Adds temporal_style='auto': Studio classifies each scene's prompt for motion
energy and bakes a continuous frame_rate multiplier into that scene's
conditioning metadata; the Scene Chain Sampler applies it per scene via a
layered model_function_wrapper (composes with embed guidance, restored in
install order). Concrete styles keep the global build_enhancements path
unchanged.
- ltx_enhancements: TEMPORAL_STYLES gains 'auto'; single-source TEMPORAL_STYLE_MULT
table; classify_temporal_intent() keyword director (energy->punchier mult<1,
stillness->hold mult>1, loop flag); factored make_temporal_wrapper() shared by
global + per-scene paths; build_enhancements skips the global wrapper for auto.
- conditioning: _v2_apply_auto_temporal() bakes funpack_temporal_mult/label/loop
into each entry inside the single finalize hook; both refine_v2 returns pass
temporal_style + the run prompt as per-scene fallback text. 'auto' added to V2
node dropdown.
- samplers: _scene_temporal_mult() reader + per-scene temporal wrapper around
_sample_chunk in the scene loop.
- web: 'auto' in the Studio dropdown + hint text.
Heuristic is the baseline director, structured so a reward-driven override can
replace the multiplier per intent-family later. loop's RoPE coordinate trick is
still unimplemented (inert flag only); auto detects loop intent but does not yet
honor it.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
clear_refinement_data() early-returned on an empty refinement_key, but a
keyless run stores its blessed/attn maps, creativity latent and velocity-bias
trajectories under the 'default' bucket. So a keyless Session Reset no-opped
and those disk-persisted stores survived restart too -- the first fresh run
felt cleaner than every later run. Normalize empty key to 'default' (matching
the write side) so reset actually wipes that bucket.
Also wire the keyless Absolute taste store (FUNPACK_ABSOLUTE_KEY) into reset:
it learns from every rated run regardless of steer_mode but had no clear path,
so it would survive reset + restart forever. Delete its state json + value fn
on reset_session.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Add guess_freeze_seed (default True) threaded refine_v2 -> _v2_pack_batch
-> _v2_pack_guess_ladder and the Studio refine_v2 call. Frozen = every rung
shares one seed (only conditioning strength varies; cleanest for learning).
Off = distinct seed per rung (varied compositions too). New "Freeze seed"
toggle in the Interactive Guessing config; persisted on Arm.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
UI: Batch Training tab gains Mode (Regular / Interactive Guessing),
Direction, Range, and a Learning toggle; Arm sets refiner.guess_* +
batch_learning; auto-disarm clears guess_mode; rating list shows each
rung's [x factor]; Submit passes the learn flag.
Learning (batch_training.py): submit honors learn=false (pure generation,
no training). Guess batches detected via guess_factor -> _learn_guess_ceiling
finds the furthest-pushed acceptable rung before quality broke and stores a
per-key safe ceiling (absolute spread + factor) via _store_guess_ceiling.
Dual auto-cap (refine_v2, normal runs only): soft pre-limit on
absolute_strength + hard clamp of the output conditioning's video-channel
spread to the learned-safe value in _v2_finalize_conditioning. Skipped
during the guessing ladder itself. Helpers conditioning_spread /
scale_conditioning_spread.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
New variant producer for Batch Training that, instead of seed/shortcut
variation, scales the conditioning's spread (sigma) on VIDEO channels by a
linear ramp across N rungs, freezing everything else including the noise
seed so the only variable is conditioning strength. Up amplifies toward
overbake, down dampens. Each rung records funpack_guess_factor (in cond
meta + batch manifest) so the ladder is interpretable and Phase-3 learning
can read each rung. Audio channels untouched (scale_conditioning_spread
reuses the LTXAV channel split). Wired refine_v2 -> _v2_pack_batch
(guess_mode branch -> _v2_pack_guess_ladder) and the Studio refine_v2 call
(guess_mode/direction/range from refiner settings).
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Reuse _normalize_video_denoised in _sample_const_rf_full (Hybrid CONST/RF
path) and sample_funpack_distilled_flow: new normalize_strength /
normalize_start_sigma (default 0 = off). Applied to the denoised after
rescue/quality-sharpness, video-only, so audio is never touched and the
samplers keep AB2/Heun/velocity/rescue. Wired node INPUT_TYPES (appended)
-> get_sampler -> Studio _build_one_sampler + JS panels for both.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
New SAMPLER for distilled LTXAV at CFG=1: deterministic 1st-order euler
base (clean ddim look + clean audio) plus per-step video-only latent
normalization to counter overbaking / oversaturation / colour drift at
~zero overhead. Tracks the video latent's robust spread, anchors a
reference once x0 is meaningful (normalize_start_sigma), and compresses
inflated later steps (normalize_strength). Benefit-only, no-op when
healthy, audio never touched (whole-latent for single-stream LTXV).
Velocity bias + rescue included, video-only.
Node FunPackNormalizingSampler + Studio sampler option ("Normalizing")
wired through _build_one_sampler and the JS panel. Registered in __init__.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Instead of full AB2 on every step, optionally ramp the AB2 contribution
linearly 0->1 across the schedule: denoised_eff = lerp(raw, ab2, i/(N-1)).
Early/high-sigma steps stay near 1st-order euler (less overshoot); late
steps get full AB2. Reuses the computed AB2 estimate -> no extra model
evals. Aimed at low-step distilled quality. No-op at order=1; audio still
rides plain euler. Wired node -> get_sampler -> Studio panel (+ JS toggle).
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
The conditioning-dim diagnostic logged once per process via _FUNPACK_AV_LOGGED,
so after the first generation it went silent — easy to read as "it never ran".
Fold the detected split into the per-run "Absolute steer applied" line so every
generation states whether audio is PROTECTED (video[:v] of D) or NOT split
(unrecognised width -> steering all channels, audio unprotected). Makes the
no-op case visible instead of silent.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
LTXAV splits one conditioning tensor into video|audio channel-slices
(av_model _prepare_context: torch.split(context,[v_dim,a_dim],-1)) and
cross-attends each stream to its own slice. Steering the whole tensor
corrupted the audio's text conditioning -> degraded audio (observed live).
Add protect_audio_channels: restore the audio channel-slice from the
unsteered conditioning so every edit moves video only. Applied at all
steering chokepoints:
- _v2_apply_conditioning_memory (per-prompt: liked/axis/concept/vf-grad)
- _v2_apply_absolute (global taste pull)
- _v2_ascend_conditioning (relative VF ascend+search)
- attn2 K/V direction patch + phrase emphasis
- FunPackConditioningAdjust (manual)
- sampler embed_guidance wrapper + per-scene VF ascend
Split auto-detected from width (7680->3840, 6144->4096); logs once.
Single-stream LTXV / unknown width = no-op (no regression).
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Relative (default, unchanged) = per-prompt steering. Absolute = a keyless,
prompt-agnostic "global taste" prior that pulls conditioning toward generally-
liked directions regardless of the prompt; Both layers them.
- New keyless Absolute store (FUNPACK_ABSOLUTE_KEY): pooled liked/disliked
direction + global value function, learned across every rated generation.
- Absolute rating semantics: a rating means "details I like in general" (not
prompt adherence) — reward-driven liked/bad-dir storage, axis attribution
bypassed. Perfect = "more of this everywhere".
- _v2_finalize_conditioning replaces the per-key ascend hook on both returns;
pure Absolute also bypasses per-prompt conditioning memory.
- Scene Chain sampler: embed_guidance_source (relative/absolute) lets the
per-step nudge draw from the global direction/value function.
- Studio popup + V2 node expose Steer mode + Absolute strength.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Adds s_churn/s_tmin/s_tmax to sample_funpack_distilled_flow: optionally
re-noise the latent within [s_tmin, s_tmax] before each eval, then denoise
from the bumped sigma_hat. No extra model calls (still one eval per step,
at a higher noise level). Fights stale/frozen distilled output (more motion)
and can sharpen by letting the model re-resolve. sigma_hat is clamped to the
schedule start so the model never sees a higher-than-trained noise level, the
final jump-to-zero detail step is never churned, and the default 0.5-1.0 band
protects the sub-0.4 detail finish per the empirical sigma findings.
Churn supersedes the legacy s_noise ancestral path while active and is
video-stream-only on packed LTXAV latents. With s_churn=0 the sampler is
byte-identical to the previous deterministic ODE. Wired into the node and
Studio's Distilled Flow config panel.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Port the Hybrid/RF velocity-bias capture/apply and rating-gated reactive
rescue into sample_funpack_distilled_flow, reusing the shared trajectory
memory helpers. Adds velocity_bias_mode/strength/source/key and
rescue_mode/threshold/strength to the FunPackDistilledFlowSampler node and
wires them into Studio's Distilled Flow config panel (same blank/'default'
velocity-key -> refinement-key fallback as Hybrid). Steering is
magnitude-preserving and, on packed LTXAV latents, video-stream only
(audio-safe). With all controls off the sampler is byte-identical to the
previous deterministic ODE.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Batch Training confirmed working end to end (controlled batch with transitions, distinct
per-variant seeds, node rating ignored during a batch, per-entry rating + VF/axis learning
on submit). Stripped the temporary trace prints (Batch Training check / Batch check / ACTUAL
scene seeds), keeping clean progress logs. Gitignore the local .testvenv.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
The live log showed the single-scene path: 'packed 3 variant conditioning(s)' with ACTUAL
scene_seeds identical across all 3 (all inherited the base entry's funpack_scene_seed). My
earlier seed fix only covered the multi-scene duplication path. When a prompt resolves to one
scene (common), _v2_build_batch_variants reused the base scene seed for every variant ->
identical noise -> identical videos (only tiny diffs from VF ascent).
Fix: _v2_pack_batch now assigns a fresh, well-spread per-variant scene seed (gen-seeded RNG,
reproducible, per-scene offset) to the packed entries in BOTH paths, after building them.
Verified in venv: single-scene 3 variants -> 3 distinct seeds.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
1) All batch videos identical: in the transition path each scene carries a
'funpack_scene_seed' the sampler honors over its own seed, so duplicating the scene-set
left every variant with the same seeds. _v2_pack_batch now assigns DISTINCT per-variant
scene seeds via a gen-seeded RNG (well-spread, reproducible per gen). Verified in venv:
4 variants -> 4 distinct seed sets, reproducible.
2) Ignore the node's rating widget while a batch generates: that selection would apply
learning to the PREVIOUS run, but it's stale during a batch (the batch is rated afterward
in the panel). When batch_variants>1, force rating to '-Just forget it-' (skip_learning),
so all learning paths (phrase/conditioning-memory update, VF training, velocity commit)
are skipped. Conditioning APPLICATION still runs (it has no skip_learning guard), so the
batch still uses the learned directions.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Root cause (found via the diagnostics + the venv tests): the producer was gated on
'not split_by_transitions', but the user's workflow is multi-scene chains, so with
transitions on the producer never ran -> no variant markers -> sampler did one pass.
Fix: defer variant packing to the FINAL conditioning, applied right before BOTH returns
(the transition early-return and the normal return), so it wraps whatever output ends up
being. New _v2_pack_batch dispatcher: single-scene output -> _v2_build_batch_variants
(shortcut variants); multi-scene output (transition split) -> duplicate the whole scene
set per variant (seed-only). Each variant tags ALL its scene entries with the same index,
so the sampler groups by marker into N full chains and keeps variants independent.
Verified in the test venv: 3-scene set x 4 -> 12 entries, markers [0,0,0,1,1,1,2,2,2,3,3,3]
-> sampler sees 4 groups of 3 scenes; a single-variant group returns None (chains normally,
no recursion). Marker detection + producer round-trip all green.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Prints (a) the batch_variants value + mode flags the refiner sees and how many packed
entries it produced, and (b) the positive entry count + variant markers + group count the
Chain Sampler sees. Pinpoints whether the break is the arm/settings (batch_variants==1 at
the refiner), the conditioning path (markers stripped before the sampler), or the split
logic. Temporary, to be removed once the cause is found.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Submit now does more than train the value function (3a). New refiner method
_v2_learn_from_batch feeds each rated entry's conditioning through the SAME per-axis
direction-memory machinery as a normal rated run (_v2_update_conditioning_memory →
axis directions + liked/bad direction stores), and tallies axis votes across the batch:
because tokens were frozen, an axis rated missing/wrong in >= half the rated entries is a
high-confidence problem (not seed luck). Those consistent axes are written to
active_repair_axes, which the next generation's repair persists until a Perfect — so a
batch where most gens were 'Missing details' makes the next run boost details.
Wiring: batch submit collects (rating, serialized cond) per rated entry, trains the VF,
then calls _v2_learn_from_batch; the resulting insight ('consistent problem axes = ...')
is returned and shown in the Studio submit toast. List route now also returns each item's
variant index + prompt for the panel.
Batch Training is now complete: seed-only + shortcut variants + node button + VF training
+ axis/direction learning, all human-rated.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Producer (Studio owns conditioning, per the boundary law): refine_v2 gains batch_variants.
When >1, _v2_build_batch_variants packs N conditioning entries into the single positive wire,
each tagged 'funpack_batch_variant'. Variant 0 is the fully-processed base; variants 1..N-1
re-resolve shortcuts with seed+i (random option per entry) and get the same conditioning-memory
treatment, deduped by expansion text. No shortcut variability -> all entries resolve identical
and reuse the base cond -> the batch becomes seed-only (sampler varies the seed per entry).
Captures the pre-shortcut prompt to re-resolve. Not combined with split_by_transitions.
Trigger: a 'Batch Training' button on the Studio NODE (next to Open Studio) — prompts for N,
sets refiner.batch_variants, queues one prompt, then auto-reverts to 1 (one-shot). Studio is
the batch trigger (hub principle); no sampler input needed.
Sampler: now enters batch mode when positive carries variant markers, even if batch_iterations
is 1 (markers are the trigger; variant count wins). Each entry already saves its own cond, so
Submit trains the VF per variant — teaching which prompt variant rated better. Panel hints now
point at the button.
End-to-end: press Batch Training -> N -> Studio makes N variant conds -> sampler samples N ->
previews to temp -> rate in Studio panel -> Submit trains VF per entry -> batch cleared.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Audit finding: value_guidance defaulted OFF, and it gated value-function TRAINING — so
by default the VF never trained, conditioning ascent + the chain sampler's embed_guidance
were permanently inert, and a user who ran many gens with it off then enabled it started
from zero (no accumulated learning).
Fix decouples learning from application:
- The VF now ALWAYS trains in the background on rated gens (cheap: small MLP, 20 steps,
no diffusion calls) whenever there's a rated previous run + refinement key. The reward
asset accumulates regardless of the toggle.
- value_guidance now controls only APPLICATION of the learned direction (output ascent +
search), via a new apply= param on _v2_ascend_conditioning. Default ON.
- Defaults flipped to True: refine_v2 signature, Studio settings read, JS default +
migration. Studio toggle relabeled 'Apply value guidance' with corrected help (training
always on; applies after 10+ ratings; off = strict prompt fidelity, learning still
accumulates). Fixed stale '5+ ratings' text (MIN_SAMPLES is 10).
Side effect: embed_guidance (chain sampler) now has a trained VF available by default.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Three issues found tracing the full Studio path with all features on:
1) BUG (silent data loss): a custom velocity_refinement_key captured trajectories
under that key but the refiner committed the rating under the effective refinement
key — so custom velocity keys never learned (banks stayed empty, rescue/velocity a
permanent no-op). This undercut per-key cut-routing. Fix: Studio resolves each pass's
velocity key (same logic as _build_one_sampler) and passes them to refine_v2, which
now commits the verdict to the union of {effective key} + velocity keys (dedup).
Backward compatible (callers without _velocity_keys behave as before).
2) Effectiveness: VELOCITY_BIAS_TARGETS (0.90, 0.80) matched only sigma~0.909 on the
standard 8-step LTX schedule, so rescue fired once per gen at a near-noise step and
never at the detail-forming sigmas. Broadened to (0.90, 0.72, 0.42) -> hits 0.909,
0.725, 0.422. Velocity APPLY still structure-only (highest target); rescue now acts
where runs actually go good/bad. (New detail targets fill as gens are rated.)
3) Redundant value: velocity_aspect_bucket was a manual text field never tied to actual
resolution, and the bank key already includes the full latent shape (which encodes
resolution) — so it was doubly redundant. Removed from the key, all sampler plumbing,
INPUT_TYPES, Studio build, and the JS UI/defaults. Persistence loads old stores fine
(the 'aspect' field is simply ignored; key is now (refkey, target, shape)).
Verified: both py files + JS parse clean; all refactored call signatures aligned.
Tests require the ComfyUI venv (torch) to run.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Compensate the slow quality degradation from velocity-bias 'apply' (additive
mean-pull) with four guards on the Hybrid Euler 2S sampler (both eps and
rectified-flow/LTXAV paths):
- B: apply is now magnitude-preserving — rotate x toward (x+delta) and
renormalize to |x| instead of x+delta, so no energy is injected.
- C: apply fires only at the highest (structure) velocity target and decays
strength with the sigma ratio; detail sigmas left untouched.
- E: new quality_sharpness knob — temporal-average unsharp on the x0 prediction
during the quality phase to restore high-frequency detail (free, no extra eval).
Default 0.0 (off).
- D: new velocity_bias_source = mean|nearest — 'nearest' steers toward the single
best-matching prompt cluster (one real good gen's detail) instead of the
washed-out average. Affects both apply and rescue. Default 'mean' (off).
Plumbed through get_sampler/INPUT_TYPES, Studio _build_one_sampler, and the
Studio JS sampler panel (both presets + UI controls).
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Root cause of "rescued toward an Awful gen": velocity capture was
rating-blind — it wrote every sampled trajectory straight into the one
"good" memory, so a fresh key whose only capture was an awful gen made that
awful run the sole steering target. Ratings (which live in the refiner) never
touched the bank.
Now:
- capture STAGES the current gen's trajectory (VELOCITY_BIAS_PENDING) instead
of committing it; staging runs whenever rescue is on (no separate capture
toggle needed).
- the refiner commits the previous gen's staged trajectory by its rating:
like/loved/nailed -> good bank, awful -> bad bank, everything else dropped.
- rescue steers TOWARD the good bank and AWAY from the bad bank (per prompt
cluster), firing when diverged from good OR aligned with bad beyond
threshold; no-op when neither bank has a prompt match.
- session reset / clear_refinement_data now clears good + bad + pending.
velocity-bias "apply" now also reads the rating-gated good bank. Tooltips and
Studio note updated.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
The velocity_refinement_key (namespace for trajectory capture + rescue
clusters) was a separate field defaulting to "default", easy to drift out
of sync with the refinement key Studio actually uses. Now when it is blank
or left at "default", Studio resolves it to the effective refinement key
(same resolution as seed memory / refine_v2), so capture and rescue share
one bucket automatically. An explicit non-default value is still respected.
JS hint added on the velocity key field.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Rescue previously steered toward a prompt-blind average of all captured
good trajectories, risking false positives that fight a legitimately
different prompt. Now the velocity memory keeps per-prompt clusters: each
tagged with a pooled+normalized conditioning signature. Capture merges into
the nearest cluster (cosine >= 0.92) or starts a new one (cap 8/key, evict
lowest-count). Rescue builds its reference from clusters similar to the
current prompt (cosine >= 0.5, >= 2 matched captures), similarity-weighted;
with no confident prompt match it skips rather than steering to the global
mean. Studio pools its positive conditioning into a signature and threads it
through _build_samplers -> get_sampler -> sampler extra_options. Standalone
node (no conditioning) falls back to the prior global-average behavior.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Studio builds its sampler via FunPackHybridEuler2SSampler.get_sampler but
did not pass the new rescue params. Thread rescue_mode/threshold/strength
through _build_one_sampler, add them to the Studio JS hybrid defaults
(high+low) and the sampler config panel, with a note that rescue needs the
velocity-bias memory captured first.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
New order: positive signals (broad→specific) → negative signals
(broad→specific) → delta cap → VF gate.
Concept-in-context delta moved before bad conditioning repulsion so
positive phrase signal isn't added after negatives are removed.
Pair repulsion stays last among negatives as most targeted.
VF final gate: after all patches + delta cap, if net effect lowered
VF predicted reward by >0.05, linearly roll back toward original
proportionally to how much worse it got (max 75% rollback). Visible
as vf-rollback:X.XX in axis adjustments.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
search() generates 16 random unit-direction perturbations (2.5% of
conditioning norm each), scores each with the VF, returns the best.
Runs after ascend() in _v2_ascend_conditioning — ascent exploits the
known gradient direction, search explores the neighbourhood around it
for any better nearby region. Total cost: 16 VF forward passes ≈ free.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Learns which phrase combinations in the final encoded prompt correlate with
anatomy/quality failures (reward < -0.10, wrong_appearance, wrong_action+quality).
For each pair of phrases (up to top 8) present in a bad generation, accumulates
the conditioning direction as a per-pair bad slot using the existing
_v2_store_direction mechanism.
At generation time: for each phrase pair in the current final prompt with ≥3
observations, applies a repulsion from the stored bad direction (max 3 pairs,
strength capped at 3.0% of conditioning norm). Visible in axis_actions as
pair-repulsion:N. Prunes to 200 pairs when exceeding 300.
Trigger includes wrong_appearance explicitly (reward=0.0 but signals anatomy
artifacts), missing quality, and all outcomes below -0.10 reward.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
The freeze locked prompt text to the previous Perfect output, overriding
intentional prompt changes when intent similarity stayed above 0.50. With
VF + conditioning memory maintaining quality direction, the freeze is no
longer needed and only causes unwanted video repetition.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Learns which phrases in the final encoded prompt (not intent, not raw input —
the actual text that went into CLIP) correlate with reward changes when added
or removed between consecutive generations.
Storage: concept_delta_memory per phrase text — add_sum/count, remove_sum/count.
Learning: on rating, diffs previous_run.final_phrase_texts vs prev_final_phrase_texts;
credits reward to added phrases, records it for removed.
Application: before conditioning memory is applied, computes a weighted direction
from phrase embeddings (via phrase_memory) for phrases new to this final prompt
that have ≥3 add observations and avg_reward > 0.10. Nudge capped at 3.5% of
conditioning norm alongside all other deltas.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Used refinement_key_input/refinement_key directly instead of eff_key
which is assigned ~340 lines later in refine_v2.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Two new VF-driven behaviours in _v2_apply_conditioning_memory:
1. Global confidence scalar — VF predicted reward scales all conditioning memory
modifications: confidence_scale = (vf_score+1)/2 clamped to [0.4, 1.0].
High score → full strength (direction is good). Low score → dampened
(be cautious, current conditioning direction looks bad). Applies regardless
of which prompt is active — purely VF-signal driven.
2. Gradient-aligned phrase boosting — VF gradient direction (∂reward/∂conditioning)
is computed and compared to each axis direction slot via cosine similarity.
Boost factor [0.5, 1.5] applied to direction strength: phrases/axes pointing
with the reward gradient are amplified, those pointing against are dampened.
Applies to liked_dir, missing axis repair, and satisfied axis preserve.
VF score and boost factors visible in adaptation status output.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Attention weight accumulation:
- Capture per-token output norm at identity blocks [14,20,21,30,33] during every
generation via the optimized_attention patch (same path as temperature)
- EMA-merge into blessed file on liked ratings (0.8 old + 0.2 new)
- Inject as V-scaling bias on future runs: important tokens get amplified V,
pushing attention toward historically attended positions
- Temp/blessed files cleared on session reset
VF-driven temperature:
- build_enhancements accepts conditioning=None, loads value function, scores it
- _derive_temperature_map(vf_score=) continuously modulates block temperatures:
high VF score → sharpen (0.80×), low → warm/explore (1.20×), regardless of rating
- Rating-driven temperature still applies when reward < 0.8; VF blends with it
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
LTX packs all spatial/temporal dims into a single token [1, 1, C*T*H*W]
during sampling. Per-step latent steering requires hooking into the model
internals, not the k-diffusion callback. Removed: compress_latent(),
_load_latent_value_function(), latent VF training, motion floor callback,
latent_value_guidance toggle in Studio.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
OUTPUT_NODE = True forces ComfyUI to run the node even with no downstream
connection on the LATENT output. Motion floor now activates as soon as
embed_guidance is on and a refinement key is set, independent of liked_dir.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Trains a second OnlineValueFunction on rated video latents (compressed via
channel mean-pool). At each denoising step, computes ∂reward/∂latent through
the lightweight MLP and applies it as an in-place drift to the noisy latent —
gradients never touch the 22B transformer. Controlled by embed_guidance_strength
alongside the existing conditioning guidance. Studio toggle: "Latent guidance".
Cleared on session reset alongside the conditioning VF.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Heart modifier now applies full axis pressure (not 50% softened) — meaning
"fix this specific issue but the quality direction was great." The quality
signal comes from boosted reward and conditioning delta, not from reducing
axis pressure. Nailed it + heart removed (that's just Perfect). Positive
grid changed to 1fr 1fr to fill width with 2 items.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
The ♥ button on any rating covers the same semantic. Removed from picker
UI and V2_RATING_LABELS; profile kept in Python for backward compat.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
ComfyUI rejects widget values not in the allowed list. Generate all
valid label|loved combinations at definition time.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Any rating can now be combined with a "Loved it" toggle. The suffix |loved
is appended to the rating string and parsed in normalize_refiner_v2_rating.
When active: reward boosted to max(base, 0.85), axis pressure softened 50%,
conditioning direction delta raised to 0.45, preferred context applied at
0.30 base_delta. Disabled for Perfect (redundant) and -Just forget it-.
Button label shows ♥ when modifier is active.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Replaces the rating dropdown on Studio and Refiner V2 nodes with a button
that opens a categorized floating picker. Each option shows its reward value
and a one-line hint. Rating auto-resets to -Just forget it- after execution
so forgotten ratings don't silently apply to the next run.
Also adds Wrong action + quality (reward -0.40, wrong_axes action, missing
quality) and drops Wrong action reward from +0.10 to -0.10.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Restores the old "Loved it" learning behavior (reward 0.75, intent delta
+0.03, preferred context 0.65, axis conditioning 0.35, LoRA 0.44/0.24)
as a distinct rating. Sits between Perfect and Loved it on the ladder:
prompt adherence is rewarded but not at full strength.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Previously a weaker "Perfect". Now means: output looks great, prompt
adherence is irrelevant. Skips missing_intent_phrases learning, skips
preferred context lock-in, zeroes intent phrase reinforcement. Keeps
conditioning direction delta and raises value function reward to 0.85.
Quality/style LoRAs rewarded at Perfect level (0.55x).
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
torch.load under inference_mode creates inference tensors; MLP params then
can't participate in backward. Same fix as the earlier value function loader
in samplers.py.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
reset_session now deletes the value function .pt file alongside the
enhancement files. Previously it was orphaned across resets.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Before returning modified_positive, ascend each scene's conditioning tensor
toward higher predicted reward via the value function. Covers both the
standalone Refiner V2 node and FunPack Studio (which delegates to refine_v2).
No-op until value function reaches MIN_SAMPLES; handles transition-split
multi-scene conditioning correctly.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
