add ldm model

README.md

@@ -1,10 +1,10 @@
-# Lama-cleaner: Image inpainting tool powered by [LaMa](https://github.com/saic-mdal/lama)
-
-This project is mainly used for selfhosting LaMa model, some interaction improvements may be added later.
+# Lama-cleaner: Image inpainting tool powered by SOTA AI model
 
 https://user-images.githubusercontent.com/3998421/153323093-b664bb68-2928-480b-b59b-7c1ee24a4507.mp4
 
-
+- [x] Support multiple model architectures
+    1. [LaMa](https://github.com/saic-mdal/lama)
+    1. [LDM](https://github.com/CompVis/latent-diffusion)
 - [x] High resolution support
 - [x] Multi stroke support. Press and hold the `cmd/ctrl` key to enable multi stroke mode.
 - [x] Zoom & Pan
@@ -12,8 +12,29 @@ https://user-images.githubusercontent.com/3998421/153323093-b664bb68-2928-480b-b
 
 ## Quick Start
 
-- Install requirements: `pip3 install -r requirements.txt`
-- Start server: `python3 main.py --device=cuda --port=8080`
+Install requirements: `pip3 install -r requirements.txt`
+
+### Start server with LaMa model
+
+```bash
+python3 main.py --device=cuda --port=8080 --model=lama
+```
+
+### Start server with LDM model
+
+```bash
+python3 main.py --device=cuda --port=8080 --model=ldm --ldm-steps=50
+```
+
+`--ldm-steps`: The larger the value, the better the result, but it will be more time-consuming
+
+Diffusion model is **MUCH MORE** slower than GANs(1080x720 image takes 8s on 3090), but it's possible to get better
+results than LaMa.
+
+Blogs about diffusion models:
+
+- https://lilianweng.github.io/posts/2021-07-11-diffusion-models/
+- https://yang-song.github.io/blog/2021/score/
 
 ## Development
 
@@ -21,8 +42,8 @@ Only needed if you plan to modify the frontend and recompile yourself.
 
 ### Fronted
 
-Frontend code are modified from [cleanup.pictures](https://github.com/initml/cleanup.pictures),
-You can experience their great online services [here](https://cleanup.pictures/).
+Frontend code are modified from [cleanup.pictures](https://github.com/initml/cleanup.pictures), You can experience their
+great online services [here](https://cleanup.pictures/).
 
 - Install dependencies:`cd lama_cleaner/app/ && yarn`
 - Start development server: `yarn dev`
@@ -30,8 +51,8 @@ You can experience their great online services [here](https://cleanup.pictures/)
 
 ## Docker
 
-Run within a Docker container. Set the `CACHE_DIR` to models location path.
-Optionally add a `-d` option to the `docker run` command below to run as a daemon.
+Run within a Docker container. Set the `CACHE_DIR` to models location path. Optionally add a `-d` option to
+the `docker run` command below to run as a daemon.
 
 ### Build Docker image
 
@@ -54,6 +75,7 @@ docker run --gpus all -p 8080:8080 -e CACHE_DIR=/app/models -v $(pwd)/models:/ap
 Then open [http://localhost:8080](http://localhost:8080)
 
 ## Like My Work?
+
 <a href="https://www.buymeacoffee.com/Sanster"> 
   <img height="50em" src="https://cdn.buymeacoffee.com/buttons/v2/default-blue.png" alt="Sanster" />
 </a>