The global prompt is now the verbatim source of truth. New conditioning helper
split_timeline_verbatim() splits it into anchor + scene chunks using shortcut-aware
transition boundaries but WITHOUT expanding shortcuts or dropping any word, so
anchor + scene texts concatenated reproduce exactly what the user typed. A 'start'
trigger leads the new scene; 'end'/'silent' trails the previous chunk.
- build_combined_prompt is now a pure join (anchor + scene texts, single spaces) —
no injected scene markers. Generation sends this verbatim prompt to Studio, which
expands shortcuts / splits by transitions / applies the anchor as it always does.
So editing a scene rewrites only its chunk and the global prompt = concatenation
(nothing un-typed ever reappears).
- bridge.parse_timeline_verbatim + parsed_verbatim on /parse and /preview.
- applyGlobalPrompt / syncFromPreview consume parsed_verbatim (authoritative).
Example: 'CHAR: a woman, man qcut hug cut hug kiss' -> anchor 'CHAR: a woman, man',
scene1 'qcut hug cut', scene2 'hug kiss'.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Renders are now ephemeral — VHS writes to ComfyUI's temp dir (save_output=False)
and the final stitch is written to temp too; both clear on ComfyUI restart.
Persisting is the user's job:
- 'Export' toolbar button saves the selected clip's render via a Save dialog
(showSaveFilePicker where available, else download). Rendered clips show a green
dot; the button is disabled until the selected clip has a render.
- 'Render Final Video' stitches available runs to temp and opens a Save dialog.
Fix regression from the shortcut-verbatim change: scene/transition structure can
be produced by shortcut EXPANSION, so the global-prompt / sync now take structure
from whichever split yields more scenes (expanded wins when raw under-splits),
keeping verbatim text only when the raw split structures the prompt equally well.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
- Models/nodes/links are now carried IN the project (Project.models), not a single
global file. New projects seed from the global default; saving updates that
default so the next new project inherits your latest loaders. Per-project routes
GET/PUT /projects/{pid}/models; generate + image-targets use the project's config;
editor reloads models on project switch. Global /api/models kept as the seed.
- New scenes default to 'carry' (continuous; scene 1 carrying just starts a fresh
run). Dropping an image onto a scene still auto-switches it to the image anchor.
- Global prompt is the first entry in the inspector list now (was sticky/hovering).
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Global prompt and 'Sync from preview' were writing shortcut-EXPANDED scene text
into scenes (parse_timeline expands before splitting), so the verbatim combined
prompt then showed expanded shortcuts. Add bridge.parse_timeline_raw() (split
without expansion) exposed as parsed_raw on /parse and /preview; apply/sync now
take scene text from the raw split (shortcuts preserved) and use the expanded
split only to DETECT transitions (incl. shortcut->transition), mapping them to
the library by visual_effect. Generation and the split preview still expand.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Dedicated, always-visible Split (⧅) and Remove (✕) buttons act on the selected
clip — replacing the cramped corner actions that the timecode overlapped. Mirror
the S / Delete shortcuts; disabled when no clip is selected.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
S splits the selected clip at the playhead (midpoint if the playhead is outside
it); Delete/Backspace removes it. Ignored while typing in a field. Replaces the
hard-to-reach corner action buttons; toolbar shows a 'S split · remove' hint.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Generate Whole Montage now splits active scenes into chain runs bounded by
anchored scenes: a run starts at an empty/image/generated_frame scene and a
'carry' scene appends to it (overlapping via carry_i2v_guides). One ComfyUI
chain-sampler request is fired per run, sequentially; each run's first scene
supplies its i2v anchor. No sampler changes needed.
New 'Render Final Video' button hard-cut concatenates the rendered runs in
timeline order (skipping ungenerated gaps) via ffmpeg, preserving the LTXAV
audio track, and plays the stitched result in the program monitor.
- server.py: generate accepts scene_ids (a run); _segment() clone; carry_i2v_guides
forced on for multi-scene runs; POST /render ffmpeg concat (-c:a aac).
- store.js: _runs() segmentation, promise-based polling, generateMontage(), renderFinal().
- api.js: generate(scene_ids), renderFinal(); menubar: Render Final Video item.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
A 4th scene source: the scene has no anchor of its own and continues from the
previous scene's i2v guide with overlap (chain-sampler carry behaviour). UI +
data model only; per-scene carry/reset in the sampler is the V2 work to follow.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
- Per-scene Frames/FPS gain a 3-way mode (project | timeline | custom): timeline
follows the trim handle live, custom locks it. Default = timeline length / project fps.
- Global prompt pinned atop the inspector: live view of the combined prompt that
updates as scenes change; edit + Apply reparses into anchor/scenes/transitions.
- Project/Scene switch is now a segmented control in the inspector (removed from the
Generate menu).
- Models > Linked inputs now allows single-member links, so a lone node input (e.g.
FPS) can be tied to a project value without needing a second member.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
- Player: window.Player.captureFrame() draws the current video frame onto a
canvas and returns a PNG Blob. Transport bar shows '📌 Use as anchor' button
+ scene selector when the playhead is on a rendered segment; clicking it
captures the frame, uploads to the media bin, and sets the selected scene's
source to {type: 'generated_frame', media_ref, target:
'port:FunPackStudio.source_image'} — the builder wires it as the i2v anchor.
Scene selector defaults to the currently selected scene.
- Inspector: renderGeneratedFrameSource() shows the captured frame thumbnail
(with a 'replace via player' hint) when media_ref is set, or instructions
when no frame has been captured yet; includes the destination-input selector
so the user can redirect the wire if needed.
- server.py: _prepare_media accepts source.type 'generated_frame' in addition
to 'image' so the captured frame is copied to ComfyUI's input dir and wired.
- styles.css: pm-sep divider, pm-anchor-sel, pm-anchor-btn for transport bar.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- player.js complete rewrite: persistent <video> element (re-appended on
re-renders, never destroyed — playback survives any editor state change);
minibar shows rendered vs ungenerated segments; drag-to-scrub on minibar;
transport bar (play/pause/stop + timecode); playback auto-jumps to next
rendered segment or stops at first unrendered gap; window.Player mediates
playhead between player and timeline
- timeline.js: ruler drag-to-scrub (replaces click-only); playhead reads from
Player.getPlayhead(); Player.onPlayheadChanged updates only the needle +
timecode element at video frame rate without triggering a full re-render;
auto-scroll keeps playhead in view during playback; split-at-playhead reads
from Player
- store.js: renderedSegments[] tracks which sceneIds map to which video file;
populated when generation completes; cleared on project switch; generate()
passes targetSceneIds to poll() so completed segments are recorded correctly
- styles.css: program zone is now a flex column (canvas + minibar + transport);
pm-canvas fills remaining space with vignette; pm-minibar/pm-chip/pm-needle
for the segment strip; pm-transport for controls
- server.py: effective_frames uses trimmed scene.frames when all active scenes
agree, so timeline trim handle affects generation length (provided
EmptyLTXVLatent is linked to Project Frames via Models → Linked inputs)
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
sampler_panel.js: remove the Low pass section — Studio outputs high_pass_
sampler/sigmas (indices 4+5) to the chain sampler; the low-pass outputs (6+7)
are not wired in the movie editor graph. Renamed header from "High pass" to
"Sampler" since there's only one now.
store.js: show elapsed time in the generating readout so a slow run doesn't
look frozen ("Generating… 1m 23s" instead of a static "Generating… (running)").
store.js: detect job-disappeared crash — if ComfyUI returns state="pending"
three polls in a row after the job was running (job left the queue but never
appeared in history), stop polling and show "Job disappeared from ComfyUI queue
— it may have crashed. Check the ComfyUI terminal." Previously this left the
UI in "Generating… (running)" indefinitely.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
builder.py: force split_by_transitions=True on FunPackStudio — this was the
root cause of single-scene generation. Studio defaults to False (single-scene
mode); without this flag it ignores the multi-scene prompt structure entirely
and outputs only one conditioning regardless of how many scenes were split.
The flag is now forced and blocked from being overridden via studio_inputs.
nodes.py: add _WIDGET_TYPES = WIDGET_PRIMITIVES | {"COMBO"} and use it in
connection_inputs() and _all_input_types(). "COMBO" (V1 new-style dropdown)
was previously passing the WIDGET_PRIMITIVES exclusion check and appearing as
a graph-connection socket in the UI.
models.js: revert auto-wire-output-on-input-source logic (previous commit).
The heuristic was too aggressive and would pick wrong destinations when
multiple IMAGE ports exist.
server.py + store.js: surface ComfyUI execution errors. Previously a node
failure inside ComfyUI returned state="completed" with no media and the UI
showed "Completed (no media found)." — unhelpful. The status endpoint now
reads history[id].status.messages for execution_error entries and returns
state="error" + error string. The frontend poll shows the node type and
exception message so the user knows what actually failed.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
nodes.py: "COMBO" (V1/new-style dropdown widget) is a string so it passed
the WIDGET_PRIMITIVES exclusion check and was incorrectly returned as a
graph-connection socket in connection_inputs() and _all_input_types(). Added
_WIDGET_TYPES = WIDGET_PRIMITIVES | {"COMBO"} and use it in both functions.
Old-style list combos (spec[0] is a list) were already excluded correctly.
models.js: when the user assigns an input source for a connection input of
type T, auto-wire the first unwired output of the same type T to the sole
pipeline destination of that type. Applies only when: (1) the selected source
is non-empty, (2) the slot has exactly one output of that type, (3) that
output has no wire set yet, and (4) there is exactly one destination available.
This covers the common image-processor case: set image input → IMAGE output
auto-wired to studio.source_image.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
The conditioning and sampler slot pickers were in the Generate menu (a
window.prompt popup) with no visual path to the settings panels in the
inspector. Users found the menu selectors but never saw the Studio sampler
algorithm controls or the Chain Sampler knobs.
Fix: add conditioning and sampler section headers with inline <select> slot
pickers directly in the project inspector, immediately above their respective
settings panels. Changing the dropdown instantly shows or hides the panel for
that choice. The menubar items remain as shortcuts.
Also wrap SamplerPanel.render() in try/catch so a JS failure shows a visible
error message instead of silently aborting the rest of the inspector render.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
build_combined_prompt had a bug: when no anchor text was set, need_sep was
False for scene 1 so its text landed in Studio's segments[0] (anchor slot)
and never generated. An N-scene project with no anchor only produced N-1 scenes.
Fix: always emit a separator before every scene. Studio splits on separators,
so segments[0] is always the anchor (empty if no anchor text is set) and
segments[1..N] are the generated scenes. Fallback label is now "scene {i+1}"
(correctly numbered) instead of the previous "scene {label_n+1}" off-by-one.
Also: pass max_scenes = active scene count from the generate route into the
builder so the chain sampler always knows the exact number of scenes to produce.
Note on per-scene images: only the source image on scene 1 (project anchor
image) is wired to studio.source_image. Scene 2+ anchoring works via the
carry_i2v_guides flag on the chain sampler, which carries each scene's last
frame as the i2v source for the next scene. Per-scene i2v requires carry_i2v_guides
to be enabled in the sampler inspector — it is off by default.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
COMFY_MATCHTYPE_V3 is ComfyUI's dynamic IMAGE-compatible match type used by
nodes like ImageTransformKJ. All four type-extraction paths (_outputs,
_all_input_types, connection_inputs, node_outputs) now call _normalize_type()
so the UI sees "IMAGE" and role-matching, source/dest pickers, and
requirements checks all work correctly.
connection_inputs also checks spec[1].get("optional") so V3 nodes that
declare an input as required in the required group but flag it optional
(e.g. bboxes on ImageTransformKJ) are reported with required=False.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Pipeline requirements panel (top of Models modal):
- Shows every required/optional pipeline input (MODEL, CLIP, Video VAE, Audio VAE,
Audio latent, Source image, Initial latent) with satisfaction status.
- Red row + hint + 'Add' button for unsatisfied required inputs — clicking Add
pre-selects the right role in the composer so user knows exactly what to add.
- Green row when satisfied; optional inputs shown below in a grayed-out group.
- Overall 'Pipeline ready' status after all required inputs are met.
Backend:
- nodes.py: PIPELINE_REQUIREMENTS constant with human-readable labels and hints.
Added 'audio_encoder' role for Audio Encoder nodes (outputs LATENT for audio path).
- server.py: pipeline-ports response now includes 'requirements' array.
Friendly generation errors (store.js):
- _friendlyGenError() maps technical builder messages (audiodec.audio_vae no source,
audio_latent no source, etc.) to plain-English explanations pointing to Models.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Curly-quote replacement turned "Link inputs" inside a double-quoted string
into bare straight quotes, breaking the JS parser. Replaced with single quotes.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
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>
