7 Commits

Include renames

Author	SHA1	Message	Date
dimtoneff	31ac10c7ba	1. Added a new TextSave_VL node (inspired from "was" pack): ... - Added skip_overwrite parameter (BOOLEAN, default False) - When enabled, prevents overwriting existing files - Useful when purging bad captions and re-running workflows to save only missing descriptions 2. LoadImagesFromDirBatch_VL and LoadImagesFromDirList_VL nodes: - Added traverse_subdirs parameter (BOOLEAN, default False) - When enabled, recursively scans all subdirectories - Returns full absolute paths instead of just filenames - When disabled, maintains original behavior (current directory only) - Useful for organizing images in folder structures These enhancements provide better control over file handling in batch image captioning workflows while maintaining full backward compatibility.	2025-08-29 02:38:11 +02:00
dimtoneff	27a8154220	- added OpenGVLab/InternVL3_5-1B/38B models support for GGUF and transformers (GGUF may or may not work for you, depends on the llama.cpp versions and python bindings)	2025-08-27 13:32:09 +02:00
dimtoneff	389fe97681	- Updated the names of some conflicting nodes ... - README updates	2025-08-25 01:39:51 +02:00
dimtoneff	6c9feba487	- Batch Image Captioning support added to all nodes ... - Added a new workflow for Batch Image Captioning - Added seed option in all captioning nodes - Added new nodes for reading images batches from a single directory	2025-08-25 00:14:24 +02:00
dimtoneff	1744cefa4d	Fixes on the Keye nodes while performing tests with the model	2025-08-22 17:35:55 +02:00
dimtoneff	79b06598b5	- added support for 2 new models Ovis2.5-2B and Ovis2.5-9B ... - fixed model location issues - added a no-wait time for the VRAM cleaner node - updated the workflows	2025-08-20 20:10:50 +02:00
dimtoneff	6ab7af32e1	Added Xiaomi MiMo-VL, LiquidAI LFM2-VL, and AIDC-AI Ovis-U1 models nodes.	2025-08-20 16:34:21 +02:00