Claude 5a1da0ce1b Revert "LTX image-to-video: the first reference picture is the start when none is picked" ...

This reverts commit e4111cf74a.

2026-10-27 08:52:11 +00:00

..

conditioning

Shot camera and SLA need H3-only traits: hidden on LTX (node fields can now require a trait)

2026-10-27 08:29:22 +00:00

latent

Rename FunPack to FunUI (5.0.3 Classy Chopper): /fun endpoint, wink logo, load-time migration of old names

2026-10-25 13:11:03 +00:00

loaders

Shot camera and SLA need H3-only traits: hidden on LTX (node fields can now require a trait)

2026-10-27 08:29:22 +00:00

media

Video input: prepare reference videos (size, crop, rate, skip, cut, every Nth, cap) per project or per scene

2026-10-27 01:04:58 +00:00

models

Revert "LTX image-to-video: the first reference picture is the start when none is picked"

2026-10-27 08:52:11 +00:00

output

Camera enhancements wheel switch, stable Save video as name, media bin remembers view and sort

2026-10-25 17:51:44 +00:00

sampling

Attention explorer: prompt focus at 0.3 of the change size, new levers change less often at first

2026-10-25 22:17:05 +00:00

system

A rating re-runs the same seed for every learner, not only the Attention explorer

2026-10-25 20:44:59 +00:00

training

Rename FunPack to FunUI (5.0.3 Classy Chopper): /fun endpoint, wink logo, load-time migration of old names

2026-10-25 13:11:03 +00:00

__init__.py

core+shell: the bridge, and the first module through it

2026-08-28 19:58:06 +03:00

_core.py

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

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

.gitkeep

core: serve the app, with the module allowlist as the wall

2026-08-28 14:18:55 +03:00