mirror of
https://github.com/comfyanonymous/ComfyUI.git
synced 2025-12-21 03:50:50 +08:00
Dataset Processing Nodes and Improved LoRA Trainer Nodes with multi resolution supports. (#10708)
* 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:
parent
a2d60aad0f
commit
cc6a8dcd1a
1532
comfy_extras/nodes_dataset.py
Normal file
1532
comfy_extras/nodes_dataset.py
Normal file
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
1
nodes.py
1
nodes.py
@ -2278,6 +2278,7 @@ async def init_builtin_extra_nodes():
|
|||||||
"nodes_images.py",
|
"nodes_images.py",
|
||||||
"nodes_video_model.py",
|
"nodes_video_model.py",
|
||||||
"nodes_train.py",
|
"nodes_train.py",
|
||||||
|
"nodes_dataset.py",
|
||||||
"nodes_sag.py",
|
"nodes_sag.py",
|
||||||
"nodes_perpneg.py",
|
"nodes_perpneg.py",
|
||||||
"nodes_stable3d.py",
|
"nodes_stable3d.py",
|
||||||
|
|||||||
Loading…
Reference in New Issue
Block a user