Merge pull request #171 from modelscope/Artiprocher-dev

update README

README.md

@@ -79,7 +79,7 @@ Until now, DiffSynth Studio has supported the following models:
 
 ## Installation
 
-Install from source code:
+Install from source code (recommended):
 
 ```
 git clone https://github.com/modelscope/DiffSynth-Studio.git
@@ -167,6 +167,8 @@ https://github.com/user-attachments/assets/95265d21-cdd6-4125-a7cb-9fbcf6ceb7b0
 
 **This video is not rendered in real-time.**
 
+Before launching the WebUI, please download models to the folder `./models`. See [here](#download-models).
+
 * `Gradio` version
 
 ```
@@ -177,6 +179,10 @@ python apps/gradio/DiffSynth_Studio.py
 
 * `Streamlit` version
 
+```
+pip install streamlit streamlit-drawable-canvas
+```
+
 ```
 python -m streamlit run apps/streamlit/DiffSynth_Studio.py
 ```

environment.yml

@@ -1,21 +0,0 @@
-name: DiffSynthStudio
-channels:
-  - pytorch
-  - nvidia
-  - defaults
-dependencies:
-  - python=3.9.16
-  - pip=23.0.1
-  - cudatoolkit
-  - pytorch
-  - cupy
-  - pip:
-    - transformers
-    - controlnet-aux==0.0.7
-    - streamlit
-    - streamlit-drawable-canvas
-    - imageio
-    - imageio[ffmpeg]
-    - safetensors
-    - einops
-    - sentencepiece

requirements.txt

@@ -2,8 +2,7 @@ torch>=2.0.0
 cupy-cuda12x
 transformers
 controlnet-aux==0.0.7
-streamlit
-streamlit-drawable-canvas
+gradio
 imageio
 imageio[ffmpeg]
 safetensors