SuperAPI AI Directory
Partner with us中文AI newsFavorites
Skillsimage-denoise-enhance

image-denoise-enhance

Design & creation

View repository

Updated 10-16 06:46

About this skill

Image denoising (image-denoise-enhance)

Overview

Remove image graininess/noise/speckles, preserving image detail while reducing noise. Covers noise reduction for high-sensitivity shooting, noise removal for low-light shooting, speckle repair for old photos, noise handling for phone night shots, and repair of color blocks/artifacts produced by compression. Only requires image_url, no prompt needed.

Before execution, the user should clearly know: this Skill will read Meitu credentials, call the local meitu CLI, send the user-provided image URL to Meitu OpenAPI for processing, and write the result to ./output/ or $VISUAL/output/image-denoise-enhance/。

API Mapping

  • Image denoising:image_denoise_enhance

Dependencies

  • meitu-cli: >=2.0.6（npm install -g meitu-cli@latest）
  • credentials：CONFIG AKSK → meitu tools update; EXEC AKSK → actual execution (see root CONFIG.md）
  • environment variables：MEITU_OPENAPI_TOOL_TASK_MODE=command

Path alias:$VISUAL = {OPENCLAW_HOME}/workspace/visual/

Core Workflow

Preflight → Execute → Deliver

Preflight

  1. meitu --version ≥ 2.0.6 (otherwise npm install -g meitu-cli@latest）
  2. confirm that meitu tools updatehas been run (using CONFIG AKSK)
  3. current AKSK = EXEC, and MEITU_OPENAPI_TOOL_TASK_MODE=command
  4. resolve output_dir: openclaw.yaml → ./output/ ｜else → $VISUAL/output/image-denoise-enhance/；mkdir -p

Execute

Trigger signals / routing rules

Scenario Judgment keywords Routing
Noise / grain / speckles denoise, noise, grain, speckles, dirty image, high ISO image_denoise_enhance

Decision order:

  1. image_url missing → ask follow-up
  2. Unique routing: call image_denoise_enhance

Single API tool: call it when parameters are complete; after 1 retry on failure return an error; no cross-tool fallback. If the image has no obvious noise, still call normally; the effect may be不明显.

Parameter definitions

Parameter Type Required Range Default Description
image_url STRING Yes -- -- Image address. If missing → prompt "Please provide the image to be denoised"

Tool invocation

meitu image-denoise-enhance \
  --skill_name skill_image-denoise-enhance \
  --image_url <image_url> \
  --json \
  --download-dir {output_dir}

Error degradation

Scenario Handling method
image_url missing Prompt "Please provide the image to be denoised"
image_url inaccessible Directly return invalid image link error, no retry
Image has no obvious noise Call normally, effect may be不明显, inform the user
image_denoise_enhance call failed Retry once, still failing return error
Content compliance interception Directly return compliance prompt, no retry
Video input Reject, only images supported

Deliver

  • Directly use the output_dir resolved by Preflight
  • From downloaded_files[0].saved_path read the downloaded file path
  • mv {downloaded_files[0].saved_path} {output_dir}/{YYYY-MM-DD}_{descriptive}_image-denoise-enhance.jpg

Output

  • Format: JPEG/PNG (keep original format)
  • Naming：{YYYY-MM-DD}_{descriptive}_image-denoise-enhance.jpg
  • Location: project → ./output/, one-time → $VISUAL/output/image-denoise-enhance/

Baseline Task ID

See references/task-id-baseline.md for the corresponding line.