Dataset Processing Nodes and Improved LoRA Trainer Nodes with multi resolution supports. (#10708)

Browse Source

* Create nodes_dataset.py

* Add encoded dataset caching mechanism

* make training node to work with our dataset system

* allow trainer node to get different resolution dataset

* move all dataset related implementation to nodes_dataset

* Rewrite dataset system with new io schema

* Rewrite training system with new io schema

* add ui pbar

* Add outputs' id/name

* Fix bad id/naming

* use single process instead of input list when no need

* fix wrong output_list flag

* use torch.load/save and fix bad behaviors

...

This commit is contained in:

Kohaku-Blueleaf

2025-11-27 08:18:08 +08:00

committed by GitHub

parent a2d60aad0f

commit cc6a8dcd1a

3 changed files with 1980 additions and 520 deletions

Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL

Download Patch File Download Diff File Expand all files Collapse all files

967

comfy_extras/nodes_train.py

File diff suppressed because it is too large Load Diff