Claude 28d191133b Training: free the card at the start of every run, cached data or not ...

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01MpnF7GwNGMbngU11wjym7P

2026-10-18 23:48:41 +00:00

..

tests

Training: the node always runs (a second resume was answered from ComfyUI's cache in 0s); the window adopts the server's pause instead of an older one

2026-10-18 23:39:55 +00:00

__init__.py

Rated results: caption only from the file's own prompt, never the project's; keep every file listed and mark doubtful ratings

2026-10-18 22:24:27 +00:00

captions.py

Training captions are plain text boxes; the set has its own prefix and postfix

2026-10-17 18:38:03 +00:00

frames.py

LoRA training add-on: sets, tagger, trainer node on ComfyUI's Train LoRA, H3 support

2026-10-17 15:05:57 +00:00

jobs.py

LoRA training: time per step, a graph of it, and the time spent in all (restarts included)

2026-10-18 00:15:41 +00:00

loop.py

LoRA training: time per step, a graph of it, and the time spent in all (restarts included)

2026-10-18 00:15:41 +00:00

media_io.py

feat: show a clip's frame count and rate in the training pickers and tags step

2026-10-17 18:58:03 +00:00

nodes.py

Training: the node always runs (a second resume was answered from ComfyUI's cache in 0s); the window adopts the server's pause instead of an older one

2026-10-18 23:39:55 +00:00

plan.py

Training takes the model file from the pipeline and loads it once itself

2026-10-17 17:48:06 +00:00

rated.py

LoRA training: a rated result made in this session takes the prompt embedded in its file; an older rating on a reused name is left out

2026-10-18 22:17:02 +00:00

store.py

LoRA training: rated results are checked against the file itself, files added without words take the prompt embedded in them, no length limit on prefix and postfix

2026-10-18 22:14:29 +00:00

swap.py

feat: block swap option for LoRA training and a per-block memory log in the backward pass

2026-10-17 19:30:50 +00:00

taggers.py

LoRA training add-on: sets, tagger, trainer node on ComfyUI's Train LoRA, H3 support

2026-10-17 15:05:57 +00:00

train.py

Training: free the card at the start of every run, cached data or not

2026-10-18 23:48:41 +00:00