Hey all, we're excited to share the latest updates in our ongoing development, with a special focus on the Checkpoint Manager and Flux support in Inference. The Checkpoint Manager now includes a Metadata Editor, along with new features like drag-and-drop enhancements and file size sorting, giving you greater control and flexibility in managing your models. Additionally, we’ve added Flux support in Inference.
We’re also thrilled to announce significant performance enhancements in the Outputs Browser and Model Browser that will make your experience smoother and faster than ever. We've optimized image loading across the app, delivering up to a 4x speed increase for local images and up to an incredible 17x boost for remote images! Additionally, we've improved memory management, reducing peak memory usage by up to 50% and ensuring that memory is released more efficiently when images are no longer in view. You’ll also notice more fluid animations when scrolling through large collections, making navigation through your outputs and models a seamless experience.
Added Settings option "Console: History Size" to adjust the number of lines stored in the console history when running packages. Defaults to 9001 lines.
Inference
Added new project type, "Flux Text to Image", a Flux-native workflow for text-to-image projects
Added support for the FP8 version of Flux in the regular Text to Image and Image to Image workflows via the "Use Flux Guidance" Sampler Addon
Model Browser
Added AuraFlow & Flux base model types to the CivitAI model browser
Added CLIP/Text Encoders section to HuggingFace model browser
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 "unet" shared model folder for ComfyUI
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)
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
Fixed "The version of the native libSkiaSharp library (88.1) is incompatible with this version of SkiaSharp." error for Linux users
Fixed download links for IPAdapters 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
A heartfelt thank you to our Visionary-tier Patreon supporter, Scopp Mcdee! We truly appreciate your continued support!
Get this and other development releases as auto-updates in the app
Or
Download manually by connecting your Patreon account in your lykos.ai/profile then find this download at lykos.ai/downloads