v6.14.1
MinishLab/semblev6.14.1Sep 6, 2026by lstein
Upgrading?
AI Summary
This release focuses on bug fixes for version 6.14, adding minor features such as the ability to screenshot workflows as PNGs, middle-click functionality in the gallery to open media in new tabs, and support for Krea-2 LoRAs built with ai-toolkit's DoRA magnitudes.
Key Highlights
- Screenshot and save workflows as PNGs
- Middle click in gallery opens media in new browser tab
- Support for Krea-2 LoRAs using ai-toolkit DoRA magnitudes
- Security fix for AlibabaCloud image downloads
- Improved VRAM memory reservation for VAEs
New Features
- Screenshot workflows as PNGs
- Middle click opens media in new browser tab
- Support for Krea-2 LoRAs with DoRA magnitudes
Full Release Notes
This release fixes a few bugs in version 6.14 and adds a couple of minor features that didn't make it into the previous release. For a full rundown of recently-added features please see [6.14.0 Release](https://github.com/invoke-ai/InvokeAI/releases/tag/v6.14.0) ## New Features in this release * Workflows can now be screenshot and saved as PNGs (@JPPhoto) * Middle clicks in the gallery will now open the media in a new browser tab. Enable *Use Middle Click to Open Images/Videos in New Tab* in settings to get this feature. (@DustyShoe ) * Krea-2 LoRAs built with ai-toolkit's DoRA magnitudes are now supported (@Pfannkuchensack ) ## Bug fixes * More robust handling of Kohya keys (@Pfannkuchensack ) * Close a security hole in the handling of AlibabaCloud image downloads (@wunianze666-netizen ) * Improve VRAM memory reservation for VAEs (@Pfannkuchensack ) * Improve internal memory management at shutdown time (@lstein ) ## Full change list with pointers to detailed descriptions: * Lstein/chore/6.14.0 post1 bump by @lstein in https://github.com/invoke-ai/InvokeAI/pull/9543 * Fix truncated image moves by @JPPhoto in https://github.com/invoke-ai/InvokeAI/pull/9545 * Workflow screenshot as PNG by @JPPhoto in https://github.com/invoke-ai/InvokeAI/pull/9501 * fix(lora): support ai-toolkit DoRA magnitudes for Krea-2 LoRAs by @Pfannkuchensack in https://github.com/invoke-ai/InvokeAI/pull/9517 * fix(krea2-lora): validate kohya keys by un-flattening, not by prefix by @Pfannkuchensack in https://github.com/invoke-ai/InvokeAI/pull/9518 * fix(ui): open media URLs directly in new tabs by @DustyShoe in https://github.com/invoke-ai/InvokeAI/pull/9523 * fix(external): guard AlibabaCloud image downloads by @wunianze666-netizen in https://github.com/invoke-ai/InvokeAI/pull/9525 * fix(fp8): honor every declared skip list, and stop overshooting the RAM reservation by @Pfannkuchensack in https://github.com/invoke-ai/InvokeAI/pull/9538 * perf(video): stream uploads into a single on-disk copy by @lstein in https://github.com/invoke-ai/InvokeAI/pull/9396 * chore(deps): bump diffusers to 0.40.0 by @lstein in https://github.com/invoke-ai/InvokeAI/pull/9550 * fix(download): require trust for injected sessions by @wunianze666-netizen in https://github.com/invoke-ai/InvokeAI/pull/9524 * fix(ui): stop range-based fetching hooks from spinning in a render loop by @lstein in https://github.com/invoke-ai/InvokeAI/pull/9439 * docs: fix typo acheived -> achieved by @vaibhav8a in https://github.com/invoke-ai/InvokeAI/pull/9557 * fix(flux2): estimate working memory for denoise and both VAE directions by @Pfannkuchensack in https://github.com/invoke-ai/InvokeAI/pull/9519 * chore(deps): remove dependency on Jupyter Notebook (and update uv) by @keturn in https://github.com/invoke-ai/InvokeAI/pull/9409 * fix(images): make single-image and intermediate deletion transactional by @lstein in https://github.com/invoke-ai/InvokeAI/pull/9361 * fix(model cache): evict records at shutdown() instead of only releasing shared weights by @lstein in https://github.com/invoke-ai/InvokeAI/pull/9494 ## New Contributors * @vaibhav8a made their first contribution in https://github.com/invoke-ai/InvokeAI/pull/9557 **Full Changelog**: https://github.com/invoke-ai/InvokeAI/compare/v6.14.0...v6.14.1
Related Repositories
public-apis/public-apis★ 491,123
A collective list of free APIs
NousResearch/hermes-agent★ 255,883
The agent that grows with you
yt-dlp/yt-dlp★ 199,986
A feature-rich command-line audio/video downloader
microsoft/markitdown★ 191,478
Python tool for converting files and office documents to Markdown.
Significant-Gravitas/AutoGPT★ 187,698
AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.