Kevin Gilper
f7061c7057
Traced the real provenance (Kevin's Codex dev sessions) and verified the
mechanism against the Krea 2 model on the render box. Two earlier claims
(07d2f0b) were wrong and are now fixed across the docs:
1. Mechanism: the 12 "deepstack chunks" are the 12 TEXT-encoder layer taps
Krea 2 conditions on (comfy/text_encoders/krea2.py: hidden_states
[2,5,8,...,35], (B,12,seq,2560) flattened to 30720), NOT the 3 vision
deepstack taps (qwen3vl.py deepstack_visual_indexes=[5,11,17]) the name
implies. 30720 % 12 == 0, so the node's split lands on the taps and the
per-layer gains do apply (no fallback) - confirmed from the model weights
(txtfusion.projector [1,12], layerwise blocks at 2560).
2. Provenance: the 12 values were NOT derived by a per-chunk sweep. They
were adopted from the third-party ComfyUI-ConditioningKrea2Rebalance node
(DEFAULT_WEIGHTS spike 8>10>7, matching STYLE_LAYER_PULL) plus the
shallow=structure/deep=appearance principle; only the scalar shape (0.45
->0.35) and cap (->0.9) were empirically tuned. The four role tables are
scalings of one template, so their agreement is design self-consistency,
not independent measurement - the "convergent evidence" framing is
withdrawn.
docs/deepstack-layers/ rewritten to separate verified mechanism, traced
provenance, and the still-unrun single-tap sweep. Corrections propagated to
the V9 technical paper (5.2 + architecture note + glossary), the V10 guide
and companion, custom_recipes/README, the V10 node doc, and CHANGELOG. Full
evidence chain preserved in local_records (gitignored).
2.1 KiB
Scoring the deepstack sweep
After generate_sweep.py --server ... renders the grid, score every spike
render against the control (<ref>__sweep-control.png) to determine what
each chunk carries. The control and the spike share prompt, seed, reference,
strength, pooled channel, and all other chunks - so any visible difference is
attributable to the spiked chunk alone.
Procedure
For each reference (subject, palette) and each chunk L:
-
Open
<ref>__sweep-control.pngand<ref>__sweep-chunk-LL-gain-4.pngside by side. -
Judge which single aspect changed most relative to the control, and how strongly (none / subtle / clear / dominant):
Aspect What to look for structure subject shape, pose, layout, spatial composition shifting toward the reference palette overall color cast, hue relationships moving toward the reference texture surface/material grain, finish, micro-detail lighting light direction, contrast, glow, shadow, mood (none) no meaningful change from control -
Record:
chunk L -> <aspect> (<strength>). If two aspects move together, record both with the dominant one first.
Recording
Fill the verdict table in README.md - one row per chunk, with the verdict from each reference and a consensus column. A determination is "solidified" when:
- both references agree on each chunk's dominant aspect, and
- the measured structure->transition->appearance ordering matches the tables' design prediction (taps 0-4 structure, 5-6 transition, 7/8/10 appearance with 8 strongest), OR any disagreement is documented with its consequence for the tables (a mismatch means the borrowed template does not match Krea 2's actual per-tap response).
If a scoring pass is done by an agent, have a second independent agent score the same grid blind and reconcile; note both in the record.
Optional: multi-level confirmation
Re-run with --gains 2 4 6 to confirm each chunk's response is monotonic in
gain (a real carrier gets stronger with a bigger spike; noise does not). Note
the gain at which each chunk's effect first becomes clearly visible.