s

[AdamOswald]

Please read the contributing wiki page before submitting a pull request!

If you have a large change, pay special attention to this paragraph:

Before making changes, if you think that your feature will result in more than 100 lines changing, find me and talk to me about the feature you are proposing. It pains me to reject the hard work someone else did, but I won't add everything to the repo, and it's better if the rejection happens before you have to waste time working on the feature.

Otherwise, after making sure you're following the rules described in wiki page, remove this section and continue on.

Describe what this pull request is trying to achieve.

A clear and concise description of what you're trying to accomplish with this, so your intent doesn't have to be extracted from your code.

Additional notes and description of your changes

More technical discussion about your changes go here, plus anything that a maintainer might have to specifically take a look at, or be wary of.

Environment this was tested in

List the environment you have developed / tested this on. As per the contributing page, changes should be able to work on Windows out of the box.

• OS: [e.g. Windows, Linux]
• Browser: [e.g. chrome, safari]
• Graphics card: [e.g. NVIDIA RTX 2080 8GB, AMD RX 6600 8GB]

Screenshots or videos of your changes

If applicable, screenshots or a video showing off your changes. If it edits an existing UI, it should ideally contain a comparison of what used to be there, before your changes were made.

This is required for anything that touches the user interface.

Summary by CodeRabbit

• New Features

  • Introduced zooming and panning functionality for canvas images.
  • Added configurable hotkeys for canvas interactions.
  • Launched new mobile layout detection and adjustment.
  • Implemented soft inpainting with adjustable parameters.
  • Added extra options section for txt2img and img2img tabs.
  • Introduced post-processing scripts for cropping, captioning, and image flipping.
  • Enhanced functionality for managing neural networks and Lora modules.
  • Added support for Stable Diffusion 3 with new schedulers and samplers.

• Improvements

  • Enhanced error handling and logging across multiple modules.
  • Improved memory management and network loading logic.
  • Refined API responses and added new endpoints for better integration.
  • Updated configurations for stable diffusion models.
  • Performance optimizations to reduce resource usage and increase efficiency.

• UI Enhancements

  • Introduced new styling for canvas tooltips.
  • Enhanced user interface for managing extra networks with sorting, filtering, and metadata display.

• Bug Fixes

  • Corrected bracket checking in prompts to handle different types of brackets accurately.
  • Resolved issues with grids lacking comprehensive infotexts and improved file handling.

• Performance Optimizations

  • Optimized self-attention layers in U-Net and VAE models using Hypertile for better computational efficiency.