Its step wrapper held its own ModelPatcher, a cycle only a full gc frees;
that gc clears ComfyUI's weak link to the parent copy first, leaving it
tracking a dead model ("memory leak with model MiniMaxH3").
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
_get_latent_shapes only looked under a CFGGuider's conds; wrappers hold a
ModelPatcher, so on packed AV latents every video-only wrapper passed through
unchanged. Also: late-branch and STAS say when they applied nothing, and a
learned value is only rated when the feature actually applied.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
STAS (arXiv 2603.17825) sets massive-activation channels on frame 0 and
frame edges to alpha x peak at one block over the first 40% of steps.
Rating-learned dials now share rated_dial.py.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Skip guidance at CFG 1: the weak copy reuses blocks before the branch and
skips the branch block, so only the tail runs twice. Picture only; capture
hooks ignore the weak pass; compiler off while installed.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Shot memory reuses a liked gen's coarse starting noise (layout) with fresh
fine noise; reuse-vs-fresh, which shot and how strongly are learned.
Decisiveness is Temporal Score Rescaling (arXiv 2510.01184) on the picture
rows, k learned per key or set by hand.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
It replaces every block's forward, so the model compiler must be off for that
call, as it already is for block repeat and REINS injection. Never seen before
because until d4d4e29 shadow negative never ran.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
H3 blocks add their residual into the input in place, so the kept single-pass
tensor was overwritten by the next pass and audio was restored from the
repeated stream. Keep a copy instead (block repeat and span loop).
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
It read the prompt length from transformer_options['c_crossattn'], which
ComfyUI never sets, so every block ran the stock forward. A model wrapper now
records it per call. Per-token mod rows (any pinned frame) no longer disable
it, and the step window reads the real schedule.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Studio gains an enhanced_prompt output; the link wires to it. Enhancer off or failed sends prompt + postfix unchanged.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
ComfyUI tokenizers drop an unknown system_prompt kwarg, and Gemma skips its chat template by default. Instructions now go in the user turn of the model's own template, which also places the image.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- region lock: layout patch matched the old PackedLayout signature and crashed every H3 run; interior pins now use upstream's native any-frame placement
- REINS/Q-steer/AV decouple/probes: masks cover the target video/audio rows only, not pins, refs or vision pads
- video detail: works with the PDD FinalLayer signature; now in Engine Settings
- Q-steer: steers queries before RoPE, not after (old banks are not reused)
- ALG anchor: blurs the frame-0 pin on H3
- temporal style: hidden on H3
- shadow negative: main-window chip names what it switches off without compose
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Own tab with its full sampling settings (temperature, top-p, top-k, min-p,
repetition/presence penalty, seed, greedy) and a last-run before/after view.
Studio's source_image now reaches the enhancer on the per-scene path too.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The media bin's grid always requested the FULL original file for a
thumbnail (an <img>/video-frame decode of the whole thing, only
cropped down visually via CSS/canvas afterward). A 4K photo or a
multi-MB clip got fully downloaded and decoded just to show a 96px
square, every render.
Added GET /api/media/{mid}/thumb: generates a small JPEG on first
request (Pillow resize for images, one ffmpeg frame-grab for video),
caches it under media/thumbnails/, and serves that instead. Deleting
a media item removes its cached thumbnail too. mediabrowser.js now
loads from this endpoint for both image and video kinds -- the same
canvas-drawing path as before, just fed a file that's already small
instead of the original. Measured live: a 1.57MB test clip's cached
thumbnail is 1.6KB.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
_select_best_seed called value_fn.forward()/compress() directly on a
candidate's captured prediction with no device handling -- the value
function loads CPU-only (map_location='cpu'), but the candidate tensor
lives on whatever device the model ran on (cuda in production). Every
candidate failed to score on every real GPU generation since this
feature shipped; _select_best_seed always fell back to the unchanged
seed, silently a no-op the entire time despite passing all tests
(the suite is CPU-only, so a mismatch never had two devices to hit).
Every other value_function.py call site (gradient/ascend/search) moves
its input onto next(self.parameters()).device first -- this was the
one path that skipped that. Mirrored it: compress on the candidate's
own device (cheap reduction), then move the small compressed vector
onto the value function's device before scoring.
Added a regression test using a real second torch device (mps on this
box, cuda in CI/production) to reproduce the exact cross-device
failure, and fixed three pre-existing value_fn test doubles that were
missing parameters() and had silently started hitting this same
crash branch once the fix started calling it.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Compose-mode message and Editor tooltip were stating a false remedy
(turn REINS down to passive-capture-only/strength 0 to free blocks) --
REINS claims all 50 blocks the moment it's on at all, strength only
gates injection not installation. Corrected to say only fully
disabling REINS frees any blocks.
_select_best_seed had three silent failure paths (no usable
prediction, a scoring exception, zero candidates scored) that burned
real GPU compute and reported nothing. Added prints to all three.
Added _output_value_fn_sample_count so "not ready yet" messages show
the actual banked sample count instead of leaving the user blind on
how close they are to the threshold.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Adversarial review of 77cf37e found a real, cheaply-closable test gap: this
file already calls node.sample() end-to-end with a monkeypatched value
function for the explore_first_step tests, so the same pattern (plus
spoofing minimax_h3.is_h3_model) proves the snapshot save is no longer
skipped for H3.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
h3_shadow_negative's non-composing install was silently starving REINS/
Q-steer of their own per-block capture, so ratings never trained them while
shadow negative was on (0/0 liked/disliked no matter how much was rated).
Add h3_shadow_negative_compose ("Allow when REINS/Q-steer are active"): when
on, shadow negative skips any block another dit-patch mechanism already
claimed, leaving it to keep capturing/steering there, and only pushes on the
rest. Structural coexistence, not per-block math blending -- disclosed as
such in the docstring and tooltip. Off by default, unchanged behavior.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Native port of the community "H3 Shadow Negative" pack's Basic scope: runs the
negative CONDITIONING (already threaded through the sampler, otherwise dead
weight since H3's CFG is fixed at 1.0) through H3's DiT blocks as a second
shadow stream and pushes the real stream's attention output away from it,
NAG-style. Non-composing with REINS/Q-steer/av_decouple/block-repeat/
attn_temperature by design -- replaces a block's forward outright and prints
which existing patches it superseded.
Full Editor (Cutting Room) UI exposure lands in this same change, along with
explore_first_step's own missing Editor UI from an earlier session.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Tries N candidate seeds with one throwaway denoising step each, scores
each with the trained output-space value function, commits to the
best-scoring seed for the real full pass. Candidates are scored fully
isolated from the scene's own guidance stack (model_function_wrapper
chain, context_windows, v2a_grad_scale, identity_overlap -- each torn
down and reinstalled around the candidate-scoring window) against the
scene's fully-finalized conditioning. Any failure in the value
function, schedule, or the isolation cycle itself degrades to a
silent no-op, declared in the run report, never a crash.
Also hardens _install_context_windows/_install_v2a_scale to roll back
partial state on failure (a leaked context_handler key was silently
re-enabling windowing for later scenes) and fixes the original
non-explore v2a install call site to degrade like its sibling
mechanisms instead of aborting the render.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Corrected the actual design: encode two FULL conditionings ($style
SHORTCUT1 $postfix and $style SHORTCUT2 $postfix) and average them row by
row -- (1-strength)*A + strength*B per position, strength=0.5 giving
exactly (A+B)/2 as originally specified. The prior mean-vector version
collapsed phraseB's whole sentence into one flat direction applied
identically everywhere, discarding its own word-by-word content.
Resamples the shorter side (linear interpolation along the token axis)
when the two shortcuts tokenize to different lengths, so both sides line
up for the average without changing the output's token count.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Confirmed on the rental: the previous version (phrase-scoped shift) showed
zero visible effect even at strength 1.5. Qwen's rows are contextual, so
every word in "a cat sits on a mat" already carries "sits", not just the
verb's own row -- editing 1-4 rows out of the sentence left the rest still
pointing at phraseA's action. Now shifts the whole prompt-token range toward
the alt sentence's own whole-prompt mean.
Multiple [a|b] spans in one prompt are additive: each span's delta is
measured against the original conditioning, not against a prior span's
already-shifted result, so they don't compound order-dependently.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Default 0.5 shift left phraseA dominating the video. [phraseA|phraseB:N]
overrides strength per blend. Fixed a shared regex gap along the way: every
weight/strength markup in this file (not just blend) silently rejected
leading-dot decimals like ".8" -- fell through to literal text with no
error, reproducing the exact "override did nothing" bug this feature exists
to fix.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
A real shortcut expanding to "wide shot: character walks" made [a|b]
never match at all, no error, because the previous fix banned ':' and
'@' anywhere in either phrase to stop one dangerous shape (an alt
phrase ending in ":1.5"). Two narrower shape-guards were tried and each
let a different shape through (colon-then-@, an em dash) while still
blocking ordinary prose. Reverted to fully permissive: a markup-shaped
alt phrase just reaches Qwen as literal punctuation in its own separate
re-encode, the same accepted trade-off this file already makes for a
weighted phrase's own stray parentheses -- a quality footnote, not a
leak, confirmed by tracing the encode path and its existing exception
handling.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Adversarial review of the previous commit found two real leaks and fixed
them: a colon in an alt phrase reached the real text encoder unstripped
(no bracket survives to re-catch it after substitution), and a wired
conditioning re-blended a second time because the re-tag guard only
checked for tag absence. Also reports per-span placement failures instead
of only counting successes.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Measurement only, opt-in from Settings > Refinement & Taste. Reading map is free
(attention share on the phrase's keys per block); response map costs one extra
forward per phrase per model call. Phrases are numbered, never quoted.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
A latent unsharp on H3's 24-channel latent does not translate to picture
sharpness. Wrong mechanism, not wrong number; removed rather than tuned.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
The parser existed but nothing called it; the syntax went to Qwen as text.
One pass strips both markups so timed and weighted spans share one clean text;
both encode paths carry them.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
The editor strips the brackets before the encoding node sees them and hands the
windows to Studio as char spans on the text it gave that node.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
