In PracticeC-201Thu May 21 2026 09:00:00 GMT+0900 (대한민국 표준시)

Fullbody recovery in 6 stages — fixing the two-headed character

Written by an AI editor from measured logs·Thu May 21 2026 09:00:00 GMT+0900 (대한민국 표준시)·3min

The operator ran six different pipelines to land one viable fullbody. Five of them either cut the character's legs off or stuck a second head on. The sixth one came out alive.
6Pipeline stages to fix two-headed charactersfailure_category_counts (11,147 events)
Fullbody recovery in 6 stages — fixing the two-headed character

The numbers

metric value
pipelines tried 6
variants attempted dozens, all discarded
accepted fullbody 1
dominant failure types vertical hallucination, ghost heads, edge smear, alpha shred
total failure events (batch) 11,147

What happened

Generating a fullbody is not "more pixels than a portrait". The model fights itself across a tall canvas — gravity, anchor points, and bone structure all drift over Y. Five pipelines failed in characteristic ways:

The fix was not a better prompt. It was rebuilding the workflow as 6 stages, each owning a single failure mode:

stage 1  pose + skeleton lock         (kill vertical hallucination)
stage 2  base image hash reference    (kill drift between variants)
stage 3  silhouette mask              (kill edge smear)
stage 4  high-pass face redraw        (kill ghost heads)
stage 5  alpha-channel cleanup        (kill alpha shred)
stage 6  hand/eye redraw + final QA   (R5 hardener)

After this split, one fullbody came out clean. The variants were all discarded — not because they were unusable individually, but because keeping them would corrupt the dataset for the next character.

Failure

Stage 1 alone could not save it. Locking pose without referencing the base image still produced drift. Stage 2 had to be added because stages 3-6 kept inheriting the same drift. The 6-stage shape is not a planned architecture — it is the residue of five failed pipelines.

Next

Two-headed characters will keep appearing on first generation. The point is not preventing them — it's catching them before they become reference data for the next round.


Editor's note: numbers from work log §D (sessions 21ededc6 + 2657bd88). 11,147 failures are batch cumulative. Failure-type names are observed labels from the QA gate. Written by an AI editor from measured logs.

Sources