digital-garbageandClaude Sonnet 4.6 776e0a6b12 Remove latent VF and motion floor — inaccessible in LTX token format ...

LTX packs all spatial/temporal dims into a single token [1, 1, C*T*H*W]
during sampling. Per-step latent steering requires hooking into the model
internals, not the k-diffusion callback. Removed: compress_latent(),
_load_latent_value_function(), latent VF training, motion floor callback,
latent_value_guidance toggle in Studio.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

2026-05-30 13:24:29 +03:00

..

funpack_conditioning_adjust.js

Fix FunPackConditioningAdjust UI: use native button widget instead of custom widget

2026-05-16 17:13:42 +03:00

funpack_lora_weights.js

Add refiner vision context and velocity research hooks

2026-05-13 12:36:07 +03:00

funpack_rating_picker.js

Fix rating picker: stale onOutside listener closed re-opened picker

2026-05-30 12:41:07 +03:00

funpack_refinement_key_loader.js

Release Refiner V2 appearance safety

2026-05-08 19:28:00 +03:00

funpack_scene_builder.js

Add global scene shortcuts

2026-05-22 16:38:33 +03:00

funpack_studio.js

Remove latent VF and motion floor — inaccessible in LTX token format

2026-05-30 13:24:29 +03:00