Hi again, thanks for all your support and suggestions after our Inference release. We're working on adding support for shared output image viewing next, along with custom file name formatting.
Added
- Added new shared outputs page, configure packages to use shared output directories by toggling "Output sharing" in their config menus
- Inference image loading is now done over API instead of file paths, the latency from generation completion to image load should now be even faster.
- Added custom file name formatting patterns for Inference file outputs. Configure this on the settings page. Selecting the text box will show a popup with supported variables. All variables need to go inside curly braces {}.
- You can use Python-like index notation to slice parts of replacement variables. For example, "{prompt}" will insert the full positive prompt, while "{prompt[:10]}" will insert up to the first 10 characters of the positive prompt.
Fixed
- Fixed interactions in Inference gallery with images deleted externally from file explorer or other sources causing a crash