961a95b9bd
* feat(ltx-director): Ghost Mask reference image (REF / character sheet) Add a no-LoRA reference-image identity anchor to LTXDirector__koolook, the way a WAN VACE reference works: attach reference image(s) and the model keeps the character's face / mouth consistent even when keyframes show a closed (or different) mouth than the audio-driven motion needs. Targets the mouth / identity drift seen in the talking-goat lip-sync workflow. Mechanism (Ghost Mask): the reference image(s) are appended as masked guide frames *after* the clean video region, so the transformer attends to them for identity but they never appear in the output; the trailing reference frames are then sliced off the result. - LTXDirector__koolook: new optional `reference_images` (IMAGE) + `reference_strength` inputs, and appended `clean_latent_frames` / `clean_pixel_frames` outputs. All additive/optional -> saved workflows unaffected. Refs are appended AFTER snap/ease so they are never grid-snapped or ease-expanded; the auto latent is grown to hold them. ltx_director.py is under ruff's forks/ exclude. - reference_ghost.py (new, Koolook-original, pure stdlib): trailing-reference geometry (insert frames, grown latent length, slice bounds). Unit-tested. - k_clean_latent_slice.py (new root node `CleanLatentSlice`): torch.narrow slice to drop the trailing reference frames (start=0, length=clean_latent_frames). torch imported lazily; clamp math unit-tested, slice path tested when real torch is present (skips under the CI stub). - Registered the node; added to sync_to_dev RUNTIME_PATHS. - Attribution: the Ghost Mask APPROACH is adapted (idea only, reimplemented) from CGlide/WhatDreamsCost-CSGlide (main_cs @ 21dd076, GPL-3.0, license verified 2026-06-24, GPL->GPL OK). THIRD_PARTY.md, forks_manifest.yaml, UPSTREAM_PIN.yaml, CHANGELOG updated. Phase 1: Ghost Mask only. The LoRA-backed Licon MSR prefix mode and the editor's character-slot UI are intentionally NOT ported. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> * feat(sidebar): action-led star footer ("Give a ★ on GitHub") Reword the GitHub discovery footer from the passive "Help creators find us on GitHub" to an action-led "Help creators find us! Give a ★ on GitHub", with the star as the explicit ask. Render the sentence as one inline text flow (not separate flex children) so the footer's `gap` doesn't space out the words; the ★ glyph keeps its gold styling inline and now carries role="img"/aria-label="star" so it is announced. Verified rendering in an isolated harness. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> * fix(ltx-director): Ghost Mask broke motion in the append-and-crop pipeline The upstream guide pipeline (LTXDirectorGuide + LTXDirectorCropGuides) appends every guide_data image as an extra latent frame and crops them back off via `exact_crop_frames = latent.shape[2] - initial_latent_length`. The Ghost Mask code (modeled on CGlide's CleanLatentSlice flow) ALSO pre-grew the video latent by n_refs, so initial_latent_length became clean+n_refs: CropGuides then left n_refs frames uncropped AND the audio latent stayed at the clean length, desyncing the A/V joint transformer and breaking motion. Fix: don't pre-grow the latent. References are added to guide_data exactly like timeline keyframes and ride the same append-and-crop path — the guide node appends them and CropGuides removes them, audio untouched. Auto latent is sized to the clean length again. CleanLatentSlice/clean_latent_frames remain available for bare pipelines that don't use LTXDirectorCropGuides. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> * feat(ltx): LTX Guide Reference Strength — per-stage reference boost Adds a small Koolook node that rewrites the strength of ONLY the Ghost Mask reference frames in guide_data (the trailing entries the Director now tags with `reference_count`), leaving the keyframe pins untouched. Insert it before a stage-2 refinement guide and set ~0.9 to lock identity during the low-denoise pass without disturbing the motion set in stage 1 — the deterministic form of "more reference in stage 2". Chosen over vendoring the 600-line upstream LTXDirectorGuide (which would force a node-ID rename + graph rewire): this is one small node inserted on the stage-2 guide_data wire. The sigma-ramp alternative (ramp reference up at low sigma) is deferred — the reference hook is noise_mask + a core-model attention term, so it needs a live-model spike, not a clean static patch. - Director tags guide_data["reference_count"] = n_refs. - k_ltx_guide_reference_strength.py: pure strength rewrite (absolute / multiply, clamped), unit-tested; registered; added to sync paths. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> * feat(ltx): LTX Reference Bind Schedule — sigma-ramp the reference attention Confirmed against core (comfy/ldm/lightricks/model.py): the reference's guide attention strength is turned into a log-space additive self-attention bias in `_build_guide_self_attention_mask`, which is rebuilt EVERY denoise step and explicitly supports strength > 1.0 to amplify. That's a clean per-step hook — so the "inverse sigma curve" idea is buildable, not just a stage knob. New node mirrors LTXAVBindSchedule: a model_function_wrapper captures the per-step sigma and stashes a gain in transformer_options; an object-patch on diffusion_model._build_guide_self_attention_mask multiplies the strength of ONLY the trailing `num_references` guide entries (references are appended after keyframes) by a smoothstep ramp — neutral early (motion forms), rising to peak_strength late (identity locks during refinement). Keyframe pins and noise-mask freezing untouched; orthogonal to reference_strength. One pass, no re-noise, no LoRA. - ref_gain ramp + _boosted_entries unit-tested (11 tests); model wiring validated by live render. - Registered; added to sync paths. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> * fix(ltx): mark Reference Bind Schedule inert without an IC-LoRA Live diagnostic on the AV model showed the builder is reached and the sigma gain flows in, but resolved_guide_entries=None despite 3276 guide tokens. Root cause: LTXDirectorGuide only records guide_attention_entries when an IC-LoRA is active (`if is_lora_active:` gates _append_guide_attention_entry). With no LoRA there is no per-guide attention bias to scale, so the attention-ramp lever does not exist in the Ghost Mask path — it can only attenuate/amplify entries that an IC-LoRA created. Rather than silently no-op, the node now logs a clear INERT warning when the entry list is empty, and the docstring/DESCRIPTION/CHANGELOG state the IC-LoRA requirement. The node remains correct for the IC-LoRA path (its partner). No-LoRA reference strengthening stays on the noise-mask lever (reference_strength / LTX Guide Reference Strength). Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> * feat(ltx): Reference Bind Schedule works without an IC-LoRA (fabricates entries) The attention-bias identity channel (_build_guide_self_attention_mask) is base-model functionality, but LTXDirectorGuide only populates the per-guide entries when an IC-LoRA is active, so the node was inert in the no-LoRA Ghost Mask path. Now, when entries are missing, the node FABRICATES them for the trailing reference tokens: it splits num_guide_tokens across (num_keyframes + num_references) guide frames and assigns the sigma-ramped strength to the reference share, then hands off to the core builder. This gives the reference the same amplified-attention channel an IC-LoRA would use — inside the Director, no guide-node vendor, no graph rewire (the node is already in the user's setup). When an IC-LoRA IS active it scales the real entries as before. - New `fabricate_reference_entries(num_guide_tokens, num_references, num_keyframes, strength)` (pure, unit-tested) + `num_keyframes` input. - Wrapper now does scale-or-fabricate; clearer one-shot diagnostics. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> * fix(ltx): keep num_keyframes last so pre-existing RefBind widgets stay aligned num_keyframes was inserted mid widget-order, which shifted ramp_start/ramp_end for workflows saved before it existed. Move it to the end of the optional inputs so saved [num_references, peak_strength, ramp_start, ramp_end] values keep mapping correctly; num_keyframes just defaults to 0 on reload. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> * fix(test): drop unused pytest import (ruff F401) The guide-reference-strength test uses plain asserts; the stray `import pytest` tripped ruff F401 and reddened the Lint & Smoke CI job. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> * fix(ltx-director): default keyframe guidance 0.8 (smooth), not 1.0 The timeline editor auto-built the guide_strength string from each clip's per-segment guideStrength, filling 1.0 for any clip left unset (and the Python fallback matched). 1.0 is a hard pin, so a clip you forgot to lower snapped instead of transitioning smoothly. Unset clips now default to 0.8 in the editor (display + serialization) and the node; explicit per-clip values still override. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> * feat(ltx): Keyframe Soften Schedule — smooth motion early, sharp poses late New model-patcher node LTXKeyframeSoftenSchedule: sigma-schedules the LTX keyframe denoise-mask pins so the model forms smooth motion between poses early (pins loosened at high sigma) and resolves sharp poses late (pins restored by a crossover). Uses the sampler's per-step denoise_mask_function hook — no IC-LoRA required — and adds no guide frames (so it can't fabricate extra poses). Audio-safe: only the video half of the NestedTensor A/V mask is softened; the audio mask is untouched, so lip-sync is unaffected. Two normalized 0-1 widgets map onto the sensitive useful range: max_soften (ease, ->0-0.20) and crossover (invention window, ->0-0.05). Pure soften_gain ramp unit-tested (11 tests); model wiring render-validated. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> * fix(review): chain denoise hook, optional_latent clean-length, audio test, CGlide manifest Addresses PR #264 review findings: - MEDIUM (Soften node): chain a pre-existing denoise_mask_function instead of clobbering it (mirrors the sibling LTX patchers' wrapper-chaining), so the node composes with anything else that sets that hook. - HIGH #2 (Director): clean_pixel_frames/clean_latent_frames now derive from the ACTUAL optional_latent shape when one is connected, so Ghost-Mask reference geometry and the reported counts follow the real latent instead of the timeline duration (with a safe fallback + warning). - LOW (Soften node): reconcile docstring (crossover is sigma-progress, maps to internal 0-0.05), one-time warn on the sigma-read fallback, and extract a testable soften_denoise_mask() helper. - LOW: lock the audio-safety guarantee with NestedTensor-stub tests — video mask softened, audio mask untouched, part-ordering asserted. - #6: add a formal forks_manifest.yaml entry for the CSGlide Ghost Mask idea-only adaptation (was prose-only in another entry's notes; THIRD_PARTY.md already carries the full attribution). Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> --------- Co-authored-by: AI Machine <ai.machine@x.baconcph.com> Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
ComfyUI-Koolook
Kforge Labs for ComfyUI: a project-kit sidebar plus Koolook nodes for VFX, image, and video workflows.
Start here: KForge Labs ComfyUI-Koolook overview
That overview explains the sidebar, snapshots, saved workflows, modules, recovery tools, and included nodes for new users.
The main experience is the Kforge Labs sidebar. It helps you keep a project setup together: favorite nodes, saved workflows, reusable modules, tags, snapshots, and recovery tools.
Kforge Labs Sidebar
Use the sidebar as a reusable project kit.
| Feature | What it does |
|---|---|
| Snapshots | Save and load the whole Kforge Labs state: favorite nodes, workflows, modules, tags, archive, and recovery data. |
| Search | Find nodes, workflows, directories, and tags from one field. Tags keep exact capitalization, so Depth and depth can be separate folders. |
| Nodes | Keep favorite nodes close, grouped by theme or repository name. |
| Workflows | Save the whole script, save a selection of nodes, load workflows, or insert saved modules into the current canvas. |
| Recovery | Use autosaves, starter presets, snapshot library settings, and missing-pack install helpers. |
New here? Start with the KForge overview. Using it inside ComfyUI? Open the operational guide:
- Browse on the web: malkuthro.github.io/ComfyUI-Koolook/web/guide/
- Inside ComfyUI: Kforge Labs sidebar → Tools row → Help (
Hicon). The in-app button opens the bundled offline copy atweb/guide/index.html.
Included Nodes
| Node ID | Display name | Category |
|---|---|---|
EasyWan22Prompt |
Wan 2.2 Easy Prompt (Koolook) | Koolook/Wan_Video |
EasyResize_Koolook |
Easy Resize (Koolook) | Koolook/Image |
EasyAIPipeline |
Easy AI Pipeline (Koolook) | Koolook/Pipeline |
easy_ImageBatch |
Easy Image Batch (Koolook) | Koolook/Image |
KoolookLoadCameraPosesAbsolute |
Koolook Load Camera Poses (Absolute Path) | Koolook/Camera |
Easy_hdr_VAE_encode |
Easy HDR VAE Encode (Koolook) | Koolook/VAE |
Easy_hdr_VAE_decode |
Easy HDR VAE Decode (Koolook) | Koolook/VAE |
Easy_Pattern |
Easy Pattern (Koolook) | Koolook/Testing |
Easy_LoadVideo |
Easy Load Video (Koolook) | Koolook/Video |
Easy_VideoCombine |
Easy Video Combine (Koolook) | Koolook/Video |
Easy_Utility |
Easy Utility (Koolook) | Koolook/Utility |
Koolook_LoopStatus |
Koolook Loop Status | Koolook/Loop |
Koolook_PublishInput |
Koolook Publish Input | Koolook/Publish |
Koolook_PublishOutput |
Koolook Publish Output | Koolook/Publish |
Koolook_PublishRouter |
Koolook Publish Router | Koolook/Publish |
Koolook_PublishResult |
Koolook Publish Result | Koolook/Publish |
LTXDirector__koolook |
LTX Director (Koolook) | Koolook/PromptRelay |
The root Koolook nodes and the slim Radiance Koolook VAE wrappers have no
extra Python dependencies beyond torch, which ComfyUI already requires.
The video wrappers require Video Helper Suite, and the LTX Director fork is
for workflows that already use the LTX / Prompt Relay node ecosystem.
Install
ComfyUI-Manager
- Open ComfyUI Manager.
- Choose Install Custom Nodes.
- Install by Git URL:
https://github.com/malkuthro/ComfyUI-Koolook.git - Restart ComfyUI.
- Open the Kforge Labs sidebar tab.
Manual
Clone this repository into ComfyUI/custom_nodes/:
git clone https://github.com/malkuthro/ComfyUI-Koolook.git
Restart ComfyUI after installation.
One install at a time. If you already installed Kforge Labs via ComfyUI Manager, it lives at
custom_nodes/koolook/(the Manager / Registry-derived folder name). A secondcustom_nodes/ComfyUI-Koolook/created bygit cloneis a parallel install — ComfyUI loads BOTH on every boot, both register the same routes and sidebar tab, and the workflow store silently corrupts on every restart. From v0.3.8 the plugin detects this and prints a critical log naming both paths, disabling the non-winning copy — but the cleanest fix is to remove one folder. Pick the install method you want and stick with it.
Learn More
- Public overview: kforgelabs.com/comfyui-projects/comfyui-koolook/
- In-app visual guide: malkuthro.github.io/ComfyUI-Koolook/web/guide/
(offline copy:
web/guide/index.html) - Support / bug reports:
SUPPORT.md - User guide:
docs/user_guide/ - Change history:
CHANGELOG.md - Maintainer docs:
docs/maintainers/ - Fork attribution and provenance:
forks/THIRD_PARTY.md - Versioning reference:
docs/reference/versioning.md
Troubleshooting
| What you see | What it usually means | What to do |
|---|---|---|
| The Kforge Labs tab does not appear | ComfyUI needs a restart, or the extension did not load | Restart ComfyUI and check the terminal for [Koolook] messages. |
| The Help guide does not open | The browser blocked the popup | Allow popups for the ComfyUI page, or open web/guide/index.html directly. |
| Missing custom nodes after loading a workflow | One or more node packs used by that workflow are not installed | In Kforge Labs, use Tools → Install missing packs, or use ComfyUI Manager's Install Missing Custom Nodes flow. |
| Snapshot save/load fails | The snapshot library path may be missing, read-only, or unavailable | Use Snapshot → Save to... or Load from... and choose a writable folder. |
| A loaded snapshot looks older than expected | Named saves and auto-saves are intentionally separate | In Snapshot → Load, select the snapshot and check Recovery auto-saves for a newer periodic/pre-load recovery. |
Support
For reproducible bugs, open a
GitHub issue.
For the fastest answer, include your ComfyUI version, Koolook version,
operating system, install method, terminal log, browser console errors, and
steps to reproduce. See SUPPORT.md for the exact checklist.
If Koolook helps your ComfyUI work, you can support development on Ko-fi.
Stability
For production work, install a pinned release tag or commit instead of following a moving branch head. Node IDs are treated carefully so saved ComfyUI workflows continue to load across compatible updates.
License
GPL-3.0. See LICENSE.
This package incorporates and adapts GPL-3.0 code from
fxtdstudios/radiance under
forks/radiance_koolook/. Attribution and per-fork modification notes are
tracked in forks/THIRD_PARTY.md and
forks/forks_manifest.yaml.