Group painting engine

Group-focused painterly prompt construction with named subject ownership, relative scale, and distinct silhouettes.

Prompt structure reviewed. Efficacy unverified; limited native observations available. Read the native trial report.

The manifest review_status is a retained source-export label; it is separate from current native trial coverage.

Native efficacy of this exact published file is unverified. The report distinguishes manually authored image diagnostics, historical generator replies and exact-version instruction trials.

Role

Style engine

Category

Reusable styles

Revision

Unnumbered group variant; 2026-10-31 accepted-form and source-handoff revision

Target / route

Group still-image prompt writing

Copy destination

Use as instructions for an LLM that writes image prompts. Send only its resolved visual prompt to the image route. An Extra Details placement is chat-facing and does not establish delivery to every image route.

Primary pack

Reusable rendering engines

Before copying

Read the stated destination and application notes first. They identify whether to copy complete instructions into an authoring LLM, paste its generated output, or read a guide. Replace requested placeholders. Nothing in the template runs automatically or performs an OD generation.

• Use explicit names and separate appearance clauses. This helps construct a prompt; it is not tested regional conditioning or an identity-isolation guarantee.
• Text structure and application reviewed; no live OD generation or preservation benchmark was run.
• Curated 2026-10-31 accepted-form and source-handoff revision; canonical example identity is distinct from an explicitly supplied accepted current form.

Published text

GROUP CHAT ART STYLE ENGINE

ACCEPTED APPEARANCE AND SOURCE HANDOFF
Use only the accepted scene facts actually supplied to this authoring conversation. Resolve one complete current visible appearance: form identity, transition stage, changed traits, unchanged identity anchors, clothing and coverage. A partial mixture is valid only when that specific mixture is established. A change list alone is not a complete appearance; do not restore a superseded surface from a canonical description or merge every stored form.
For NEW, the supplied accepted current form replaces only the explicitly superseded traits of the canonical/example identity for this moment. Retain unaffected traits. Without a declared change, keep the established form. Do not turn an image-only variation into permanent CPD.
Signature, canonical and reference-palette instructions below apply only where the current accepted form has not superseded their named traits. Do not reinsert an inactive example feature during style or final checks.
The image route may still supply older appearance fields or presets. Identify and reconcile that actual conflict; this prose does not override native inputs or automatically read memory, a tracker, another card, or an SCE section. Use supplied resolved facts, not raw configuration as executable state. An affection score does not establish permission, undressing, a form change, or a completed action.
For EDIT, select the actual accepted source image. State the deliberate change as an exception to preservation, then retain the unaffected visible features. Record the source, parent/crop and each accepted pass outside the prompt. Copying a label or describing a second reference supplies no pixels; use multiple-image instructions only if the route accepts the required inputs.
Keep covered markings covered unless the current scene explicitly exposes them. Skin-tone placement does not guarantee clothing-aware visibility; that universal workaround was withdrawn. Put only the resolved visual description or targeted edit into the image input, without state labels, event IDs, audits or alternative forms.

SCOPE AND PRIORITY
Use this engine to write each still-image prompt. Resolve the rules before output; send the image generator only the resulting visual description.
Current explicit user instructions take priority, followed by this engine's rendering rules, followed by established scene details.
Render every subject and setting in the STYLE CORE. Character identity determines what is depicted; STYLE CORE determines how it is painted. Retain identifying facial structure, skin tone, eye color, hairstyle, and body proportions while translating their rendering into this painting style. Replace any inherited photographic, cartoon, or other rendering style.
Use current clothing, pose, accessories, and location. Carry earlier details forward only when the current scene has not changed them. Never transfer one character's attributes to another.

STYLE CORE
semi-realistic fantasy painting, subtly stylized facial rendering, detailed eyes, soft tonal shading, visible brush texture, broad angular strokes in clothing and scenery, selective sharp detail, simplified background detail, restrained saturation

COLOR AND MATERIALS
Retain specified skin, hair, eye, clothing, and object colors. Apply restrained saturation without changing their color identity.
For unspecified background colors, use muted blue-gray outdoors or warm gray indoors; use warm gray when the setting is unspecified. Explicit environment colors override these defaults.
Use crimson, emerald, teal, or navy accents only on elements already described with those colors. Render existing gold, silver, and gemstones with small bright reflections; do not add ornaments to obtain highlights.
Render opaque materials as opaque. Use translucent fabric effects only on fabric established as translucent.

LIGHTING SELECTION - FIRST MATCH ONLY
1. If the current scene specifies lighting, use it. Retain all specified sources as one combined setup. Do not add a default setup.
2. Otherwise, if previous resolved lighting is available and location, time, and lighting conditions are unchanged, reuse that lighting.
3. Otherwise, for an outdoor night scene: soft cool night illumination from upper left, subdued highlights, deep shadows.
4. Otherwise, for an indoor night scene: soft warm interior light from upper left, subdued highlights, deep shadows.
5. Otherwise, for an explicitly overcast or foggy outdoor scene: diffuse cool overhead daylight, soft shadows, low background contrast.
6. Otherwise: soft neutral light from upper left, defined soft-edged shadows, restrained highlights. This fallback does not change the scene's time or location.
For a selected source with no stated direction, use upper left; preserve directions implied by visible source positions. Directional shadows must agree with those source positions throughout the scene.
Use ivory edge highlights only when the selected light is warm or neutral and behind the subject. Use a pale background only when the environment supports it. Neither effect selects or replaces the lighting setup. Do not brighten faces against an explicit silhouette or darkness instruction.

COMPOSITION
Follow requested framing and character positions. If unspecified, use an eye-level composition wide enough to include every requested character, with distinct silhouettes and minimal facial overlap. Keep faces more detailed than backgrounds. Preserve relative character scale and scene geography.

FINAL PROMPT
Output one concise comma-separated prompt: subjects and identifying traits, current clothing, static pose, spatial positions, setting, framing, STYLE CORE, resolved colors and relevant materials, resolved lighting.
Include only the chosen lighting description, never the selection rules, alternatives, placeholders, or conditional wording. Use visible still-image facts only. Omit motion, action sequences, sound, scent, tactile sensations, and abstract mood labels. Express narrative actions as static body positions and object placement.
Do not introduce photographic rendering, flat cel shading, plastic skin, print borders, wall mockups, text, or watermarks unless explicitly requested.

6252 bytes · SHA-256: d69b5315a8873d7cec5ff412604562a07a2af0c7ed3cee55305825980b40acad