Visual Qa
Outcome
Find visible and technical failures that single-view or file-only validation misses.
Required inputs
- asset, scene, or build under review
- reference target and acceptance criteria
- representative cameras, states, platforms, and budgets
Ask for missing information only when it changes the route materially. Otherwise
state conservative assumptions and proceed with read-only analysis.
Workflow
- Confirm the comparison baseline, capture settings, color pipeline, cameras, states, and tolerances.
- Capture consistent front, side, rear, three-quarter, close-up, silhouette, wireframe, and motion views as applicable.
- Compare against references and prior approved artifacts without hiding uncertainty behind a single similarity score.
- Inspect temporal stability, animation contacts, particles, lighting, UI states, and transition frames.
- Run engine import and representative runtime captures, then classify findings by severity and reproducibility.
Expected artifacts
- capture manifest
- annotated contact sheet
- temporal review
- runtime metrics
- reproducible findings
Workflow-specific gates
- Control resolution, camera, lighting, exposure, pose, animation time, and platform before comparing images.
- Review transparent assets over light, dark, and checkerboard backgrounds.
- A visual pass never overrides license, format, performance, playability, or human-approval gates.
Production completion gate
Before recommending production use, complete and report all seven gates:
- Rights, consent, code/model/dataset/output license, and generation-provenance checks.
- Technical format, naming, scale, color, metadata, and target-import validation.
- Visual and temporal consistency review across representative views and states.
- Runtime memory, frame-time, draw-call, streaming, and asset-budget checks.
- Playability and interaction smoke tests in the target runtime.
- Screenshot, capture, diff, or artifact-regression evidence with reproducible settings.
- Human approval before replacing source assets or promoting generated output.
Unknown rights, missing consent, unsupported hardware, conflicting host adapters,
or failed quality gates block production promotion. Preserve originals and make
fallbacks explicit.
1---2name: visual-qa3description: Run evidence-based multi-view visual, temporal, import, and runtime checks for generated game assets and scenes.4---56# Visual Qa78## Outcome910Find visible and technical failures that single-view or file-only validation misses.1112## Required inputs1314- asset, scene, or build under review15- reference target and acceptance criteria16- representative cameras, states, platforms, and budgets1718Ask for missing information only when it changes the route materially. Otherwise19state conservative assumptions and proceed with read-only analysis.2021## Workflow22231. Confirm the comparison baseline, capture settings, color pipeline, cameras, states, and tolerances.242. Capture consistent front, side, rear, three-quarter, close-up, silhouette, wireframe, and motion views as applicable.253. Compare against references and prior approved artifacts without hiding uncertainty behind a single similarity score.264. Inspect temporal stability, animation contacts, particles, lighting, UI states, and transition frames.275. Run engine import and representative runtime captures, then classify findings by severity and reproducibility.2829## Expected artifacts3031- capture manifest32- annotated contact sheet33- temporal review34- runtime metrics35- reproducible findings3637## Workflow-specific gates3839- Control resolution, camera, lighting, exposure, pose, animation time, and platform before comparing images.40- Review transparent assets over light, dark, and checkerboard backgrounds.41- A visual pass never overrides license, format, performance, playability, or human-approval gates.4243## Production completion gate4445Before recommending production use, complete and report all seven gates:46471. Rights, consent, code/model/dataset/output license, and generation-provenance checks.482. Technical format, naming, scale, color, metadata, and target-import validation.493. Visual and temporal consistency review across representative views and states.504. Runtime memory, frame-time, draw-call, streaming, and asset-budget checks.515. Playability and interaction smoke tests in the target runtime.526. Screenshot, capture, diff, or artifact-regression evidence with reproducible settings.537. Human approval before replacing source assets or promoting generated output.5455Unknown rights, missing consent, unsupported hardware, conflicting host adapters,56or failed quality gates block production promotion. Preserve originals and make57fallbacks explicit.
frabcd