Input sources (nodes modal, expanded slot):
- New "Input sources" section per slot — choose where each connection input
comes from: (auto-wire), Timeline (scene image, IMAGE only), core primitives
(Project frames/fps), or another slot's named output.
- builder.py step 3b: applies input_sources before auto-wire; "timeline" creates
media_load node and wires it; "out:<slotId>:<outName>" and "core:<id>:<idx>"
resolve to specific graph edges.
- nodes.py: core_producers() lists the fixed core primitives as source options.
- server.py: pipeline-ports response includes core_producers array.
Role label editing:
- slot.role_label — user-editable name shown in the slot header role position.
- The rename button (✎) now edits role_label (applies to all slots, not just custom).
- Blank resets to the automatic role name from the roles registry.
Better picker labels:
- slotFullLabel(slot) = "RoleLabel · NodeName" — used in destinations() and
sources() so every option clearly identifies which slot it belongs to.
- roleLabel handles null/undefined role keys gracefully (shows "?").
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- builder.py: wires[outName] now accepts a list of targets (string = legacy single,
list = multi). Each target in the list gets its own graph edge from the same output.
- models.js: destSelect replaced with destMulti — shows current targets as a list of
selects each with a remove button, plus an "+ Add" button to wire the same output
to additional inputs. Old string-format wires normalized to array on first render.
Health check updated to validate all targets in the array.
- styles.css: wire-multi / wire-multi-row / wire-rm / wire-add classes.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- sampler_panel.js: full port of funpack_studio.js renderSampler() —
High/Low pass sections with Hybrid Euler 2S / Distilled Flow / Normalizing /
KSampler modes, velocity bias, rescue, motion pulses, variability macro.
Writes into project.studio_inputs.studio_settings (JSON) so builder sends it
as the studio_settings widget value to FunPackStudio.
- inspector.js: renderStudioSettings now renders the full panel; bool knobs
use setSamplerInputNow for immediate re-render on toggle.
- store.js: setSamplerInputNow / setStudioInputNow for instant notify on
structural changes (selects, checkboxes).
- styles.css: sp-macro / sp-sub styles for the sampler panel sections.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- Project now stores negative_prompt, sampler_inputs, studio_inputs
- Builder applies sampler_inputs/studio_inputs as widget overrides on the
ChainSampler and Studio nodes (only when funpack slot is selected)
- Inspector renderProject shows: negative prompt textarea + full sampler knobs
(cfg, frame_overlap, carry_i2v_guides, mid_scene_guide + strength,
embed_guidance + strength, decode_noise_scale, decode_timestep)
- Dependent knobs only appear when their parent bool is on
- Store: setSamplerInput / setStudioInput write into sampler_inputs/studio_inputs
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
54 typographic left/right double-quote chars snuck into JS string literals,
causing an immediate SyntaxError that broke the whole app.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- Bug: anchor prompt editing (selectedSceneId=null) no longer resets to scene 1 after
autosave — commit() now only resets selection when a non-null id disappears.
- Bug: generate errors now return {detail: '...'} JSON (400/502) so the frontend shows
the actual reason (missing node, blocking port, etc.) instead of 'Bad Request'.
- Transition autodetect: Split preview now shows the detected visual_effect badge on each
seam; a '↺ Sync scenes from preview' button distributes the parsed anchor/scenes/
transitions back into the project (with confirm dialog).
- Project save/load: File menu gains 'Save Project File…' (downloads .funpack_project.json)
and 'Load Project File…' (file picker → POST /api/projects/import → new project, safe
id, auto-opens). Useful for backup/restore when the ComfyUI instance is lost.
- Conditioning/Sampler roles: Project model gains conditioning_slot + sampler_slot
('funpack' by default). Generate menu shows current selection and opens a numeric
prompt picker to switch to any configured slot node. Stored in project JSON; full
builder wiring is a future phase.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- Shortcuts + Transitions bins: Add ↓ Export (download JSON) and ↑ Import (file picker
→ POST to new /api/library/{shortcuts,transitions}/{export,import} routes). bridge.py
gains import_shortcuts / import_transitions / export_* calling templates.py directly.
- nodes.py widget_inputs: handle V1/io.ComfyNode combo encoding (type "COMBO" with
options in dict) so LTX2LoraLoaderAdvanced and similar nodes expose all their widget
inputs. Also skip forceInput=True fields (socket-only, never user widgets).
- menubar.js: show window.location.host instead of internal comfy_url in the FunPack
menu — stops showing the loopback 8188 port vs the actual browser-facing port.
- store.js resizeScene: switch to scheduleSaveSilent so dragging a clip edge doesn't
trigger a notify/re-render mid-drag that resets the timeline selection.
- 26 tests pass (+1 test for V1 combo + forceInput coverage).
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Media wiring (chosen destination): a scene's image Source now lets you pick the
media asset AND which node IMAGE input it feeds (/api/image-targets lists core
IMAGE ports + configured nodes' IMAGE inputs). At generate the editor copies the
asset into ComfyUI's input folder (ephemeral) and the builder injects a LoadImage
wired to that input. Clips show the media as a thumbnail.
Editor-driven links: a link can be 'Driven by' a project setting (FPS / Frames /
Width / Height) instead of a manual value; builder fills every member input from
params at generate, so node inputs stay consistent with the timeline. Exposed
editor-driven links show read-only in the inspector.
Project width/height added (Scene gains width/height/source.target too).
Bonus from the backlog: split-at-playhead now respects the playhead position.
+3 builder tests (editor link, media inject, optional ports don't block). 25 pass.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
The builder treated every open port as mandatory, so a valid text-to-video
montage (no image source) was rejected with 'Incomplete config' because
studio.source_image / studio.latent (both OPTIONAL on FunPackStudio) had no
producer. Now open ports carry a required flag and only required gaps block;
ambiguous REQUIRED inputs (e.g. two VAEs into one) also block with a 'wire it
explicitly' message. Generate returns the full blocking list as the reason.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Left panel is now tabbed bins (Media / Shortcuts / Transitions):
- Media: upload via click or drop, thumbnail grid, delete; drag an asset onto a
timeline clip (or click with a scene selected) to set its image source.
Backend media store (media.py: upload/list/serve/delete under MEDIA_DIR).
- Shortcuts: list/search FunPack shortcuts, add, delete, click 'insert' to append
a trigger to the selected scene's prompt.
- Transitions: list/search, add, delete, 'apply' to the selected scene's seam.
Library CRUD runs in-process via bridge (templates.py functions); new routes
under /api/library/* and /api/media/*.
Autosave fix: free-text/number fields use quiet patches (state update + debounced
save, no per-keystroke re-render) so typing isn't interrupted; debounce 550→900/
1100ms; inspector preserves focus+caret across the eventual rebuild.
+test_media.py; 22 tests pass.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
- Link inputs: enter link mode, click ＋ on 2+ node inputs across nodes,
Save link (named) → one shared control drives them all (e.g. width/height).
Linked inputs render disabled with a 🔗 tag; edits route through the link.
- Links section in the Models modal lists each link: rename, shared-value
control, member chips (unlink), expose-to-main-editor eye, unlink-all.
- Exposed links appear in the inspector's Exposed controls (Store.setModelLink
writes through to all members).
- Rename any configured node (slot.label) via a ✎ in its header.
- Builder applies links: each member input set to the link's shared value.
Scene/models config gains links[]; +builder test. 21 tests pass.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Rebuilt the timeline as a time-based editor:
- HH:MM:SS:FF-aware ruler with zoom-adaptive tick labels; click to move playhead
- clips laid out on a time axis (width = duration × zoom), absolutely positioned
- drag the right edge to trim → recomputes frame count from duration × fps
(snapped to LTX-valid 8k+1); live timecode/frame tooltip
- split clip, move, delete; per-scene length/FPS + duration in the inspector
- per-seam crossfade: drag to set transition_frames (new field; post-decode pixel
op, never re-encodes) + transition-type picker
- zoom −/＋/fit, playhead, total-duration readout
Scene gains transition_frames; Store gains resizeScene/splitScene/snapFrames.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
- each configured node input gets an eye toggle ('Show in main editor
window'); exposed inputs render as live controls in the inspector's
'Exposed controls' panel and edit/persist the node config (Store.models is
now shared between the Models modal and the main editor via a
funpack-models-changed event)
- node slot cards are collapsed by default and after adding (like Studio
shortcuts); click the header to expand; header shows exposed count + status
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
FunPack menu -> 'Restart ComfyUI' relaunches the server process in place
(POST /funpack/movie/api/restart -> os.execv, mirroring ComfyUI-Manager's
reboot incl. the comfy-cli session case; no Manager dependency). Restart is
deferred 0.7s so the 200 flushes first. UI shows a blocking spinner overlay,
polls /health, and auto-reloads when ComfyUI is back. Confirms first.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
candidates()/all_nodes() now process each node defensively (like ComfyUI's
own /object_info) so one node with an unexpected schema (V3-style dict
outputs, non-list input, etc.) is skipped instead of 500ing the whole list.
node_outputs() hardened to tolerate non-list output/output_name. Routes log a
traceback and return the real error message instead of a blank 500.
Root cause: until object_info was built in-process, the candidate filter had
never actually run against the full live registry. Regression test added.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
- models composer now shows the actual error text (and logs it) instead of a
generic 'ComfyUI offline' when the node list fails to load
- FunPack menu reads the current health fields (reference_loaded /
configured_slots) instead of the removed template_exists
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
The previous commit accidentally swept in untracked junk (__pycache__,
.DS_Store, .claude/, refinements/*.pt runtime artifacts, research PDF) via
git add -A. Untrack them and ignore going forward. No source changes.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Generate now builds the fixed FunPack path in code (builder.py) instead of
loading a runtime template:
- emits the fixed core (Studio -> LTXVConditioning -> Chain Sampler ->
Separate AV -> Audio decode -> Normalize -> VHS Combine, plus Concat AV,
SaveRefinement, KeyLoader, fps/frames primitives) with internal links and
widget values seeded from the reference workflow
- splices in the user's configured loader/image-proc/empty-latent slots,
resolves explicit 'Wire to' links, then auto-wires remaining typed inputs
from the unique producer of that type; ambiguous/unsatisfied are reported
- forces VHS save_output so results are retrievable
- generate route uses builder + blocks on unsatisfied config; drops the
template injector (workflow.py removed)
Fix 'ComfyUI offline' when adding loader nodes: object_info is now built
in-process from NODE_CLASS_MAPPINGS (no loopback HTTP, no port guessing;
tuples normalized via JSON), HTTP kept as fallback. Refresh clears
folder_paths.filename_list_cache like ComfyUI's R key.
Tests: +test_builder.py (4), removed obsolete workflow-injection tests; 19 pass.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Models modal now filters the 'Any node…' list with a live search box
(capped at 300 results) instead of a giant select, and validates the
slot config: per-slot error/warning badges + issue list (missing
required fields, no-option combos, unwired/dangling outputs) plus a
summary banner flagging missing essential roles (Unet/CLIP/Video VAE).
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Lets the Models UI express the full graph wiring (per user: 'just allow this
wiring, nothing more'):
- 'Any node…' option in the composer: searchable picker over every registered
ComfyUI node (all-nodes), not just the 8 typed roles — so nodes like LoadImage,
VAEEncode, ImageTransformKJ, LTXVImgToVideo* can be added and wired
- backend: all_nodes(), describe_node(cls); pipeline_ports(object_info) now also
exposes LTXV fixed-core external inputs (LTXVConcatAVLatent, LTXVAudioVAEDecode,
LTXVConditioning, Separate, VideoCombine, ...) so loader/image outputs can wire
into them, not just Studio/Chain Sampler
- frontend: unified node-spec-by-class cache + specFor(); routes all-nodes/node/{cls}
- tests: +2 = 17 passing
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
- _serve_static: Cache-Control no-store + explicit text/javascript (fixes stale
files / wrong-MIME blanking the app across fast iteration)
- index.html: inline window.onerror/unhandledrejection overlay so any script
failure shows on screen instead of a blank editor (self-diagnosing)
- save user's real montage workflow as backend/reference/montage.workflow.json
to encode the fixed graph builder (loaders + image-proc groups = the pluggable
slots; rest is the fixed path)
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Each configured node now declares where its outputs connect, so users rebuild
the node graph as a tidy list instead of canvas spaghetti:
- backend: candidates now expose outputs + connection_inputs; pipeline_ports()
derives Studio/Chain Sampler connection points live from their real INPUT_TYPES
(authoritative); /api/pipeline-ports route
- frontend: per-output 'Wire to' select in each slot card, offering type-matched
destinations (pipeline ports OR another configured node's input). Enables chains
like CLIP Vision -> CLIPVisionEncode -> Studio, or a Latent Combine feeding Studio
- tests: +2 (outputs/connection inputs, port derivation) = 15 passing
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
The fixed pipeline only varies in its loaders + a few pipeline nodes (they depend
on installed models). New 'Models' menu configures them via ComfyUI /object_info,
no hardcoded model family:
- backend nodes.py: role registry (Unet, LoRA, Video/Audio VAE, CLIP, CLIP Vision,
Input Image Processing, Empty Latent); filters object_info candidates by output
type (source roles exclude patchers); extracts user widgets (combos w/ installed
files, int/float/string/bool), skips graph-connection inputs; global config store
- bridge.object_info() (cached; refresh = ComfyUI 'R'); server routes for
node-roles / node-candidates / models get|put / refresh
- frontend models.js: Models menu (Settings + Refresh model list) + modal
'Add Model/Node' composer (type -> node -> exposed inputs) + configured slot list
- tests: +5 (filtering, widget extraction, store) = 13 passing
Note: drops the runtime-template concept per user — the editor will own the fixed
graph and inject these loaders. Graph builder is the next step (needs the montage
workflow JSON to encode exactly).
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Full frontend redesign into a real movie-editor layout:
- menu bar (File/Edit/View/Generate/FunPack) with dropdowns + status chips
- left Media Browser (projects + media bin drag-drop placeholder)
- right Preview/program monitor + context Inspector (clip props or project
settings + live split preview)
- bottom Timeline track: clips with transition seams, click-to-select drives
the inspector, reorder/exclude/delete
- draggable panel splitters; cinematic dark theme (warm near-black, amber clip
accent, teal selection, film grain), Bricolage Grotesque + IBM Plex Sans/Mono
Architecture: central pub/sub store (store.js) + per-zone view modules; all
backend wiring unchanged (same /funpack/movie/api). Editing moved from cards
into the inspector. Render/Export and media drag-drop are stubbed for later.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Per user: serve from ComfyUI's own aiohttp PromptServer at /funpack/movie/
instead of a separate FastAPI/uvicorn process. Removes fastapi/uvicorn/httpx
entirely (all on ComfyUI's bundled aiohttp); backend/requirements.txt deleted,
root requirements.txt needs nothing new.
- server.py: aiohttp route registration on PromptServer (projects/preview/
generate/status/result/library + static UI), guarded for standalone tests;
wired into root __init__.py like batch_training
- bridge.py: parse_timeline/transitions IN-PROCESS (direct FunPack imports);
/prompt /history /view over loopback HTTP
- config.comfy_base_url(): detect the REAL port from PromptServer.instance /
comfy.cli_args so non-default --port works; browser uses same-origin relative
URLs (api.js derives base from window.location) so the port is automatic
- delete app.py, routes/, comfy_client.py, backend/requirements.txt
- README updated; tests still 8/8
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Editable scene timeline + transition library feeding the existing Studio ->
Chain Sampler chain. Light FastAPI sidecar (no torch/comfy) that drives a
running ComfyUI over its API and reuses /funpack/* routes for parsing.
- backend: project store (JSON), timeline model + Studio-format prompt
assembly, ComfyUI client, graph-agnostic workflow injector, routes
(projects/timeline preview/generate/library), FastAPI app
- frontend: vanilla-JS editable timeline (scene cards, transitions, exclude,
generate-only, source type), live split preview, result player
- forward-compat data model: scene source (empty/image/generated_frame),
per-scene excluded flag, intro_transition for the anchor boundary
- tests: 8 passing (prompt assembly, project CRUD, workflow injection)
V1 drives the uniform chain in one pass; per-scene length/FPS, Empty/Image
latent building, media browser, frame->scene anchors, selective regen and
cuts/trims are scaffolded (UI/model) but deferred to later phases.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
DynamicConditioning is an unpacked-video technique; on LTXAV (packed AV latent, 3D
mask) it can only no-op (comfy's process_timestep patchifies expecting 5D). Rather
than keep dead knobs in the Chain Sampler UI, remove i2v_anchor_power /
i2v_anchor_first_frame_only, the install block, and _install_i2v_anchor entirely.
The packed-safe path for cross-cut appearance carry (strengthen the Chain Sampler's
own carry/guide masks pre-pack) remains available as a future native feature.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
The i2v anchor (DynamicConditioning port) crashed on LTXAV with 'not enough values
to unpack (expected 5, got 3)': comfy's process_timestep patchifies the video denoise
mask expecting unpacked 5D [B,C,F,H,W], but LTXAV packs the AV latent so its mask is
3D [B,C,N]. The else-branch (first_frame_only=False) modified + propagated the 3D mask
unguarded -> patchify blew up.
Hard-guard the whole denoise_mask_fn to genuine 5D masks; packed/non-5D -> clean no-op
(one-time log). The technique is fundamentally unpacked-video-only, so on LTXAV it does
nothing -- documented in the tooltip. Native packed-safe carry-strength is the follow-up.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Two optional Chain Sampler inputs (i2v_anchor_power, i2v_anchor_first_frame_only),
default power=1.0 = off. When >1.0, installs a denoise-mask model patch via the stock
comfy API (set_model_denoise_mask_function) that raises the denoise mask to power**step,
progressively holding the i2v conditioning frame harder as denoising proceeds -> anti-drift
from the input image. No modified model, no extra forward pass, ~zero overhead.
Patched before the batch/main split so both paths inherit it. Fully defensive: missing
mask / unexpected (e.g. packed) shape / any error falls through to the unmodified mask.
EXPERIMENTAL on packed AV latents - validate in ComfyUI. pos_embedding_exp_values.py was
also assessed and is a dead end (internal RoPE precision-matching constant, not a technique).
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
The Laplacian pyramid blend from the LTXV pack is a SPATIAL pixel-space tool and
doesn't transfer to our temporal latent crossfade (uniform full-frame alpha over a
2-4 latent-frame overlap -> multi-band adds nothing). The actual seam problem is that
a linear lerp of two latents superimposes them and lets magnitude collapse at ~0.5
(ghosting + washout). Fix in-domain instead:
- _slerp_block: spherical interp of the overlap block per (batch, frame), direction
via slerp + magnitude interpolated linearly, so the crossfade keeps its energy.
Uses torch.linalg.vector_norm (Tensor.norm treats a 3-tuple dim as a matrix norm).
- _blend_tensors: smoothstep alpha (less dwell at the 50/50 ghost point) + slerp for
video; audio/any further stream stays on the untouched linear path (audio-safety).
- Verified: exact endpoints, magnitude preserved across the seam vs linear washout.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Reverts the separate FunPackVAEDecoderNoise node (boundary-law violation: if the
Chain Sampler can own it, it should). Decode-time noise is now two optional inputs
on the Scene Chain Sampler (decode_noise_scale / decode_timestep), applied to a
shallow VAE copy via _vae_with_decode_noise before any decode so both the main and
batch-training IMAGES paths benefit. Never mutates the shared input VAE.
decode_noise_scale defaults to 0 (off) -> no behavior change unless enabled.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Phase 1 of the LTXVideo-pack technique pull. Standalone VAE->VAE passthrough that
stamps decode_timestep / decode_noise_scale / seed onto the LTX VAE so its internal
decoder restores fine detail/grain. ~zero cost, scale=0 disables. Place before any
VAE decode (Scene Chain Sampler, VAE Decode).
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Ports LTXVNormalizingSampler's between-step scalar normalization onto the FunPack
Normalizing sampler. Two new STRING inputs on FunPackNormalizingSampler:
video_normalization_factors / audio_normalization_factors (comma-separated per-step
scalars; short lists repeat last value; both default '1' = off/no-op).
Applied to the running latent at the end of each euler step via _apply_av_norm_factors,
using the existing _packed_video_mask to scale the video and audio streams independently.
This is the ONLY FunPack lever that touches audio, and it does so audio-safely by latent
magnitude only (never attention/hidden states) - the same mechanism the reference node
uses. Conservative + opt-in: ships off, audio untouched unless the user authors a schedule
(reference default was '1,1,0.25,1,1,0.25,1,1'). The adaptive normalize_strength remains
the smarter video-side lever; these are a manual per-step gain schedule.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Adds temporal_style='auto': Studio classifies each scene's prompt for motion
energy and bakes a continuous frame_rate multiplier into that scene's
conditioning metadata; the Scene Chain Sampler applies it per scene via a
layered model_function_wrapper (composes with embed guidance, restored in
install order). Concrete styles keep the global build_enhancements path
unchanged.
- ltx_enhancements: TEMPORAL_STYLES gains 'auto'; single-source TEMPORAL_STYLE_MULT
table; classify_temporal_intent() keyword director (energy->punchier mult<1,
stillness->hold mult>1, loop flag); factored make_temporal_wrapper() shared by
global + per-scene paths; build_enhancements skips the global wrapper for auto.
- conditioning: _v2_apply_auto_temporal() bakes funpack_temporal_mult/label/loop
into each entry inside the single finalize hook; both refine_v2 returns pass
temporal_style + the run prompt as per-scene fallback text. 'auto' added to V2
node dropdown.
- samplers: _scene_temporal_mult() reader + per-scene temporal wrapper around
_sample_chunk in the scene loop.
- web: 'auto' in the Studio dropdown + hint text.
Heuristic is the baseline director, structured so a reward-driven override can
replace the multiplier per intent-family later. loop's RoPE coordinate trick is
still unimplemented (inert flag only); auto detects loop intent but does not yet
honor it.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
clear_refinement_data() early-returned on an empty refinement_key, but a
keyless run stores its blessed/attn maps, creativity latent and velocity-bias
trajectories under the 'default' bucket. So a keyless Session Reset no-opped
and those disk-persisted stores survived restart too -- the first fresh run
felt cleaner than every later run. Normalize empty key to 'default' (matching
the write side) so reset actually wipes that bucket.
Also wire the keyless Absolute taste store (FUNPACK_ABSOLUTE_KEY) into reset:
it learns from every rated run regardless of steer_mode but had no clear path,
so it would survive reset + restart forever. Delete its state json + value fn
on reset_session.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
1) Widget order: moved the refinement_key_input forceInput SOCKET to the
end of optional (after decode_tile_size + embed_guidance_source). A
forceInput placed between widgets desynced ComfyUI's widgets_values
mapping on reload -> the combo's "relative" landed on the decode_tile_size
INT (NaN field).
2) RecursionError: _run_batch_training's no-key fallback called self.sample()
with the variant markers still in positive -> sample() re-detected the
batch -> re-entered _run_batch_training -> infinite loop (hit when
Interactive Guessing/batch is armed without refinement_key_input wired).
Now runs keyless as generate-only: loops every variant, concatenates to
the IMAGES output, skips temp-save/manifest/rating. (Per-variant sub-calls
are single-variant -> _split_batch_variants returns None -> no recursion.)
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Add guess_freeze_seed (default True) threaded refine_v2 -> _v2_pack_batch
-> _v2_pack_guess_ladder and the Studio refine_v2 call. Frozen = every rung
shares one seed (only conditioning strength varies; cleanest for learning).
Off = distinct seed per rung (varied compositions too). New "Freeze seed"
toggle in the Interactive Guessing config; persisted on Arm.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
UI: Batch Training tab gains Mode (Regular / Interactive Guessing),
Direction, Range, and a Learning toggle; Arm sets refiner.guess_* +
batch_learning; auto-disarm clears guess_mode; rating list shows each
rung's [x factor]; Submit passes the learn flag.
Learning (batch_training.py): submit honors learn=false (pure generation,
no training). Guess batches detected via guess_factor -> _learn_guess_ceiling
finds the furthest-pushed acceptable rung before quality broke and stores a
per-key safe ceiling (absolute spread + factor) via _store_guess_ceiling.
Dual auto-cap (refine_v2, normal runs only): soft pre-limit on
absolute_strength + hard clamp of the output conditioning's video-channel
spread to the learned-safe value in _v2_finalize_conditioning. Skipped
during the guessing ladder itself. Helpers conditioning_spread /
scale_conditioning_spread.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
New variant producer for Batch Training that, instead of seed/shortcut
variation, scales the conditioning's spread (sigma) on VIDEO channels by a
linear ramp across N rungs, freezing everything else including the noise
seed so the only variable is conditioning strength. Up amplifies toward
overbake, down dampens. Each rung records funpack_guess_factor (in cond
meta + batch manifest) so the ladder is interpretable and Phase-3 learning
can read each rung. Audio channels untouched (scale_conditioning_spread
reuses the LTXAV channel split). Wired refine_v2 -> _v2_pack_batch
(guess_mode branch -> _v2_pack_guess_ladder) and the Studio refine_v2 call
(guess_mode/direction/range from refiner settings).
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Previously the batch path returned only the last variant's frames on the
IMAGES slot. Collect each variant's decoded frames (CPU) and concatenate
them so the whole batch comes out IMAGES back-to-back — enabling the
"just make N slight variations, don't rate them" use case. Falls back to
the last variant if frame shapes are incompatible. (Phase 1 of Interactive
Guessing.)
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Reuse _normalize_video_denoised in _sample_const_rf_full (Hybrid CONST/RF
path) and sample_funpack_distilled_flow: new normalize_strength /
normalize_start_sigma (default 0 = off). Applied to the denoised after
rescue/quality-sharpness, video-only, so audio is never touched and the
samplers keep AB2/Heun/velocity/rescue. Wired node INPUT_TYPES (appended)
-> get_sampler -> Studio _build_one_sampler + JS panels for both.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
New SAMPLER for distilled LTXAV at CFG=1: deterministic 1st-order euler
base (clean ddim look + clean audio) plus per-step video-only latent
normalization to counter overbaking / oversaturation / colour drift at
~zero overhead. Tracks the video latent's robust spread, anchors a
reference once x0 is meaningful (normalize_start_sigma), and compresses
inflated later steps (normalize_strength). Benefit-only, no-op when
healthy, audio never touched (whole-latent for single-stream LTXV).
Velocity bias + rescue included, video-only.
Node FunPackNormalizingSampler + Studio sampler option ("Normalizing")
wired through _build_one_sampler and the JS panel. Registered in __init__.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Instead of full AB2 on every step, optionally ramp the AB2 contribution
linearly 0->1 across the schedule: denoised_eff = lerp(raw, ab2, i/(N-1)).
Early/high-sigma steps stay near 1st-order euler (less overshoot); late
steps get full AB2. Reuses the computed AB2 estimate -> no extra model
evals. Aimed at low-step distilled quality. No-op at order=1; audio still
rides plain euler. Wired node -> get_sampler -> Studio panel (+ JS toggle).
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
The FunPack Hybrid Euler 2S and Distilled Flow samplers applied AB2 denoised
extrapolation and the Heun corrector to the whole packed LTXAV latent, audio
slice included -> degraded audio. (Stock euler/ddim are clean because they're
1st-order; ComfyUI "ddim" == euler.) Confine both to the video stream via
_video_only so audio always rides plain 1st-order euler on the raw model
denoised, regardless of order/correction settings. Distilled Flow s_noise
diversity injection is now video-only too.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Absolute/Relative steer mode (Refiner V2 + Studio) and audio-safe
conditioning steering on LTXAV.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
The conditioning-dim diagnostic logged once per process via _FUNPACK_AV_LOGGED,
so after the first generation it went silent — easy to read as "it never ran".
Fold the detected split into the per-run "Absolute steer applied" line so every
generation states whether audio is PROTECTED (video[:v] of D) or NOT split
(unrecognised width -> steering all channels, audio unprotected). Makes the
no-op case visible instead of silent.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
LTXAV splits one conditioning tensor into video|audio channel-slices
(av_model _prepare_context: torch.split(context,[v_dim,a_dim],-1)) and
cross-attends each stream to its own slice. Steering the whole tensor
corrupted the audio's text conditioning -> degraded audio (observed live).
Add protect_audio_channels: restore the audio channel-slice from the
unsteered conditioning so every edit moves video only. Applied at all
steering chokepoints:
- _v2_apply_conditioning_memory (per-prompt: liked/axis/concept/vf-grad)
- _v2_apply_absolute (global taste pull)
- _v2_ascend_conditioning (relative VF ascend+search)
- attn2 K/V direction patch + phrase emphasis
- FunPackConditioningAdjust (manual)
- sampler embed_guidance wrapper + per-scene VF ascend
Split auto-detected from width (7680->3840, 6144->4096); logs once.
Single-stream LTXV / unknown width = no-op (no regression).
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Inserting the combo mid-list shifted every saved widgets_values slot in
existing Scene Chain Sampler nodes, so a leftover numeric value validated
against the combo ("0 not in ['relative','absolute']"). Moved it to the end
of optional inputs; old workflows keep their widget positions and fall back
to the 'relative' default.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Relative (default, unchanged) = per-prompt steering. Absolute = a keyless,
prompt-agnostic "global taste" prior that pulls conditioning toward generally-
liked directions regardless of the prompt; Both layers them.
- New keyless Absolute store (FUNPACK_ABSOLUTE_KEY): pooled liked/disliked
direction + global value function, learned across every rated generation.
- Absolute rating semantics: a rating means "details I like in general" (not
prompt adherence) — reward-driven liked/bad-dir storage, axis attribution
bypassed. Perfect = "more of this everywhere".
- _v2_finalize_conditioning replaces the per-key ascend hook on both returns;
pure Absolute also bypasses per-prompt conditioning memory.
- Scene Chain sampler: embed_guidance_source (relative/absolute) lets the
per-step nudge draw from the global direction/value function.
- Studio popup + V2 node expose Steer mode + Absolute strength.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
