kamp/IOPaint
1
0
Fork 0
Code Issues Pull Requests Releases 1 Activity

update docker

Browse Source
This commit is contained in:
Qing 2022-10-05 23:15:09 +08:00
parent 8a565e97b3
commit 1fd74a7cc6
5 changed files with 147 additions and 68 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

36
.github/workflows/docker_image.yml vendored Normal file
View File

@ -0,0 +1,36 @@
name: Publish Docker image
on:
release:
types: [published]
jobs:
push_to_registry:
name: Push Docker image to Docker Hub
runs-on: ubuntu-latest
steps:
- name: Checkout
uses: actions/checkout@v3
# - name: Log in to Docker Hub
# uses: docker/login-action@f054a8b539a109f9f41c372932f1ae047eff08c9
# with:
# username: ${{ secrets.DOCKER_USERNAME }}
# password: ${{ secrets.DOCKER_PASSWORD }}
- name: Extract metadata (tags, labels) for Docker
id: meta
uses: docker/metadata-action@98669ae865ea3cffbcbaa878cf57c20bbf1c6c38
with:
images: cwq1913/lamacleaner
tags: type=semver,pattern={{version}}
- name: Build and push CPU Docker image
uses: docker/build-push-action@v3.1.1
with:
context: .
file: ./docker/CPUDockerfile
push: false
tags: |
${{ steps.meta.outputs.tags }}
cpu
labels: ${{ steps.meta.outputs.labels }}

36
Dockerfile
View File

@ -1,36 +0,0 @@
#
# Lama Cleaner Dockerfile
# @author Loreto Parisi (loretoparisi at gmail dot com)
#
FROM python:3.7.4-slim-buster
LABEL maintainer Loreto Parisi loretoparisi@gmail.com
WORKDIR app
RUN apt-get update && apt-get install -y --no-install-recommends \
software-properties-common \
libsm6 libxext6 ffmpeg libfontconfig1 libxrender1 libgl1-mesa-glx \
curl \
npm
# python requirements
COPY . .
COPY requirements.txt /etc/tmp/requirements.txt
RUN pip install -r /etc/tmp/requirements.txt
# nodejs
RUN npm install n -g && \
n lts
# yarn
RUN npm install -g yarn
# webapp
RUN cd lama_cleaner/app/ && \
yarn && \
yarn build
EXPOSE 8080
CMD ["bash"]

115
README.md
View File

@ -33,40 +33,65 @@
## Usage ## Usage
| Usage | Before | After | <details>
| ---------------------- | --------------------------------------------- | -------------------------------------------------------------- | <summary>1. Remove any unwanted things on the image</summary>
| Remove unwanted things | ![unwant_object2](./assets/unwant_object.jpg) | ![unwant_object2](./assets/unwant_object_clean.jpg) |
| Remove unwanted person | ![unwant_person](./assets/unwant_person.jpg) | ![unwant_person](./assets/unwant_person_clean.jpg) | | Usage | Before | After |
| Remove Text | ![text](./assets/unwant_text.jpg) | ![text](./assets/unwant_text_clean.jpg) | | ---------------------- | --------------------------------------------- | --------------------------------------------------- |
| Remove watermark | ![watermark](./assets/watermark.jpg) | ![watermark_clean](./assets/watermark_cleanup.jpg) | | Remove unwanted things | ![unwant_object2](./assets/unwant_object.jpg) | ![unwant_object2](./assets/unwant_object_clean.jpg) |
| Fix old photo | ![oldphoto](./assets/old_photo.jpg) | ![oldphoto_clean](./assets/old_photo_clean.jpg) | | Remove unwanted person | ![unwant_person](./assets/unwant_person.jpg) | ![unwant_person](./assets/unwant_person_clean.jpg) |
| Text Driven Inpainting | ![dog](./assets/dog.jpg) | Prompt: a fox sitting on a bench<br/> ![fox](./assets/fox.jpg) | | Remove Text | ![text](./assets/unwant_text.jpg) | ![text](./assets/unwant_text_clean.jpg) |
| Remove watermark | ![watermark](./assets/watermark.jpg) | ![watermark_clean](./assets/watermark_cleanup.jpg) |
</details>
<details>
<summary>2. Fix old photo</summary>
| Usage | Before | After |
| ------------- | ----------------------------------- | ----------------------------------------------- |
| Fix old photo | ![oldphoto](./assets/old_photo.jpg) | ![oldphoto_clean](./assets/old_photo_clean.jpg) |
</details>
<details>
<summary>3. Replace something on the image </summary>
| Usage | Before | After |
| ---------------------- | ------------------------ | -------------------------------------------------------------- |
| Text Driven Inpainting | ![dog](./assets/dog.jpg) | Prompt: a fox sitting on a bench<br/> ![fox](./assets/fox.jpg) |
</details>
## Quick Start ## Quick Start
The easiest way to use Lama Cleaner is to install it using `pip`:
```bash ```bash
pip install lama-cleaner pip install lama-cleaner
# Model will be downloaded automatically # Models will be downloaded at first time used
lama-cleaner --model=lama --device=cpu --port=8080 lama-cleaner --model=lama --device=cpu --port=8080
# Lama Cleaner is now running at http://localhost:8080 # Lama Cleaner is now running at http://localhost:8080
``` ```
Available arguments: If you prefer to use docker, you can check out [docker](#docker)
| Name | Description | Default | Available command line arguments:
|-------------------|-------------------------------------------------------------------------------------------------------------------------------| -------- |
| --model | lama/ldm/zits/mat/fcf/sd1.4 See details in [Inpaint Model](#inpainting-model) | lama | | Name | Description | Default |
| --hf_access_token | stable-diffusion(sd) model need [huggingface access token](https://huggingface.co/docs/hub/security-tokens) to download model | | | -------------------- | ----------------------------------------------------------------------------------------------------------------------------- | -------- |
| --sd-run-local | Once the model as downloaded, you can pass this arg and remove `--hf_access_token` | | | --model | lama/ldm/zits/mat/fcf/sd1.4 See details in [Inpaint Model](#inpainting-model) | lama |
| --sd-disable-nsfw | Disable stable-diffusion NSFW checker. | | | --hf_access_token | stable-diffusion(sd) model need [huggingface access token](https://huggingface.co/docs/hub/security-tokens) to download model | |
| --sd-run-local | Once the model as downloaded, you can pass this arg and remove `--hf_access_token` | |
| --sd-disable-nsfw | Disable stable-diffusion NSFW checker. | |
| --sd-cpu-textencoder | Always run stable-diffusion TextEncoder model on CPU. | | | --sd-cpu-textencoder | Always run stable-diffusion TextEncoder model on CPU. | |
| --device | cuda or cpu | cuda | | --device | cuda or cpu | cuda |
| --port | Port for backend flask web server | 8080 | | --port | Port for backend flask web server | 8080 |
| --gui | Launch lama-cleaner as a desktop application | | | --gui | Launch lama-cleaner as a desktop application | |
| --gui_size | Set the window size for the application | 1200 900 | | --gui_size | Set the window size for the application | 1200 900 |
| --input | Path to image you want to load by default | None | | --input | Path to image you want to load by default | None |
| --debug | Enable debug mode for flask web server | | | --debug | Enable debug mode for flask web server | |
## Inpainting Model ## Inpainting Model
@ -141,27 +166,53 @@ great online services [here](https://cleanup.pictures/).
## Docker ## Docker
Run within a Docker container. Set the `CACHE_DIR` to models location path. Optionally add a `-d` option to You can use [pre-build docker image]() to run Lama Cleaner. The model will be downloaded to the cache directory when first time used.
the `docker run` command below to run as a daemon. You can mount existing cache directory to start the container,
so you don't have to download the model every time you start the container.
### Build Docker image The cache directories for different models correspond as follows:
``` - lama/ldm/zits/mat/fcf: /root/.cache/torch
docker build -f Dockerfile -t lamacleaner . - sd1.4: /root/.cache/huggingface
```
### Run Docker (cpu) ### Run Docker (cpu)
``` ```
docker run -p 8080:8080 -e CACHE_DIR=/app/models -v $(pwd)/models:/app/models -v $(pwd):/app --rm lamacleaner \ docker run -p 8080:8080 \
python3 main.py --device=cpu --port=8080 --host=0.0.0.0 -v /path/to/torch_cache:/root/.cache/torch \
-v /path/to/huggingface_cache:/root/.cache/huggingface \
--rm lamacleaner \
lama-cleaner --device=cpu --port=8080 --host=0.0.0.0
``` ```
### Run Docker (gpu) ### Run Docker (gpu)
``` ```
docker run --gpus all -p 8080:8080 -e CACHE_DIR=/app/models -v $(pwd)/models:/app/models -v $(pwd):/app --rm lamacleaner \ docker run --gpus all -p 8080:8080 \
python3 main.py --device=cuda --port=8080 --host=0.0.0.0 -v /path/to/torch_cache:/root/.cache/torch \
-v /path/to/huggingface_cache:/root/.cache/huggingface \
lama-cleaner --device=cuda --port=8080 --host=0.0.0.0
``` ```
Then open [http://localhost:8080](http://localhost:8080) Then open [http://localhost:8080](http://localhost:8080)
### Build Docker image
cpu only
```
docker build -f ./docker/CPUDockerfile -t lamacleaner .
```
gpu & cpu
- cuda11.6
- pytorch1.12.1
```
docker build -f ./docker/GPUDockerfile -t lamacleaner .
```
## One Click Installer
TODO

14
docker/CPUDockerfile Normal file
View File

@ -0,0 +1,14 @@
FROM python:3.7.4-slim-buster
RUN apt-get update && apt-get install -y --no-install-recommends \
software-properties-common \
libsm6 libxext6 ffmpeg libfontconfig1 libxrender1 libgl1-mesa-glx \
curl
RUN pip install --upgrade pip && \
pip install torch==1.12.1 --extra-index-url https://download.pytorch.org/whl/cpu
RUN pip install lama-cleaner
EXPOSE 8080
CMD ["bash"]

14
docker/GPUDockerfile Normal file
View File

@ -0,0 +1,14 @@
FROM nvidia/cuda:11.6.1-runtime-ubuntu20.04
RUN apt-get update && apt-get install -y --no-install-recommends \
software-properties-common \
libsm6 libxext6 ffmpeg libfontconfig1 libxrender1 libgl1-mesa-glx \
curl python3-pip
RUN pip3 install --upgrade pip && \
pip3 install torch==1.12.1 --extra-index-url https://download.pytorch.org/whl/cu116
RUN pip3 install lama-cleaner
EXPOSE 8080
CMD ["bash"]