Follow-ups
AuraScore 83/100

Virtual Staging Prompt Calibration Protocol

Organizes lighting, texture, and architectural token discrepancies into a post-rendering client decision matrix.

Use this template after delivering synthetic 3D virtual staging or architectural renders when client feedback requires precise clarification on diffusion conditioning tokens, camera angles, and materials.

Template

Role: Synthetic Visual Effects Supervisor specializing in diffusion-based architectural staging and spatial prompts.

Context

  • Project Reference Code: {{project_code}}
  • Lead Interior Architect: {{lead_designer}}
  • Environment Lighting Profile: {{lighting_profile}}
  • Identified Diffusion Artifacts: {{unresolved_artifacts}}
  • Conditioning Pipeline: {{diffusion_pipeline}}
  • Delivery Stage Milestone: {{approval_milestone}}

Task

Produce a precise follow-up email and prompt parameter calibration matrix addressed to {{lead_designer}}, clarifying subjective spatial adjustments to eliminate {{unresolved_artifacts}} within {{diffusion_pipeline}} before reaching {{approval_milestone}}.

Method

  1. Deconstruct the initial render feedback for {{project_code}} into material, geometry, and lighting categories.
  2. Cross-reference requested scene modifications against {{lighting_profile}} to maintain photometric realism.
  3. Evaluate how ControlNet depths, segmentations, and text prompts interact within {{diffusion_pipeline}}.
  4. Translate aesthetic preferences regarding textures and furniture placement into explicit prompt syntax and conditioning weights.
  5. Highlight potential trade-offs where specific style requests might reintroduce {{unresolved_artifacts}}.
  6. Assemble the recommendations into an architectural prompt calibration matrix.
  7. Draft an email articulating required client selections to lock the scene prior to final upscaling.

Constraints

  • MUST present options in a structured decision matrix with explicit trade-offs for each prompt variation.
  • MUST NOT recommend manual 3D remodeling where conditioning prompt adjustments suffice.
  • MUST explicitly categorize visual changes by Prompt Keyword, ControlNet Weight, and Denoising Strength.
  • Language must remain accessible to non-technical interior designers while preserving prompt precision.

Output format

  • Staging Status Summary (1 concise opening section)
  • Prompt Calibration Matrix (5 columns: Scene Zone | Client Aesthetic Request | Recommended Prompt Syntax | Conditioning Weights | Photometric Risk)
  • Immediate Sign-Off Actions (3 bullet points tailored to {{approval_milestone}})

Self-review

  • Checks that lighting terminology aligns precisely with {{lighting_profile}}.
  • Confirms denoising and ControlNet ranges are technically viable for {{diffusion_pipeline}}.
  • Verifies that all 6 template variables are incorporated into the generated text.
AuraScore breakdown
83/100Provisional
Instruction clarity15/15 · Strong

Explicit role, a named task, and discrete steps the model can follow.

Context architecture12/12 · Strong

Background, inputs and variables the model needs before it starts.

Constraint engineering12/12 · Strong

Hard boundaries — what the model must and must not do.

Output specification6/14 · Thin

A named, field-level shape for the response.

Reasoning structure10/10 · Strong

Ordered work items that force analysis before an answer.

Model compatibility10/10 · Strong

Length and structure that travel across frontier models.

Token efficiency7/10 · Adequate

Signal density — instruction weight without padding.

Reusability7/7 · Strong

Documented variables so the scaffold adapts to new inputs.

Robustness3/5 · Adequate

Quality bar, assumptions and behaviour when inputs are thin.

Observed performance1/5 · Thin

How much real usage the template has behind it.

emails
emails-follow-ups
image-multimodal-prompting
virtual-staging
controlnet
prompt-engineering