Update README.md

README.md

@@ -235,32 +235,32 @@ We present several examples to qualitatively compare the original qwen-image-edi
 
 ## Installation
 
-### Requirements
+Install from source (recommended):
 
-- Python 3.8+
-- CUDA-capable GPU (recommended)
-- 8GB+ VRAM
+```
+git clone https://github.com/modelscope/DiffSynth-Studio.git  
+cd DiffSynth-Studio
+pip install -e .
+```
 
-### Setup
+<details>
+<summary>Other installation methods</summary>
 
-1. Clone the DiffSynth-Studio repository:
+Install from PyPI (version updates may be delayed; for latest features, install from source)
 
-```bash
-git clone https://github.com/modelscope/DiffSynth-Studio.git
-cd DiffSynth-Studio
+```
+pip install diffsynth
 ```
 
-2. Install the package:
+If you meet problems during installation, they might be caused by upstream dependencies. Please check the docs of these packages:
 
-```bash
-pip install -e .
-```
+* [torch](https://pytorch.org/get-started/locally/)
+* [sentencepiece](https://github.com/google/sentencepiece)
+* [cmake](https://cmake.org)
+* [cupy](https://docs.cupy.dev/en/stable/install.html)
 
-3. Install additional dependencies:
+</details>
 
-```bash
-pip install torch torchvision --index-url https://download.pytorch.org/whl/cu118
-```
 
 ## Usage
 
@@ -425,18 +425,6 @@ image = pipe(prompt, edit_image=input_image, num_inference_steps=10)
 | `seed` | int | 0 | Random seed for reproducibility |
 | `edit_image_auto_resize` | bool | True | Auto-resize input to match target area |
 
-## Performance
-
-- **Inference Speed**: ~2-3 seconds per image (40 steps, RTX 4090)
-- **VRAM Usage**: ~6-8GB (bfloat16)
-- **Recommended Steps**: 20-40 for optimal quality
-
-## Limitations
-
-- Works best with natural images and common objects
-- May struggle with highly abstract or unusual concepts
-- Quality depends on prompt clarity and specificity
-- Very large images may require more VRAM
 
 ## Citation