Bỏ qua tới nội dung
TakoAPI
Quay lại kỹ năng

vtl-image-analysis

bởi rusparrish

Image & Video Generation
221Lượt tải do clawskills.sh công bố
0Lượt xem
0 lượt thíchĐăng nhập để thích kỹ năng này
—Chưa có đánh giá
Đánh giá của bạn

Tóm tắt

Measure compositional structure in AI-generated images using the Visual Thinking Lens (VTL) framework.

Mô tả

Kỹ năng này làm gì

Measures compositional structure in AI-generated images using the Visual Thinking Lens (VTL) framework. Detects patterns like center lock, radial collapse, and low tension that indicate default-mode model behavior. When patterns are found, generates alternative prompts targeting specific compositional issues.

Uses deterministic metric coordinates instead of subjective feedback, so compositional diagnosis is repeatable and not influenced by the model's priors.

Khi nào nên dùng

  • Diagnosing why a generated image looks generic or flat
  • Getting re-prompt variants after a center-locked image output
  • Checking visual tension and void distribution in AI art
  • Iterating on prompts that consistently produce similar layouts
  • Validating compositional quality before finalizing a generated image

Quy trình ví dụ

ĐẦU VÀO

User asks: 'Why does this image look so bland and centered?'

AGENT
  1. 1

    Run vtl_probe.py on the image to extract compositional metrics

  2. 2

    Check valid and mask_status fields; halt and report failure if either fails

  3. 3

    Report the five VTL coordinates and any flags detected

  4. 4

    Run vtl_regen.py with the original prompt and metrics to generate re-prompts

  5. 5

    Present the selected prompt variant as the primary recommendation with alternatives

ĐẦU RA

VTL coordinates showing CENTER_LOCK flag, plus up to 3 revised prompt variants targeting off-center placement and increased tension

Cài đặt

clawhub install rusparrish/vtl-image-analysis

Chạy lệnh CLI, hoặc dán prompt vào Claude Code, Cursor, Codex hay coding agent bạn đang dùng.

Liên kết