Easy Diffuser is a chrome extension that handles user interaction. The chrome extension sends image to ML model, gets images or tokens as response to support Stable Diffusion users.
1.Features
6.Licenses
This is the UI of the chrome extension.
Import an image
When right-clicking on the image in any webpage, the menu will show 'Import to Easy Diffuser' button. This button imports image into Easy Diffuser chrome extension.
Choose a feature by selecting a radio button
By selecting radio button, user can use either 'Image to Image' or 'Image to Tag' function. Checkbox under radio buttons enables filtering sexual contents when using functions, and it is set to be filtered by default.
Execute Button
By clicking execute button, easy diffuser runs selected function and exports result.
Loader
When function is running, circular loader rotates until the result is outputted.
Img2Img Result
Img2Img result is shown below the button, as a form of an image. The image is saved in ./output directory.
Img2Tag Result
Img2Tag result is shown below the button, as having cards for each tokens in positive and negative prompt. By clicking 'x' on each cards, tags are deleted and not included in copy.
Copying Resulted Tags
By clicking 'Copy Positive' and 'Copy Negative' buttons, tags can be easily copied. As each results are copied, alert message shows as the copy succeeded.
- Move to
chrome://extensions/page - Toggle 'Developer Mode' button on right-top of the page
- Import chrome extension in ./chrome-extension/dist
- Clone the repository:
git clone https://huggingface.co/leeyunjai/img2txt - Define the software version using the
Requirements.txtfile in theEasy-Diffuser/Modelfolder. - Insert the following code into the
webui-user.batfile:set COMMANDLINE_ARGS=--api - The installation is now complete.
- run local with http server
cd ./chrome-extension/local
python server.py
cd ../../model
python http_run.py
- open chrome extension by clicking button
- Find any image on web. By right clicking on the image, you can easily import image to the extension by clicking import-image button.
- Select either Image to Image or Image to Tag function.
- Click execute button.
- Receive results and use it as you want.
Easy Diffuser is implemented by 박찬호, 허찬용.
If there's any need for support or feedback, feel free to add issues in the corresponding repository.
Or you can freely contact via email:
박찬호 : chanho.park@dankook.ac.kr
허찬용 : yong5835@gmail.com
Easy Diffuser was developed to address the following issues:
- Users spend a lot of time generating diffusion images.
- Repeated generation of diffusion images consumes a lot of computing resources and power.
- It is difficult to share the experience of the image generation process among users.
To solve these problems, Easy Diffuser provides the following two functions:
-
Extraction of generation conditions from a reference image:
- Users can load a reference image and extract generation conditions. Easy Diffuser converts the input image into text using OpenAI's CLIP and translates it into tag combinations using a transformer-based translator. The resulting tag combinations can be used as inputs for
txt2imgin the WebUI.
- Users can load a reference image and extract generation conditions. Easy Diffuser converts the input image into text using OpenAI's CLIP and translates it into tag combinations using a transformer-based translator. The resulting tag combinations can be used as inputs for
-
Image-to-image generation using a reference image:
- The existing image-to-image generation functionality requires users to go through steps such as finding, saving, and loading images, or using images generated with
txt2img. Easy Diffuser provides a convenient menu to directly load images from web pages into the WebUI'simg2imggeneration.
- The existing image-to-image generation functionality requires users to go through steps such as finding, saving, and loading images, or using images generated with