From f0a023e952ea16e1ab31356c1cff6a626cd620f8 Mon Sep 17 00:00:00 2001 From: AI Machine Date: Thu, 25 Jun 2026 22:21:50 +0200 Subject: [PATCH] docs: update CHANGELOG for Soften Schedule protect_until + info output Co-Authored-By: Claude Opus 4.8 --- CHANGELOG.md | 22 +++++++++++++--------- 1 file changed, 13 insertions(+), 9 deletions(-) diff --git a/CHANGELOG.md b/CHANGELOG.md index 5af5a0e..80d26e0 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -10,15 +10,19 @@ The format is inspired by Keep a Changelog and SemVer. - **LTX Keyframe Soften Schedule node (`LTXKeyframeSoftenSchedule`).** Smooths motion between keyframes without adding any guide frames: a model patcher that sigma-schedules the keyframe denoise-mask pins — loosening them early (high - sigma) so the model forms smooth motion between poses, then restoring them by a - crossover point so the poses sharpen for the back half of denoise. Uses the - sampler's per-step `denoise_mask_function` hook; works with **no IC-LoRA**. - Audio-safe: the A/V mask is a `NestedTensor((video, audio))`, so only the video - keyframe pins are softened and the audio mask passes through untouched (lip-sync - unaffected). Two normalized 0-1 widgets map onto the (very sensitive) useful - range: `max_soften` (ease amount, 0-1 → internal 0-0.20) and `crossover` - (invention window, 0-1 → internal 0-0.05). Pure `soften_gain` ramp unit-tested; - model wiring render-validated. + sigma) so the model forms smooth motion between poses, then restoring them so + the poses sharpen as denoise finishes. Uses the sampler's per-step + `denoise_mask_function` hook; works with **no IC-LoRA**. Audio-safe: the A/V + mask is a `NestedTensor((video, audio))`, so only the video keyframe pins are + softened and the audio mask passes through untouched (lip-sync unaffected). + Controls: `max_soften` (ease amplitude, 0-1 → internal 0-0.20; default 0.5 ≈ + 10% unpinned at peak) and **`protect_until`** — *how long* to soften as a + **fraction of the steps**, resolved against the sampler's actual sigma schedule + at run time, so "0.4 = first 40% of the steps" means the same thing on any + curve / step count (no per-schedule re-tuning). An optional `sigmas` input + an + `info` STRING output report the resolved window (softened steps + sigma range) + in-graph; the same coverage line is logged each run. Pure `soften_gain` ramp + + `resolve_soften_window` unit-tested; model wiring render-validated. - **LTX Director fork bumped to upstream v2.0.2** with a new `forks/whatdreamscost_koolook/versions/v2_0_2/` namespace (pinned to upstream commit `fe09f73`). This version is a **faithful replica of upstream 2.0.2** —