silveroxides
94d2a93b91
fix layer renaming issues
2026-05-16 16:32:44 +02:00
silveroxides
bb915f0599
refactor all saves to use IncrementalSafetensorsWriter
2026-05-16 11:07:20 +02:00
silveroxides
f9a96d78a2
Bump version from 0.3.7 to 0.3.8
2026-05-10 18:52:38 +02:00
silveroxides
8ee4654c80
Improve layer filters in the merger nodes
2026-05-10 18:52:10 +02:00
silveroxides
73ce12cf9f
Bump version from 0.3.6 to 0.3.7
2026-05-10 18:22:23 +02:00
silveroxides
21c0972a5b
Refine LoRA extraction to output accurate layer formats across the board and add experimental new DARE+Ties merge operation variant
2026-05-10 18:21:54 +02:00
silveroxides
3bcd2bf3f8
Bump version from 0.3.5 to 0.3.6
2026-05-09 03:09:30 +02:00
silveroxides
29f03fe979
Add new 'enhanced' PowerUp/DARE-Ties merge modes
2026-05-09 03:08:57 +02:00
silveroxides
2e6eec7f63
Bump version from 0.3.4 to 0.3.5
2026-05-02 19:25:55 +02:00
silveroxides
2e0f79a396
handle Anima net. layer prefix
2026-05-02 19:25:20 +02:00
silveroxides
9f5d894320
Bump version from 0.3.3 to 0.3.4
2026-04-29 13:26:32 +02:00
silveroxides
10d0547e05
bump unifiedefficientloader requirement
2026-04-29 12:39:20 +02:00
silveroxides
d2adfb3183
Bump version from 0.3.2 to 0.3.3
2026-04-27 11:49:18 +02:00
silveroxides
8fbbe8a5ae
refactor to use only unifiedefficientloader and fix header loading
2026-04-27 11:48:53 +02:00
silveroxides
308d839ce3
Bump version from 0.3.1 to 0.3.2
2026-04-26 20:21:39 +02:00
silveroxides
7f6e2c4300
Add DARE+TIES Merge mode
2026-04-26 20:21:13 +02:00
silveroxides
a8098b769e
Bump version from 0.3.0 to 0.3.1
2026-04-26 13:23:17 +02:00
silveroxides
ff1706a320
make merger go brrrrr
2026-04-26 12:41:19 +02:00
silveroxides
6dd89d4bbc
Bump version to 0.3.0
2026-04-25 22:11:07 +02:00
silveroxides
4a2faa5a8e
Add incremental saving when merging
2026-04-25 22:09:24 +02:00
silveroxides
bb787378fe
add usage of unifiedefficientloader module
2026-04-25 19:06:50 +02:00
Silver
95393aea13
Merge pull request #10 from silveroxides/feature/preview-meta-wf-loader
...
Feature/preview meta wf loader
2026-04-25 19:05:51 +02:00
silveroxides
0a82e071b8
fix NodeOutput issue
2026-04-08 17:50:10 +02:00
silveroxides
dc43040562
Rename downloader nodes and add nodes for displaying previews, metadata of model and workflows extracted from images/videos
2026-04-08 16:46:35 +02:00
silveroxides
39380f533d
Remove subprocess, use av. More info in status output from Downloader nodes
2026-04-08 16:28:45 +02:00
silveroxides
2ac0d46935
Add progress bar
2026-04-08 15:43:05 +02:00
silveroxides
378c327406
Add subdirectory selector
2026-04-08 15:31:42 +02:00
silveroxides
4076c14cb5
Add requirements.txt entries
2026-04-08 15:16:16 +02:00
silveroxides
c4c967172b
Add Model preview/example image/video downloading, model hashing, preview/example workflow extraction from images and videos followed by compression of images to save storage, saving of hash database and much more
2026-04-08 15:04:24 +02:00
Silver
095ac89164
Bump version to 0.2.9
2026-03-07 19:10:13 +01:00
Silver
2d477767d6
Merge pull request #9 from silveroxides/fix/loading-fixes
...
Fix models getting stuck in memory when merging
2026-03-07 19:09:32 +01:00
silveroxides
4d49477f58
Fix models getting stuck in memory when merging
2026-03-07 16:32:43 +01:00
Silver
6c4d505d84
Bump version from 0.2.7 to 0.2.8
2026-02-24 17:41:25 +01:00
Silver
1e53a87427
Merge pull request #8 from silveroxides/feature/expand-lora-functionality
...
expand on functionality and reduce restrictions when extracting LoRA
2026-02-24 17:40:47 +01:00
silveroxides
b497022c3c
expand on functionality and reduce restrictions when extracting LoRA
2026-02-24 17:39:48 +01:00
Silver
5df8c6711a
Merge pull request #7 from silveroxides/fix/loading-imporovements
...
improve memory efficiency
2026-02-12 08:07:39 +01:00
Silver
f4cecdc49b
Merge branch 'main' into fix/loading-imporovements
2026-02-12 08:07:31 +01:00
Silver
8b34d57003
Merge pull request #6 from silveroxides/patch/lora-changes
...
changes to LoRAs
2026-02-12 08:05:19 +01:00
silveroxides
9f8b337584
changes to LoRAs
2026-02-07 16:02:40 +01:00
silveroxides
0d011d1232
improve memory efficiency
2026-02-07 16:01:00 +01:00
silveroxides
6a119e63f5
Bump version from 0.2.6 to 0.2.7
2026-01-23 19:21:02 +01:00
silveroxides
4097326a82
Add pad/crop for mismatched tensors and interpolation mode for weight redistribution across rank
2026-01-23 19:04:51 +01:00
silveroxides
31eee604de
Bump version from 0.2.5 to 0.2.6
2026-01-23 18:54:09 +01:00
silveroxides
2bfecf9c2d
Fix resize_tensors to handle cases where model B is larger than model A
2026-01-23 18:53:40 +01:00
silveroxides
1ba0932d6b
Bump version from 0.2.4 to 0.2.5
2026-01-23 18:42:23 +01:00
silveroxides
b1ec55ff42
improve and correct merger operations based on papers
2026-01-23 18:41:35 +01:00
silveroxides
8deb4fd739
perf: Add low_memory mode to reduce RAM usage in LoRA merge
...
- MemoryEfficientSafeOpen now supports low_memory=True which disables mmap
- Uses direct file reads with readinto() to avoid OS page caching
- _deserialize_tensor avoids bytearray copy when input is already bytearray
- merge_loras_to_model now uses low_memory=True for base model
This should reduce peak RAM from 2x model size to 1x + overhead
2026-01-15 03:13:51 +01:00
silveroxides
e9f7cda706
fix: Free cpu_base after storing to avoid duplicate RAM usage
2026-01-15 02:51:17 +01:00
silveroxides
cffb92aa06
fix: Add HuggingFace LoRA format support (.lora.down.weight/.lora.up.weight)
...
- Add detection for HuggingFace format in detect_lora_format()
- Strip trailing .lora suffix in extract_core_layer_lora() for proper key matching
- Applied fix to resize_lora_via_base, merge_multi_loras_via_base, and merge_loras_to_model
2026-01-15 02:43:42 +01:00
silveroxides
ce8c6aab97
feat: Add LoRAMergeToModel node for merging LoRAs directly into model
...
- New merge_loras_to_model() function that merges LoRAs into base model
weights and saves the result without extraction
- New LoRAMergeToModel node with simplified inputs (no extraction params)
- Outputs merged model to the base model's directory
2026-01-15 02:30:51 +01:00
silveroxides