Skip to content

Releases: chaiNNer-org/chaiNNer

Alpha v0.24.1

07 Jun 21:36
Compare
Choose a tag to compare

This update contains a few bug fixes and some QOL improvements.

What's Changed

Bug Fixes

Full Changelog: v0.24.0...v0.24.1

Alpha v0.24.0

01 Jun 19:50
Compare
Choose a tag to compare

This update brings many new major features to chaiNNer, including but not limited to conditional branching (via two new nodes: Conditional and Compare), node passthrough/skipping, new themes, PyTorch optimizations, and many more fixes and quality of life improvements all around.

The conditional and compare nodes bring a long-awaited feature: branching support. Well, mostly. These nodes allow you to switch between inputs based on a condition created by comparing two values in various ways. This means users can finally set up chains that do one thing under a certain condition and another thing under a different one (e.g. if an image is over a certain size vs under a certain size). The thing to keep in mind is how you have to set this up might be opposite of what's intuitive. Since you're switching between values, it's what comes before the condition that is decided between, not what comes after.

The disable toggle has also been replaced with a button that allows you to swap between three states: "enabled", "disabled", and "skipped". In skipped mode, the node will not be run, but it also will not disable downstream nodes like disabling it would. This is another heavily-requested feature that we are happy is finally in chaiNNer.

New themes can be selected in settings. This is semi-experimental as we plan on adding support for fully custom themes in the future, as well as improving the existing default selection. The current selection is mainly just a proof of concept to show that we can support themes of some kind, and also to give users some options for customization. We'd love to hear feedback on the current selection and if you have any suggestions on themes to add.

PyTorch upscaling has been heavily optimized. I was able to using a visual profiling tool (called VizTracer, which I highly recommend for anyone wanting to optimize a python project) to see what was slowing down upscaling. Upscaling has been optimized to a point where it's roughly 1.25x faster than it was before (though YMMV depending on what model you use, as well as other factors). While not perfect, it's still a large improvement and should help your PyTorch upscaling chains run faster.

Major Changes

Minor Changes

New Nodes

Bug Fixes

New Contributors

Full Changelog: v0.23.2...v0.24.0

Alpha v0.23.3

24 Apr 18:19
Compare
Choose a tag to compare

This is a hotfix release to fix a regression introduced in the v0.23.2 which caused iterators to error when running. Apologies to anyone who was affected by this issue.

Bug Fixes

Alpha v0.23.2

23 Apr 23:34
Compare
Choose a tag to compare

This update fixes a few bugs and adds some new features.

Please note: If you install or update chaiNNer and get a critical error upon setup completion, please attempt restarting chaiNNer before reporting.

What's Changed

New Nodes

Bug Fixes

New Contributors

Full Changelog: v0.23.1...v0.23.2

Alpha v0.23.1

12 Apr 14:30
Compare
Choose a tag to compare

What's Changed

Bug Fixes

Full Changelog: v0.23.0...v0.23.1

Alpha v0.23.0

11 Apr 03:08
Compare
Choose a tag to compare

This biggest part of this release was a bunch of internal changes we made that aren't super easily reflected to users. However, you will (hopefully) notice a bit more stability in certain areas.

There are a bunch of new features, changes, bug fixes, and all the rest of the usual stuff included as well.

As always, please report any new issues that pop up in this release.

Major Changes

Dependency Updates

  • (PyTorch) Update Spandrel for improved model support by @RunDevelopment, @joeyballentine in #2655, #2710, #2661, #2646
    • Adds support for RGT, Restormer, FFTformer, M3SNet, DCTLSA, APISR, MixDehazeNet, ATD, AdaCode, MPRNet, MIRNet2, DnCNN, FDnCNN, and DRUNet
    • Removes SPSR support
  • (ONNX) Update ONNX & ONNX Runtime which fixes execution issues @joeyballentine in #2717

New Nodes

Minor Changes

Bug Fixes

Full Changelog: v0.22.2...v0.23.0

Alpha v0.22.2

01 Mar 23:26
Compare
Choose a tag to compare

What's Changed

New Nodes

Bug Fixes

Full Changelog: v0.22.1...v0.22.2

Alpha v0.22.1

28 Feb 00:16
Compare
Choose a tag to compare

What's Changed

New Nodes

Bug Fixes

Full Changelog: v0.22.0...v0.22.1

Alpha v0.22.0

20 Feb 00:15
Compare
Choose a tag to compare

Dependency Changes

  • Auto update dependencies by default, except GPU Pytorch & Torchvision by @joeyballentine in #2524
    • Most dependencies will now be auto-updated if installed, to avoid any issues due to users not updating
  • (PyTorch) Update Spandrel to v0.2.2 by @joeyballentine in #2553
    • Fixes SPAN model loading when created by updated neosr

Major Changes

  • Collapsing & expanding nodes by @joeyballentine, @RunDevelopment in #2544, #2560
    • A new button on the top-left corner of nodes to collapse or expand nodes
  • Add "Breakpoints" feature to edges for custom edge routing by @joeyballentine, @RunDevelopment in #2548, #2583, #2586
    • Right-click > Add Breakpoint or hold alt and click to add a "breakpoint" to a connection line
  • Arrow-key navigation in node search panel by @joeyballentine in #2575
    • The viewport's right-click/drag-out node search panel now supports arrow key navigation

Changes

New Nodes

Bug Fixes

New Contributors

Full Changelog: v0.21.2...v0.22.0

Alpha v0.21.2

24 Jan 03:47
Compare
Choose a tag to compare

This update fixes a few things as well as makes some general improvements. You know the drill.

Dependency Updates

  • (PyTorch) Update to spandrel v0.2.1 by @RunDevelopment in #2487
    • Adds support for SAFMN and fixes a few minor issues with upscaling small images.

What's Changed

New Nodes

Bug Fixes

Other/Dev Changes

Full Changelog: v0.21.1...v0.21.2