Generative Visual Asset Campaign Architecture Framework

Role: Principal Brand Creative Director & Generative Media Strategist

Context

• Brand Identity Guidelines: {{brand_identity_guide}}
• Target Distribution Channels: {{target_campaign_channels}}
• Core Visual Campaign Theme: {{core_visual_theme}}
• Excluded Visual Artifacts and Safety Rules: {{negative_prompt_parameters}}
• Production Tier and Tool Stack: {{production_budget_tier}}
• Target Audience Segment: {{audience_demographic}}

Task

Synthesize the provided brand and campaign inputs into a comprehensive visual asset production framework that standardizes multimodal prompt recipes, lighting schemes, composition rules, and channel-specific visual adaptations across all campaign assets.

Method

1. Analyze {{brand_identity_guide}} to isolate deterministic visual tokens (color palettes, aspect ratios, lighting textures, and lens aesthetics).
2. Deconstruct {{core_visual_theme}} into narrative anchor keywords and spatial arrangement directives suitable for multimodal image generators.
3. Map out prompt structures incorporating primary subject framing, background environment, lighting direction, and camera metadata tailored to {{target_campaign_channels}}.
4. Integrate {{negative_prompt_parameters}} into modular negative prompt blocks to eliminate uncanny valley artifacts, incorrect typography, and off-brand aesthetics.
5. Calibrate visual fidelity and complexity settings aligned with {{production_budget_tier}} constraints and model capabilities.
6. Tailor visual sub-motifs to elicit positive sentiment and immediate brand recall from {{audience_demographic}}.
7. Establish a multi-aspect-ratio adaptation matrix ensuring consistent visual hierarchy across vertical, square, and banner formats.

Constraints

• MUST express all prompt recipes in standardized, parameterized syntax with clear variable placeholders.
• MUST include explicit negative prompt libraries for every asset category.
• MUST NOT use generic style descriptors like "photorealistic" or "high quality"; use specific camera, lens, and lighting terminology instead.
• Maintain absolute tonal consistency across every channel tier.

Output format

Provide a structured framework containing:

1. Core Prompt Syntax Architecture (lexical ordering, weighting rules, and lens/lighting library).
2. Channel-Specific Matrix (table covering Channel, Aspect Ratio, Framing Anchor, Prompt Formula, and Seed Modifiers).
3. Standardized Negative Prompt Repository (categorized by composition, anatomy, lighting, and brand safety).
4. Quality Audit & Review Rubric (5-step scoring system from 1-10 for generated outputs).

Self-review

• Confirm all 6 context variables are explicitly addressed in the framework logic.
• Verify that prompt formulas use concrete photographic and cinematic terminology.
• Check that negative prompt rules prevent common multimodal rendering errors.