v2.13.0

Added

• Added new package - ComfyUI-Zluda - for AMD GPU users on Windows
• Added file sizes to the Checkpoint Manager tab
• Added the Discrete Model Sampling addon for Inference samplers, allows selecting different sampling methods, such as v_prediction, lcm, or x0, and optionally adjusts the model’s noise reduction strategy with the zero-shot noise ratio (ZSNR) toggle.
• Added Default GPU override in Settings -> System Settings -> Default GPU
• Added new "Copy" menu to the Inference gallery context menu, allowing you to copy generation parameters as well as the image
• Added "StableDiffusion" folder as an option when downloading Flux models in the CivitAI model browser
• Added support for SD3.5 in Inference
• Added CLIP_G to HuggingFace model browser
• Added search bar to the Installed Workflows tab
• Added "Search with Google" and "Search with ChatGPT" to the package console output & install progress console output context menus
• Added "Date Created" and "Date Last Modified" sorting options to the Checkpoints tab
• Added a new "Extension Packs" section to the extension manager, allowing you to create packs for easier installation of multiple extensions at once
• Added "Search by Creator" command to Civitai browser context menu
• Added Beta scheduler to the scheduler selector in Inference
• Added zipping of log files and "Show Log in Explorer" button on exceptions dialog for easier support
• Added max concurrent downloads option & download queueing for most downloads
• Added the ability to change the Models directory separately from the rest of the Data directory. This can be set in Settings > Select new Models Folder
• Added InvokeAI model sharing option

Changed

• Improved Packages Page grid layout to dynamically stretch to fill available space
• Text Encoder / CLIP selection in Inference is now enabled via the cogwheel ⚙️ button next to the model selector
• Updated Civitai model descriptions to properly render the interactive elements
• Adjusted the Branch/Release toggle during package install flow to be a little more obvious
• Updated the Dock library used for Inference - fixes some weirdness with resizing / rearranging panels
• New file format and key derivation for protecting locally encrypted secrets (i.e. Civit / Lykos accounts) that is no longer dependent on the OS Version. This should prevent system updates from clearing account logins.
• (Internal) Updated to .NET 9 Runtime and Avalonia 11.2.2 for performance improvements, lower memory usage, and bug fixes
• Updated pytorch index to rocm6.2 for AMD users of ComfyUI on Linux

Fixed

• Fixed text alignment issues in the Downloads tab for certain long names / progress infos
• Improved startup performance and resource usage with optimizations to hardware lookups. Moved reflection usages in dependency injection to source generation.
• Fixed an issue with ComfyUI-Impact-Subpack not being installed when using FaceDetailer in Inference
• Fixed GGUF models not showing in Inference without the GGUF extension installed (this means it will now properly prompt you to install the extension as well)

Supporters

Visionaries

• We're extremely grateful to our incredible Visionary-tier Patreon supporters, Waterclouds and TheTekknician! Thank you very much for your unwavering support!

Pioneers

• Many thanks to our amazing Pioneer-tier Patreon supporters, tankfox, Mr Unknown, Szir777, and our newest Pioneer, NowFallenAngel! Your generous support is very much appreciated!

v2.12.4

Added

• Added new package - CogVideo - many thanks to @NullDev for the contribution!
• Added more formatting options for Inference output filenames - thanks to @yansigit!

Changed

• Model browser base model types are now loaded dynamically from CivitAI, reducing the need for updates to add new types

Fixed

• Fixed crash when clicking "Remind me Later" on the update dialog
• Fixed some cases of crashing when GitHub API rate limits are exceeded
• Fixed Git missing from env vars when running SwarmUI
• Fixed missing package thumbnails due to moved or inaccessible urls
• Fixed an issue with updating FluxGym in certain cases - thanks to @NullDev!
• Fixed a typo in the Japanese translation - thanks to @mattyatea!

Supporters

Visionaries

• A huge thank you to our dedicated Visionary-tier Patreon supporter, Waterclouds! We’re thrilled to have your ongoing support!

Pioneers

• Shoutout to our great Pioneer-tier patrons: tankfox, tanangular, Mr. Unknown, Szir777, and our newest Pioneer, Tigon!. Your continued support is greatly appreciated!

v2.12.3

Added

• Added new package - SimpleSDXL - many thanks to @NullDev for the contribution!
• Added new package - FluxGym - many thanks to @NullDev for the contribution!
• Added more base model types to the CivitAI Model Browser & Checkpoint Manager

Changed

• Updated Russian translations thanks to @vanja-san
• Updated Simplified Chinese translations thanks to @QL-boy

Fixed

• Fixed some cases of FileTransferExists error when running re/Forge or Automatic1111
• Fixed update check not happening on startup for some users
• Fixed error when installing Automatic1111 on macOS
• Fixed some instances of Civitai model browser not loading new results
• Fixed "Unsupported Torch Version: Cuda" errors when installing a1111

Supporters

Visionaries

• A huge shout-out to our dedicated Visionary-tier Patreon supporter, Waterclouds! Your unwavering support is greatly appreciated!

Pioneers

• We'd also like to express our gratitude to our amazing Pioneer-tier patrons: tankfox, tanangular, Mr. Unknown, and Szir777! Your ongoing support means a great deal!

v2.12.2

Added

• Added Beta scheduler to the scheduler selector in Inference

Changed

• (Internal) Updated to Avalonia 11.1.4

Fixed

• Fixed ComfyUI NF4 extension not installing properly when prompted in Inference
• Fixed #932, #935, #939 - InvokeAI failing to update
• Fixed repeated nested folders being created in Models/StableDiffusion when using Forge in Symlink mode in certain conditions. Existing folders will be repaired to their original structure on launch.
• Fixed minimize button not working on macOS

Supporters

Visionaries

• We extend our heartfelt appreciation to our dedicated Visionary-tier Patreon supporter, Waterclouds. Your ongoing support is invaluable!

Pioneers

• We’d also like to thank our great Pioneer-tier patrons: tankfox, tanangular, Mr. Unknown, and Szir777. Your continuous support means a lot!

v2.12.1

Fixed

• Fixed #916 - InvokeAI failing to install/update on macOS
• Fixed #914 - Unable to use escaped colon : character in Inference prompts
• Fixed #908 - Forge unable to use models from "unet" shared folder
• Fixed #902 - Images from shared outputs folder not displaying properly in Stable Diffusion WebUI-UX
• Fixed #898 - Incorrect launch options for RuinedFooocus
• Fixed index url parsing in Python Packages window causing some packages to not have versions available
• Fixed a crash when switching between Model Sharing options for certain packages

Supporters

Visionaries

• A sincere thank you to our valued Visionary-tier Patreon supporter, Waterclouds. Your continued support is truly appreciated, and we’re grateful to have you with us on this journey.

Pioneers

• We’d also like to extend our gratitude to our Pioneer-tier patrons: tankfox, tanangular, Mr. Unknown, and Szir777. Your ongoing support means a great deal to us!

v2.12.0

Added

New Packages

• Fooocus - mashb1t's 1-Up Edition by mashb1t
• Stable Diffusion WebUI reForge by Panchovix

Inference

• Added type-to-search for the Inference model selectors. Start typing while the dropdown is open to navigate the list.

  • 

• Added "Model Loader" option to Inference, for loading UNet/GGUF/NF4 models (e.g. Flux)

  • 

• Added support for the FP8 version of Flux in the default Model Loader via the "Use Flux Guidance" Sampler Addon

  • 

• Added trigger words to the Inference Extra Networks (Lora/Lyco) selector for quick copy & paste

• Image viewer context menus now have 2 options: Copy (Ctrl+C) which now always copies the image as a file, and Copy as Bitmap (Shift+Ctrl+C) (Available on Windows) which copies to the clipboard as native bitmap. This changes the previous single Copy button behavior that would first attempt a native bitmap copy on Windows when available, and fall back to a file copy if not.

• Added Face Detailer module to Inference

  • 
  • 

Package Manager

• Added Python dependencies override table to package installation options, where the default pip packages may be overriden for a package's install and updates. This can be changed later or added to existing packages through Package Menu > Python Dependencies Override

  • 
  • 

• Added "Change Version" option to the package card overflow menu, allowing you to downgrade or upgrade a package to a specific version or commit (#701, #857)

• Added "Disable Update Check" option to the package card overflow menu, allowing you to disable update checks for a specific package

• Added Custom commit option in the Advanced Options for package installs (#670, #839, #842)

• Added macOS support for Fooocus & related forks

• Added Intel OneAPI XPU backend (IPEX) option for SD.Next

Checkpoint Manager

• Added new Metadata Editor (accessible via the right-click menu), allowing you to create or edit metadata for models
  • 
• Added "New Directory" and "Delete" options to the context menu of the tree view.
• Added new toggle for drag & drop - when enabled, all selected models will now move together with the dragged model
• Added "File Size" sorting option
• Added "Hide Empty Categories" toggle
• Added "Select All" button to the InfoBar (shown when at least one model is selected)
• Added "Show NSFW Images" toggle

Model Browser

• Added "Hide Installed Models" toggle to the CivitAI Model Browser
• Added toggle to hide "Early Access" models in the CivitAI Model Browser
• Added ultralytics models to HuggingFace model browser

Other

• Added "Sign in with Google" option for connecting your Lykos Account on the Account Settings page
• Added zoom sliders for Outputs, Checkpoints, and Model Browser pages
• Added Settings option "Console: History Size" to adjust the number of lines stored in the console history when running packages. Defaults to 9001 lines.
  • 
• Added optional anonymous usage reporting for gauging popularity of package installs and features. You will be asked whether you want to enable this feature on launch, and can change your choice at any time in Settings > System > Analytics
• Added "Run Command" option in Settings for running a command with the embedded Python or Git executables
  • 
• Added "Enable Long Paths" option for Git to the Settings page
• Added "System Settings > Enable Long Paths" option to enable NTFS long paths on Windows
• Added Korean translations thanks to maakcode!
• (Windows, Linux) Added Vulkan rendering support using launch argument --vulkan. (On Windows, the default WinUI composition renderer is likely still preferrable. Linux users are encouraged to try the new renderer to see if it improves performance and responsiveness.)

Changed

• Optimized image loading across the app, with loading speed now up to 4x faster for local images, and up to 17x faster for remote images
• Image loading in the Outputs page now uses native memory management for ~2x less peak memory usage, and will release memory more quickly when switching away from the Outputs page or scrolling images out of view
• Improved animation fluidity of image rendering while scrolling quickly across large collections (e.g. Outputs, Model Browser)
• ComfyUI will no longer be pinned to torch 2.1.2 for nvidia users on Windows (#861)
• Model browser download progress no longer covers the entire card for the entire duration of the download
• Updated torch index to rocm6.1 for AMD users of ComfyUI
• Show better error message for early access model downloads
• Updated torch version for a1111 on mac
• Checkpoints tab now shows "image hidden" for images that are hidden by the NSFW filter
• OAuth-type connection errors in Account Settings now show a more detailed error message
• The "Download Failed" message for model downloads is now persistent until dismissed
• Separated the Generate button from the prompt control in Inference so it can be moved like other controls
• Updated translations for Turkish and Russian
• (Internal) Updated Avalonia to 11.1.3 - Includes major rendering and performance optimizations, animation refinements, improved IME / text selection, and improvements for window sizing / z-order / multi-monitor DPI scaling. (avaloniaui.net/blog/avalonia-11-1-a-quantum-leap-in-cross-platform-ui-development)
• (Internal) Updated SkiaSharp (Rendering Backend) to 3.0.0-preview.4.1, potentially fixes issues with window rendering artifacts on some machines.
• (Internal) Updated other dependencies for security and bug fixes.

Fixed

• Fixed #888 - error updating kohya_ss due to long paths
• Fixed some ScrollViewers changing scroll position when focus changes
• Fixed CivitAI Model Browser sometimes incorrectly showing "No models found" before toggling "Show NSFW" or "Hide Installed" filters
• Fixed SwarmUI settings being overwritten on launch
• Fixed issue where some Inference-generated images would be saved with the bottom missing
• Fixed #851 - missing fbgemm.dll errors when using latest torch with certain packages
• Fixed issue where ApproxVAE models would show up in the VAE folder
• Fixed #878 - Checkpoints tab will no longer try to browse directories it can't access
• Fixed crash when opening Settings page when refreshing CivitAI account status results in an error
• Fixed #814, #875 - Error when installing RuinedFooocus
• LORAs are now sorted by model name properly in the Extra Networks dropdown
• (macOS) Fixed OAuth connection prompts in Account Settings not automatically updating status after connection. Custom URL schemes are now also supported on macOS builds.

Supporters

Visionaries

• A heartfelt thank you to our Visionary-tier patron, Waterclouds! We greatly appreciate your continued support!

Pioneers

• A special shoutout to our Pioneer-tier patrons: tankfox, tanangular, Mr. Unknown, and Szir777! Your unwavering support means a great deal!

v2.11.8

Added

• Added Flux & AuraFlow types to CivitAI Browser
• Added unet folder links for ComfyUI thanks to jeremydk
• Added CLIP folder links for Forge

Changed

• Updated Brazilian Portuguese translations thanks to thiagojramos

Fixed

• Fixed #840 - CivitAI model browser not loading search results
• Fixed SwarmUI settings being overwritten on launch
• Fixed #832 #847 - Forge output folder links pointing to the incorrect folder
• Fixed errors when downloading models with invalid characters in the file name
• Fixed error when installing RuinedFooocus on nvidia GPUs

Supporters

Pioneers

• A big shoutout to our Pioneer-tier patrons: tankfox, tanangular, Mr. Unknown, and Szir777! We deeply appreciate your ongoing support!

v2.11.7

Changed

• Forge will use the recommended pytorch version 2.3.1 the next time it is updated
• InvokeAI users with AMD GPUs on Linux will be upgraded to the rocm5.6 version of pytorch the next time it is updated

Fixed

• Fixed Inference not connecting with "Could not connect to backend - JSON value could not be converted" error with API changes from newer ComfyUI versions

Supporters

Pioneers

• Shoutout to our Pioneer-tier supporters on Patreon: tankfox, tanangular, Mr. Unknown, and Szir777! Thanks for all of your continued support!

v2.11.6

Fixed

• Fixed incorrect IPAdapter download links in the HuggingFace model browser
• Fixed potential memory leak of transient controls (Inference Prompt and Output Image Viewer) not being garbage collected due to event subscriptions
• Fixed Batch Count seeds not being recorded properly in Inference projects and image metadata
• Fixed #795 - SwarmUI launch args not working properly
• Fixed #745 - not passing Environment Variables to SwarmUI

Supporters

Visionaries

• Shoutout to our Visionary-tier Patreon supporter, Scopp Mcdee! Huge thanks for your continued support!

Pioneers

• Many thanks to our Pioneer-tier supporters on Patreon: tankfox, tanangular, Mr. Unknown, and Szir777! Your continued support is greatly appreciated!

v2.11.5

Added

• Added DoRA category to CivitAI model browser

Fixed

• Fixed TaskCanceledException when adding CivitAI Api key or searching for models when the API takes too long to respond. Retry and timeout behavior has been improved.
• Fixed #782 - conflict error when launching new versions of Forge
• Fixed incorrect torch versions being installed for InvokeAI
• Fixed ArgumentOutOfRangeException with the Python Packages dialog ItemSourceView when interacting too quickly after loading.

Supporters

Visionaries

• Shoutout to our Visionary-tier Patreon supporters, Scopp Mcdee, Waterclouds, and our newest Visionary, Akiro_Senkai! Many thanks for your generous support!

Pioneers

• Many thanks to our Pioneer-tier supporters on Patreon, tankfox, tanangular, and our newest Pioneers, Mr. Unknown and Szir777! Your support is greatly appreciated!