Commit Graph

20 Commits

Author SHA1 Message Date
Z User
01946fa657 fix: harden every H3 sizing entry point against off-grid API canvases
The 2026-10-16 user crash report (544x960 project, reshape '[1, 24, 1, 1,
15, 2, 8, 2]' invalid for input of size 12240) decodes to a keyframe
conditioning latent of 272x480/16: the raw, unaligned half-res first pass
that e83beb1 already floors onto the 32px grid. The crashing install runs
a pre-fix pack build (the workflow's embedded pack hash is not on main),
so the reported trace itself is stale-build behavior - users must update
the pack and restart ComfyUI.

This commit closes the two remaining paths that could still feed an odd
latent to comfy's patchify_video:

- EasyMultiTrackProject now floors info width/height onto CANVAS_MULTIPLE
  right after parsing tracks_info. The MultiTrack Editor only offers grid
  sizes, but external app clients inject project dimensions through the
  ComfyUI API and could send any value; media loading, reference encoding,
  both sampling passes and exports now agree on one aligned canvas
  (no-op for every editor-selected size).
- MiniMaxH3ReferenceToVideoFallback grid-aligns reference video frames
  before vae.encode, matching what comfy core's native node already does
  on builds that ship H3 (the fallback only registers on older builds).

Adds regression tests: the 544x960 single-pass first pass must condition
at 256x480, off-grid API dimensions (530x964) must align to 512x960 with
a 1.25x second pass at 640x1216, and the reference fallback must encode
off-grid ref videos on the grid.
2026-10-16 18:45:53 +00:00
Z User
078a7749b3 revert: remove Moxie MultiTrack Project Slow and restore the certified project nodes
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.
2026-10-15 04:30:50 +00:00
Z User
5347719cdd fix: scope the even-latent first-pass snap to Moxie MultiTrack Project Slow
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.
2026-10-15 03:08:37 +00:00
Z User
46617b71b8 fix: snap the half-res first pass onto the even-latent grid
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).
2026-10-15 02:05:48 +00:00
Z User
68d30bd69a feat: add a tiling on/off switch to Moxie MultiTrack Project Slow
Tiling stops being a baked setting and becomes a widget: the new Boolean
tiling switch next to upscale_model (default on) turns the memory-adaptive
spatial tiles of the 2-step refine pass off, so the pass can be sampled in
one piece on machines that prefer the pre-tiling behaviour.

- OFF injects {enabled_tiling: "false", tile_count: 0}; the engine then
  builds the plain SamplerCustomAdvanced second pass instead of the tiled
  preview sampler
- ON keeps tile_count 0 (automatic): the engine picks the tile count from
  the available accelerator memory and skips tiling when the full
  evaluation fits, keeping 1920x1080 within reach of 12 GB and AMD/Intel
  GPUs
- workflows saved before the switch existed keep tiling on
- tests: schema slot order + defaults, switch ON/OFF passthrough, legacy
  fallback; docs: CHANGELOG + multitrack-schema reference
2026-10-15 00:43:30 +00:00
Z User
ce03875c69 feat: enable automatic spatial tiling on Moxie MultiTrack Project Slow
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
2026-10-14 23:37:47 +00:00
Z User
43d5bf9a1e feat: expose the latent upscaler as an upscale_model widget on Moxie MultiTrack Project Slow
The Slow node previously baked the upscaler checkpoint filename
(minimax_h3_latent_upscaler_3d_fp16.safetensors) into its settings with
no place on the node to choose it. The checkpoint is now a proper
upscale_model combo widget placed with the model components (after
audio_vae):

- options are None plus every file under ComfyUI/models/latent_upscale_models/
  (the bundled default is always kept selectable so the combo default is
  valid even before the checkpoint is downloaded)
- picking None (or an empty string, e.g. from a converted primitive
  socket) raises a clear error instead of silently falling back to the
  decode/RTX-resize/re-encode path this node exists to avoid
- workflows saved before the widget existed fall back to the bundled
  checkpoint, so they run unchanged
- engine untouched: the value flows through the existing
  kwargs.get('upscale_model') read; baked settings simply stop
  overriding it (base BAKED_PROJECT_SETTINGS copy pops the key)
- MoxieProject gains a _component_inputs() schema hook so subclasses can
  slot inputs in with the model components; base node schema unchanged
- tests: schema spot/ordering, folder listing without duplicates, widget
  passthrough, pre-widget fallback to the bundled checkpoint, None/empty
  rejection; CHANGELOG + multitrack-schema.md updated
2026-10-14 22:37:59 +00:00
Z User
5a3b03ef61 feat: add Moxie MultiTrack Project Slow with latent-upscale refine pass
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
2026-10-14 22:14:07 +00:00
Z User
0a9416b91a feat: expose context_frames on Moxie MultiTrack Project
MoxieProject subclasses EasyMultiTrackProject and runs the same
continuation engine, but its consolidated schema hid the new
context_frames widget added to the parent node in 724da63 - so the
overlap stayed locked at 22 for the node end users actually see.

- add the same context_frames combo (5/22/39/56, default 22) between
  steps and seed on Moxie MultiTrack Project; execute() already
  forwards kwargs through to the base engine untouched
- baked euler/beta sampling stack unchanged: sampling_plan stays
  'custom', sampling_mode stays 'single'
- tests: MoxieProject schema order/options, execute passthrough proof
  (widget reaches the base engine, baked settings never clobber it),
  and the moxie_nodes schema assert updated for the new widget; test
  harness gains a comfy.samplers stub and ControlAfterGenerate.randomize
- docs: multitrack-schema.md notes the widget on MoxieProject;
  CHANGELOG updated

Default 22 keeps every existing MoxieProject workflow identical.
2026-10-14 05:12:39 +00:00
Z User
724da63f7f feat: expose context_frames on the MultiTrack Project node
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.
2026-10-13 16:45:41 +00:00
Z User
88849ced65 refactor: remove the LoRA pipeline; distill weights ship baked into the model
The 3-step distill (speedup) LoRA is now baked into the diffusion model
itself, so the Moxie Multimedia Loader no longer applies any LoRA:

- moxie_loader.py: drop the models/loras scan, _auto_lora(), the module
  level LoRA cache and _apply_lora(); the load chain is now
  diffusion model -> attention backend -> CLIP -> VAEs. A leftover file
  in models/loras is silently ignored and the folder can be deleted.
- moxie_project.py / moxie_preview.py: tooltips reference the baked-in
  distill instead of the LoRA.
- tests + standalone loader script: assert no load_lora_for_models call
  happens (the comfy.sd stub now raises if the loader tries), and fix
  the pre-existing MMnode.tiny_vae stub gap (missing pack_vae_approx_files)
  that broke the whole test module at fixture setup.
- README: models table drops the Turbo LoRA row; CHANGELOG entry added.

Node schema, outputs and sampling behavior are unchanged; workflows
saved before this change keep working.
2026-10-13 03:34:47 +00:00
Z User
8ede97ab11 feat: revert editor to pristine upstream, drop format label mapping and T2V==R2V, fix editor delivery
- 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
2026-09-27 21:24:56 +00:00
Z User
0c4987d090 T2V resolves to the same value as R2V; loader shows a single model
- 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.
2026-09-27 05:50:35 +00:00
Z User
5ad3859bf7 feat: slim Moxie Project Video Combine to GetVideoComponents-style outputs
MoxieCombine now exposes exactly images / audio / fps - the leftover
VIDEO and FILENAME_PREFIX outputs are gone, so the output file name is
chosen on easy saveVideo itself. The base easy multitrackProjectVideoCombine
keeps its VIDEO and FILENAME_PREFIX outputs for legacy workflows.

The shipped Moxie-consolidated template is rewired accordingly: fps/images
links follow the new slot indices (2/0), the filename_prefix link is replaced
by the same project-scoped literal the removed output produced, and the
TEMPLATE's save location is unchanged.

pytest: new schema/execute/blocker coverage for MoxieCombine via a
_load_moxie_combine helper; base-combine assertions untouched.
2026-09-27 04:16:02 +00:00
Z User
fc040c1645 feat: translate all cache/task console logs to English
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.
2026-09-26 23:27:09 +00:00
Z User
27041a8a9f feat: scrub EasyMedia/MiniMax branding from all user-facing output
Console, errors, tooltips, descriptions and display names no longer
reveal the pack heritage or the underlying model family:

- [EasyMedia]/[Easy Media] console prefixes -> [Moxie] (11 files)
- New console privacy filter (utils/log.py, installed at pack import):
  rewrites MiniMax variants in every displayed logging record, including
  ComfyUI core lines like 'Model MiniMaxH3 prepared for dynamic VRAM
  loading', %-args and matching tracebacks. api.minimaxi.com is protected
  so cloud-API errors stay accurate.
- Node display names rebranded (node_ids untouched, workflows safe):
  'MiniMax H3 To Video' -> 'Moxie To Video', etc.
- ~40 error/tooltip/description strings reworded to Moxie terms.
- CLIP error no longer names CLIPType.MINIMAX; test match updated.

Unchanged on purpose (breaking if touched): node_ids/class names,
combo value 'MiniMax' (workflow payloads), internal dict keys
(minimax_keyframes/minimax_refs), llm_api cloud provider strings,
class-name logic checks, source-only docstrings.
2026-09-26 23:05:24 +00:00
Z User
d3ce6866a4 fix: move LoRA cache off the node class for ComfyUI locked classes
Newer ComfyUI builds lock registered v3 node classes after registration
(comfy_api internal __setattr__ guard), so _apply_lora writing
cls._loaded_lora raised: Cannot modify class attribute '_loaded_lora'
on locked class 'MoxieMultimediaLoaderClone'.

The (path, sd, metadata) cache now lives at module level, which the
locking mechanism does not touch. Test monkeypatch updated to match.
2026-09-26 22:34:21 +00:00
Z User
e2ae630ec2 feat: lock Moxie loader to MiniMax H3 and drop model_loader bundle
The Moxie model set is MiniMax H3-only, so no other model choices are
exposed in the editor:

- Moxie Multimedia Loader: removed the clip_type dropdown (which listed
  every CLIPType recipe in ComfyUI). The H3 Qwen3-VL text encoder is now
  always loaded with CLIPType.MINIMAX; older ComfyUI builds raise a
  clear error instead of silently loading the wrong encoder.
- Moxie Multimedia Loader: outputs are now exactly model, clip,
  video_vae, audio_vae - the legacy FAST_MODEL_LOADER (model_loader)
  bundle output is removed. The model output keeps the attention
  backend and LoRA applied.
- Moxie MultiTrack Project: takes model, clip, video_vae and audio_vae
  as required direct inputs instead of a bundled model_loader; the
  fallback plumbing is removed while EasyMultiTrackProject keeps its
  model_loader input for non-Moxie workflows.
- Moxie Preview Override: dropped the model_loader pass-through slots
  and patches the model input directly.
- Moxie-consolidated.json reference workflow updated to the new slots.
- Added tests/test_moxie_nodes.py covering the schema contracts, the
  attention -> LoRA -> output chain, the MINIMAX lock and the project
  loader synthesis.
2026-09-26 19:06:50 +00:00
Z User
bec001f6f7 test: skip zh localization tests when locales bundle is absent
The upstream locales/zh/nodeDefs.json is not part of this repository,
so every test reading it failed at runtime. Guard all 16 call sites
with pytest.skip and add a tests/conftest.py that stubs folder_paths
so collection works outside a full ComfyUI installation.
2026-09-26 19:06:41 +00:00
4ea8431cd0 init
Some checks are pending
Publish to Comfy registry / Publish Custom Node to registry (push) Waiting to run
2026-09-26 11:11:23 -07:00