H3's latent upscaler loads through the H3 module (ComfyUI's loader has no
branch for it); an upscale resizes H3's anchor pin so pass 2 stays pinned.
FunPack Sampler takes an optional wired schedule, run exactly as written.
New preset: H3 Reference to Video + second pass.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The port plan calls for every module under modules/ to declare a
CATEGORY so Settings/Engine panels can group by it. Only alg, sharpen,
appearance, and full_control had one; the other 12 (loaders, empty
latent, media load, minimax_h3, output decode, sampling modifiers/
sampler, system pipeline) are plain infrastructure with no user-facing
settings dial, so they land in "system" except output_decode (post,
matching its STAGE) and the two sampling modules (sampling). Verified
against core/tests (548 passed) -- category validation and the
registry's field-mapping catch a typo here, per the earlier fixture-gap
fix.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
The wording fix a commit ago was written by hand in two files and the same
mislabel was still sitting in four others -- traits, chain, modifier install and
node schema all reported a thing that loaded, recognised its work and then
raised as one that "did not load", sending a reader after an import error that
never happened. Three hand-written strings would have drifted, so log.broke()
now says it once and every site calls it.
Two of the new tests were vacuous when first written -- "nothing said did not
load" is also true where nothing ran at all, and picking the first provider
found lands on one whose traits exclude the test's model. Both assert the line
is present before asserting the wrong line is not.
One finding, confirmed, plus four sites it did not name.
`log.failed` means "did not load", and both the latent and the decode paths used
it for a provider that loaded, claimed the model and then broke while working --
"did not load -- RuntimeError: ..." sends whoever reads the log looking for an
import error that never happened. The levels were separated for exactly this.
One finding, confirmed.
Two corrections to the commit before this one.
A rank-1 latent's length is in the NODE that builds it and never in the format:
core turns seconds into samples with a 44100 rate and a 2048 hop that
latent_format does not carry, and the same rank means tokens of geometry for
Hunyuan3D. Deriving `length` samples gave StableAudio a latent of 1 where core's
own default is 1024 -- three orders of magnitude short, reported as success.
Refused now, with the reason and the way out: a module for that model.
The sweep claimed to skip H3 and did not. H3 has a rank-3 latent, so it was
derived and passed at 32 channels for a video branch that has 24 -- a test
passing on a model it is not correct for. So the previous message's "produces
exactly what core's nodes compute for every single-tensor model" was wrong on
both counts, and the sweep now says what it actually proves: the derivation
agrees with what a model PUBLISHES, which is a floor and not a certificate.
Rejected from the same report: an absent model module letting H3 fall through to
the generic shape. Core cannot detect that without naming models, which is the
one thing it must not do; a module that fails to import is already reported as a
Warning, which is the level that can see it.
LTX and WAN needed no module: both publish everything the derivation reads, and
it produces exactly what EmptyLTXVLatentVideo and Wan22ImageToVideoLatent
compute, by a different route. Pinned, along with a sweep over all 101 configs
ComfyUI ships -- rank, channel count and no empty axis -- so a family that
arrives after this was written is covered or fails here rather than at the first
sampling step.
H3 remains the only model needing a module of its own, because its latent is not
a single tensor.
A provider that raised was treated exactly like one that said "not my
model", so the node fell through and derived a shape for the very model the
provider existed to handle -- and reported success. For H3 at length=124
that is 31 latent frames against a real grid of 37: a 16% shorter video,
with nothing downstream saying anything.
The protocol is now stated: return None for "not mine", and let anything
else raise. Recognition happens before anything that can fail, so an
exception means the model was already claimed, and the node refuses rather
than substituting a generic shape.
execute() had no test at all -- the dispatch between claimed and derived is
the point of the node, and both earlier tests called around it. It now runs
through the real registry, and the refusal test fails against the old
fall-through.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Derived from latent_format where that is possible, which is every
single-tensor model: SDXL, Wan21 and LTXV all come out matching the numbers
core's own nodes compute, including models that ship after this.
H3 cannot be derived and is the reason modules exist. Its latent is a
NestedTensor of a video and an audio branch, its video channel count is not
the latent_channels its format reports, and its length snaps to a frame
grid. So modules/models/minimax_h3 claims it and builds it, importing the
grid from ComfyUI rather than copying a second definition of it.
Nothing outside that folder names a model, and nothing here assumes video:
a 2-D latent format yields an image latent with no branch anywhere.
Modules reach core through modules/_core.py. ComfyUI imports a pack by file
location, so an absolute `import core` in a module resolves under pytest and
not under ComfyUI -- the node then never registers, silently. That cost the
same bug twice, so there is now a test that loads the pack the way ComfyUI
does, in an isolated subprocess whose cwd is NOT the repo. The first version
of that test passed with the bug reintroduced, because cwd was on sys.path.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
digital-garbage