Claude 919097c732 LoRA training: our own loop for H3, and a Log that survives a crash ...

The H3 run trains with a loop of our own (LoRA on the attention and feed-forward projections of the
50 blocks, per-block checkpoint, uniform noise levels, musubi-tuner's approach) while ComfyUI carries
the batches. Every Log record is flushed to disk as it is said and reloaded on start; the run
writes each stage and step to it. ComfyUI's own offloading toggle is ignored by the new loop.
UNTESTED on the real weights.

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

2026-10-17 19:57:06 +00:00

..

ltx

fix: optional nodes are declared per node class by the model modules (saved pipelines and swapped nodes covered); skip chain cannot crash; skipped controls hidden in the project tab; skipped card says so (attacker round 26)

2026-10-16 01:02:59 +03:00

minimax_h3

LoRA training: our own loop for H3, and a Log that survives a crash

2026-10-17 19:57:06 +00:00

sd15

feat: FunPack Save Video takes frames, sound and fps directly; Create Video dropped from the presets

2026-10-07 16:08:28 +03:00

tests

fix: skipped slots offer no Remove/Swap, stand-in load clears skipped, null pass value refused; route-level and precedence tests

2026-10-16 01:28:22 +03:00

__init__.py

latent: an empty latent the model decides the shape of

2026-08-29 12:21:25 +03:00