diff --git a/README.md b/README.md
index 5b0aac9..dded3f5 100644
--- a/README.md
+++ b/README.md
@@ -19,10 +19,8 @@ Bo Dai
 ## Todo
 - [x] Code Release
 - [x] Arxiv Report
-- [ ] GPU Memory Optimization
+- [x] GPU Memory Optimization
 - [ ] Gradio Interface
-<!-- - [ ] Online Demo -->
-<!-- - [ ] Support WebUI -->
 
 ## Setup for Inference
 
@@ -77,28 +75,6 @@ python -m scripts.animate --config configs/prompts/7-FilmVelvia.yaml
 python -m scripts.animate --config configs/prompts/8-GhibliBackground.yaml
 ```
 
-<!-- ## Setup
-Install the required packages:
-```
-pip install -r requirements.txt
-```
-
-## Inference
-
-1. Download personalized Stable Diffusion (LoRA or DreamBooth are currently supported) from [CivitAI](https://civitai.com/) or Huggingface;
-
-2. Download our motion module's pretrained weights from [this link](); 
-
-3. Edit config files in 
-```
-configs/prompts/lora.yaml
-```
-
-4. Execute animation generation:
-```
-python -m scripts.animate --prompt configs/prompts/lora.yaml
-``` -->
-
 ## Gallery
 Here we demonstrate several best results we found in our experiments or generated by other artists.
 <table class="center">