Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Buckets new
  • Docs
  • Enterprise
  • Pricing
    • Website
      • Tasks
      • HuggingChat
      • Collections
      • Languages
      • Organizations
    • Community
      • Blog
      • Posts
      • Daily Papers
      • Learn
      • Discord
      • Forum
      • GitHub
    • Solutions
      • Team & Enterprise
      • Hugging Face PRO
      • Enterprise Support
      • Inference Providers
      • Inference Endpoints
      • Storage Buckets

  • Log In
  • Sign Up

Artedaut
/
Parser

Text-to-Image
Diffusers
stable-diffusion
lora
template:sd-lora
Model card Files Files and versions
xet
Community

Instructions to use Artedaut/Parser with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Libraries
  • Diffusers

    How to use Artedaut/Parser with Diffusers:

    pip install -U diffusers transformers accelerate
    import torch
    from diffusers import DiffusionPipeline
    
    # switch to "mps" for apple devices
    pipe = DiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-3-medium", dtype=torch.bfloat16, device_map="cuda")
    pipe.load_lora_weights("Artedaut/Parser")
    
    prompt = "Description: The Data Extractor Extension is a browser extension designed to help users conveniently extract data from web pages and save it in Excel format. The primary goal of the extension is to provide a tool for quick and efficient data collection from websites, such as prices, links, images, and more. The extension features an integrated interface for configuring and managing the data extraction process, as well as storing a history of requests for further analysis. Core Features      Adding Input Fields:         Users can add new input fields for specifying CSS classes and column names using the \"Add Field\" button.         Fields include options to specify a CSS class, column name, and whether to parse links.      Data Extraction:         The \"Extract Data\" button allows users to extract data from a web page based on the specified CSS classes.         Data can be extracted as text content, image URLs, or link URLs.      Saving Data in Excel Format:         Extracted data is saved in Excel (.xlsx) format, making it easy to analyze and process.      Request History:         History keeps track of past requests, including the webpage URL, date and time of the request, and field settings.         Users can view the history of requests and delete all records.      Settings:         Users can configure extension settings through a dedicated settings page.         Settings allow for adjustments to data saving parameters and interface display.      Content Interaction:         The \"Add Field\" and \"Extract Data\" buttons interact directly with the web page via content scripts.         Users can enable or disable content scripts on the active page.      Minimize Window:         A \"Minimize\" button allows users to collapse the extension window to free up screen space.  Additional Features      Import/Export Settings:         The import and export functions have been removed, as request history now serves as the storage solution for data.      Window Interaction:         The extension window opens with the content script when clicking the extension icon, ensuring access to all features without closing the current tab.      Link Parsing Checkbox Functionality:         Checkbox options for parsing links from web pages have been added, allowing users to save data only from active links.  Ideas for Improvement      UI/UX Enhancement:         The interface can be improved to enhance usability and design.      Expanded Data Extraction Capabilities:         Support for additional data types or output formats can be added.      Automation and Scheduling:         Implementing automatic data extraction based on a schedule or specific events.      Integration with Other Services:         Connecting to third-party services for further data processing or automatic cloud storage.  This description provides a clear overview of the extension's functional capabilities and its purpose."
    image = pipe(prompt).images[0]
  • Notebooks
  • Google Colab
  • Kaggle
  • Local Apps
  • Draw Things
  • DiffusionBee
Parser
191 kB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 2 commits
Artedaut's picture
Artedaut
Add 2 files
fdc24d2 verified almost 2 years ago
  • images
    Add 2 files almost 2 years ago
  • .gitattributes
    2.31 kB
    initial commit almost 2 years ago
  • 08.zip

    Pickle imports

    • No problematic imports detected

    What is a pickle import?

    34.7 kB
    xet
    Add 2 files almost 2 years ago
  • README.md
    6.68 kB
    initial commit almost 2 years ago