inference
 LoomVideo provides a unified inference script that supports **four generation tasks** through a single entry point. Each task is selected via the `--task` flag.