You are given an image-generation prompt, the labelled REFERENCE
image(s) that were attached to it, and ONE photograph generated
from them (the current best pick of {count_word_lower}).

EDITING IS NOT FREE AND NOT LOCAL. The image model redraws the whole
frame from your instruction. Measured on this pipeline: asking it to
remove one stray foot changed the clothing of corpses elsewhere in
the frame; asking it to restore a fuel hose put the hose across a
phone screen; asking for a colder smile erased the character's eyes;
asking to fix a face invented a skull in a background tree. So the
default is to leave the picture alone, and every issue you raise has
to earn its place.

List what is WRONG with it — ONLY violations of the prompt or of
its reference instructions: the shot's stated moment and action,
who/what must or must NOT be in frame, camera framing and shot
scale as the shot text states them, time of day, location
consistency with the reference, pose/immobility and carried-state
clauses, object orientation, anatomy, and every exclusion (no
text, no invented people or objects).

Rate every issue in `severity`:
  critical — a viewer cannot miss it and it breaks the shot: the
             wrong person entirely (wrong sex, or wrong apparent
             ethnicity where the prompt fixes it), a duplicated or
             floating body part, an object hovering with no hand or
             support, a duplicated control surface, a person in the
             wrong seat, an impossible reflection, a named object
             that is the wrong object, or a drawn line/arrow/marker
             surviving into the photograph.
  major    — a real miss a careful viewer would notice, but the
             still still reads correctly.
  minor    — detail, texture, small continuity.

FRAMING SCOPE RULE: judge pose/immobility, wardrobe and
carried-state clauses ONLY within what the photograph's framing
shows. If the framing (as the shot text states it) excludes a body
part, garment or carried item, its absence is NOT an issue — do
not flag it, and NEVER propose a fix that widens, reframes or adds
elements the framing excludes. Fixes must preserve the existing
framing exactly.

Base every finding only on what is visible; ignore taste and
generic aesthetics. For each issue give: issue_ko (short Korean
line) + fix_en (ONE imperative English edit that fixes exactly
that while changing nothing else). Empty array if nothing wrong.

FIX FEASIBILITY: fix_en must be an edit the current photograph can
absorb IN PLACE — keep the existing camera position, view direction
and overall geometry. If repairing an issue would require moving the
camera, changing the viewpoint, reversing a slope or stair direction,
changing who sits where, or otherwise re-photographing the scene from
another position, do NOT write such an instruction: set
"needs_regeneration": true on that issue so the caller can shoot it
again instead, and keep fix_en as the smallest in-place mitigation.
Set "unfixable": true when neither an edit nor a reshoot can help.
Never instruct the editor to relocate the camera or rebuild the
scene's geometry.

WRITING A FIX THAT SURVIVES THE REDRAW:
  - Name only the issues you rated critical. Leave major and minor
    ones in the list for the record, but do not put them in fix_en.
  - End fix_en with an explicit preservation clause that lists, by
    name, what in THIS photograph must not change: the people
    present and their positions, their clothing, the set, the light,
    the framing. A fix without that clause is how a corpse changes
    outfit.
  - When you forbid something from appearing, also say what occupies
    that space instead. A bare prohibition tends to be ignored; a
    positive description of the same area is followed.
  - Where a prop's quantity, grade or denomination is what makes the
    moment read, say what it has to be, in the terms of the era and
    place the prompt establishes. Given only a category, the image
    model reaches for the most ordinary member of it.
  - But do NOT ask for a specific number or word to appear legibly on a
    prop's surface. Measured on this pipeline: told to render a
    50,000-won note, the image model printed "500" and "10" on it, and
    told to leave the notes blank it printed "1000". The model does not
    render exact figures or lettering to instruction. When a prop's
    printed face would give the fault away, stage that face out of the
    reading: a hand across it, the bundle fanned so only edges show,
    the reverse turned to camera, or the surface too oblique and too
    shallow in focus to resolve. Say which of those the frame uses.