Tree restored to 0a9416b (before the Slow arc): the Slow node and its
registration, the upscale_model/tiling widgets, the even-latent
first-pass snap, and every Slow-motivated change to the shared project
nodes (first-pass sizing hooks, tile_count relaxation, preview widget
minimum) are gone. LoRA removal and the context_frames feature predate
the Slow arc and are kept.
The crash fix for the scene-2+ patchify_video failure had been applied in
the shared EasyMultiTrackProject pipeline, changing the hidden first-pass
size of the certified MultiTrack Project and Moxie MultiTrack Project
nodes too. Certification requires those nodes to keep their exact
behavior, so the snap now lives behind overridable hooks whose defaults
are the certified rules:
- _h3_first_pass_size default: max(32, int(editor * scale)) plain
halving (the certified formula). MoxieProjectSlow overrides it to snap
onto the nearest 64px grid, fixing the odd-latent crash on its own
continuation segments only (1080p -> 960x512, 1344x768 -> 704x384,
4K -> 1920x1088 unchanged).
- _h3_needs_latent_upscale default: the certified 'upscale_by <= 1'
skip rule. MoxieProjectSlow overrides it with a true size comparison
(load-bearing for its latent-upscale refine at upscale_by 1.0).
- The certified sampling preview sampler keeps its widget text, default
2 and max 8; min stays 0 only because the engine passes the Slow
node's automatic tile_count 0 through it and ComfyUI validates inputs
against min at execution.
utils/h3_project.py is back to its certified state (the snap helper now
lives in the Slow node's own file). Regression tests pin the certified
first-pass dims and decision rules of both certified project nodes so
any future drift fails the suite loudly.
Multi-segment projects crashed on the first continuation segment with
RuntimeError: shape '[1, 24, 1, 1, 8, 2, 15, 2]' is invalid for input of
size 12240 (patchify_video). The hidden half-resolution first pass
declared its size with plain integer halving, so a 1920x1080 editor
sampled at 960x540 - and a latent encoded from 540px carries an odd
17-row count. Odd latents sample fine, but when the segment tail comes
back as motion-context keyframes on the next segment, the model's
patchify_video (2x2 latent patches) cannot reshape them.
The first pass now snaps onto the nearest 64px grid (h3_even_latent_size)
so every latent in the pipeline keeps even row/column counts:
- 1920x1080 editor samples at 960x512 (was 960x540 -> 17 rows)
- 1344x768 samples at 704x384 (672 had odd latent columns)
- 3840x2160 is unchanged at 1920x1088 - the size the VAE already rounds
up to, so the 4K-editor trick behaves identically
Outputs and second-pass dimensions are unchanged; only continuation
segments that previously crashed now run. Also updates the stale
single-task expansion test, which still expected pre-half-res-trick
conditioning dimensions (editor size instead of the sampled size).
Bake enabled_tiling with tile_count 0 (automatic) into the Slow node's
second pass: the engine picks the tile count from the available
accelerator memory and bypasses tiling entirely when the full evaluation
fits. This brings 1920x1080 output within reach of 12 GB cards and
AMD/Intel GPUs - the tiling machinery only uses device-agnostic ComfyUI
memory helpers.
- _h3_tiling_config now accepts tile_count 0 (automatic) alongside 2-8
- easy h3SamplingPreviewSampler schema allows tile_count min 0
- tests: tiling config parsing, baked Slow passthrough, second-pass
graph receives tile_count 0, sampler schema range
- docs: CHANGELOG + multitrack-schema reference
New project node variant (MoxieProjectSlow, display name 'Moxie
MultiTrack Project Slow') that replaces the RTX VSR pixel restore with
a latent upscaler plus a short refine pass:
- identical UX to MoxieProject: end users only set steps and seed (plus
the shared context_frames overlap); schema mirrors the base node via
a shared _project_inputs() helper
- first pass stays at the hidden half resolution (engine gains a
_h3_first_pass_resolution_scale class hook, overriding the previous
sampling_mode == 'single' hardcode; MoxieProjectSlow returns 0.5
under dual mode)
- the half-res latent is upscaled to the final (editor) size by the H3
latent upscaler (minimax_h3_latent_upscaler_3d_fp16.safetensors,
models/latent_upscale_models) and refined with a hidden 2-step euler
pass at 0.33 denoise; the schedule replicates KSampler.set_steps
(int(steps/denoise) total steps, last steps+1 sigmas) without relying
on the denoise kwarg that newer comfy.samplers builds dropped
- baked settings: sampling_mode dual, upscale_by 1.0 (final size IS the
editor size), upscale_model as above; the engine's upscale-skip
condition now compares actual first-pass vs target dimensions instead
of upscale_by <= 1, which is behavior-identical for every existing
configuration
- segments are saved at the project resolution, so the Video Combine
restore passes through untouched - no RTX VSR anywhere
- MoxieProject refactor: component check and baked settings moved into
reusable helpers (_require_moxie_components, _baked_project_settings
classmethod) so the subclass composes cleanly; messages unchanged
- tests: Slow schema mirror, execute passthrough (sigma schedule math,
baked settings, context_frames forwarding, first-pass schedule), the
resolution-scale hook, and the denoise truncation helper
- docs: CHANGELOG entry, multitrack-schema.md note
The number of frames copied from the previous segment as continuation
context (Context / Context Swap continuity) was hardcoded at 22. The
H3 context sampler nodes already accept 5 / 22 / 39 / 56, so the
project node now exposes the same choices as a context_frames combo:
- resolve the widget once in execute() and thread it through every
continuation site: the ContextSwap / MotionContextHard / HiResContinuity
graph nodes, the audio-lock prepend, the runtime latent trims, the
passthrough context encode, and the hires/low context re-encodes
- the context continuation now generates context_frames + 12 grid-tail
frames (was a hardcoded 34) so every supported value stays on the
H3 temporal grid; off-grid values raise a clear error up front
- tests: widget propagation at 5 frames end-to-end in the built graph,
off-grid rejection, schema order/options; existing 22-frame asserts
unchanged
- docs: multitrack-schema.md documents the widget; CHANGELOG entry
Default 22 keeps every existing workflow byte-identical.
- frontend/src + messages restored byte-identical to upstream v1.3.3:
format normalization shims, isMoxieEditorFormat gates, bundle marker,
tooltip reword, and their tests all removed; editor bundle rebuilt from
that pristine source so the editor behaves exactly like upstream
- format combo shows 'MiniMax' again (options=[MiniMax]); legacy queued
'Moxie Multimedia' values still normalized to MiniMax at execution
- T2V resolves natively again: t2v stays t2v in h3_task_type,
_multitrack_task_type and getMultiTrackTaskType; generation-mode t2v
mapping and the zero-media cloud fallback removed (upstream behavior);
Python tests and stub scripts updated accordingly
- editor delivery fix: core lets WEB_DIRECTORY overwrite the pack's
EXTENSION_WEB_DIRS entry, so the /extensions listing never contained
dist/release and a fresh browser never imported the editor (it only
ever appeared from stale browser cache). web/js/editor-loader.js now
imports the editor entry from the pack's own static mount, which
serves index.js with no-cache (chunks stay cacheable); the
/extensions/<pack>/index.js route was removed as a 404 trap
- shipped Moxie*.json templates carry format value MiniMax
Verified: frontend diff vs upstream = 0; bundle string checks + chunk
refs; vitest 565/566 (same pre-existing jsdom URL.revokeObjectURL env
failure); py_compile; test_t2v_r2v_and_loader.py ALL PASS;
test_rtx_upscale_integration.py ALL PASS
- T2V selections (editor default mode, explicit [start-end,t2v] override
tags, raw t2v values) now resolve to r2v in every task-type resolver
(h3_task_type, _multitrack_task_type, frontend getMultiTrackTaskType);
h3_generation_mode maps raw t2v to reference conditioning as belt and
braces. Reference-mode with zero reference media renders text-only
locally; the cloud path falls back to its native t2va request instead
of raising. i2v/l2v/v2v/edit flows unchanged.
- MoxieMultimediaLoader now presents a single model picker: LoRA, video
VAE, audio VAE, and CLIP widgets removed and auto-selected from the
pack's models/ folders (first sorted file, loud error when missing,
LoRA applied at strength 1.0 when bundled). Outputs and load order
unchanged; saved workflows keep working (extra widget values ignored).
Verified: py_compile; scripts/test_t2v_r2v_and_loader.py 50/50;
frontend vitest 566/567 (one pre-existing env failure on HEAD);
bun run build; scripts/test_rtx_upscale_integration.py all pass.
- the format combo on MultiTrack Editor and MultiTrack Project now
shows 'Moxie Multimedia' (FORMAT_DISPLAY_LABEL); every queued value
is normalized back to the internal 'MiniMax' value at both execute
entries and check_lazy_status, so tracks_info, conditioning caches,
saved manifests and frontend lookups are unchanged
- frontend: normalizeFormatValue() maps the display label back at the
format-widget read point so MiniMax-specific editor features keep
working; shipped templates carry the new label
- removed the per-run 'Output upscale' console line; the restore now
happens silently (one-shot fallback diagnostics kept)
Note: workflows saved before this change need the format re-picked
once, since 'MiniMax' is no longer a combo option.
The compose step previously built the timeline at the manifest
resolution while staging segments are written at the (hidden) half-res
sampling size, so ffmpeg's overlay pasted the smaller segments into the
top-left quarter of a black full-res canvas and the combine's restore
gate saw frames already at the manifest size and never fired.
- compose_h3_project_video now probes the timeline segments and composes
at the size they all share (_uniform_probed_size; manifest dims remain
the fallback for mixed/unknown sizes)
- restore_project_video_resolution (utils/rtx_vsr.py) fast-probes the
composed file, and when it differs from the manifest decodes once,
upscales (RTX VSR, Lanczos fallback, exact size) and rebuilds the
video so VIDEO, images, audio and fps all carry the editor-selected
resolution; any failure keeps the original video
- the restore lives in the base combine so MoxieCombine (images slot)
and the legacy GetVideoComponents wiring are both covered; the
duplicated images gate in MoxieCombine is gone
Single-pass projects condition and sample at exactly half the
editor-selected resolution (plain integer halving, no dimension
policies). Moxie Project Video Combine restores the exact editor
resolution on the combined frames right before its images output,
driven by the fresh project manifest so a stale frontend widget can
never misgate it.
- utils/rtx_vsr.py: RTX VSR core (Apache 2.0, from
Comfy-Org/Nvidia_RTX_Nodes_ComfyUI) + Lanczos fallback; the gate is
simply 'frames differ from the manifest resolution'
- nodes/project.py: halve first-pass dims for single mode only;
dual-pass, SelfLift, passthrough and audio-only keep the editor size
- moxie_combine.py: restore before the images output
- scripts/test_rtx_upscale_integration.py: 17 standalone checks
Single-pass MultiTrack projects now condition and sample at half the
editor-selected resolution; Moxie Project Video Combine restores the
exact editor resolution on the combined frames before export, so the
editor resolution remains what the user sees and gets.
- utils/rtx_vsr.py (new): RTX Video Super Resolution core adapted from
Comfy-Org/Nvidia_RTX_Nodes_ComfyUI (Apache 2.0) driving the optional
nvidia-vfx package per frame, with automatic Lanczos fallback and
exact-size correction; owns the sampling-dimension policy and the
project_data gating so only half-res signatures are upscaled
- nodes/project.py: gate half-res conditioning/sampling to single-pass
mode (dual-pass, SelfLift, passthrough, audio-only unchanged)
- moxie_combine.py: restore editor resolution right before the images
output; VIDEO preview output passthrough unchanged
- scripts/test_rtx_upscale_integration.py: standalone sanity checks
(no ComfyUI/torch needed) for the dimension policy and gating
MultiTrack and H3 conditioning cache logging printed Chinese labels
(ProjectMedia/SegmentMedia statuses, timing and cache-size breakdowns).
Translate every console-facing string to English so the ComfyUI log is
fully English-readable:
- cache status values are now 'cache-hit' / 'first-load' (was Chinese),
including the _all_media_caches_hit sentinel comparison and the
_easy_media_cache_status data written into tracks_info
- cache size breakdown now reads 'file(...)=conditioning(...)+...'
with English category labels
- timing/stage messages, video-track compositing and locked-audio
extraction messages, and llama.cpp install errors are English
- fullwidth '|' in the media_loading timing line replaced with ASCII
- test assertions updated to the new English strings
No behavioral changes beyond the log/status wording; the Chinese
prompt-reference syntax (@图片N etc.) and LLM prompt templates are
intentionally untouched as they are functional.