SuperAPI AI Directory

image-poster-generate

Design & creation

View repository

Updated 10-16 06:46

About this skill

Image Poster Generate

Overview

Text/image-to-poster, multi-style, multi-size, supports poster editing, text modification, background replacement. Covers promotional posters, event promotional images, ad Banners, social media graphics, brand promotion images.

API Mapping

  • Poster generation:image_poster_generate
  • model value (first letter capitalized, different from the snake_case namespace of image-edit):Praline_2(default) / GummyV4.5 / PralineV2 / Gummy / Nougat

Dependencies

  • meitu-cli: >=2.0.6
  • 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
  2. Already ran with CONFIG AKSK meitu tools update
  3. Current AKSK = EXEC,MEITU_OPENAPI_TOOL_TASK_MODE=command
  4. output_dir:openclaw.yaml → ./output/ |else → $VISUAL/output/image-poster-generate/;mkdir -p

Execute

Trigger signals / routing rules

Core dimensions:complete parameters + poster scenario match + model selection。

Scenario Determination keywords Routing
Text-to-poster (no reference image) poster, promotional image, Banner image_poster_generate
Image-to-poster / poster editing (with image_list) modify this poster, reference poster image_poster_generate + image_list

model selection (first letter capitalized, different from the snake_case namespace of image-edit): default Praline_2(general), realistic portrait → GummyV4.5, high creativity → PralineV2, general portrait → Gummy, special style → Nougat。

Parameter definitions

Parameter Type Required Range Default Description
prompt STRING Yes -- -- Poster description. If missing → prompt "Please describe the poster content you want"
model STRING No Gummy / Nougat / PralineV2 / GummyV4.5 / Praline_2 Praline_2 Model selection (note the first letter is capitalized, unlike image-edit)
image_list ARRAY No -- -- Array of reference image URLs
ratio STRING No auto / 1:1 / 1:3 / 3:1 / 2:1 / 1:2 / 3:2 / 2:3 / 4:3 / 3:4 / 4:5 / 5:4 / 9:16 / 16:9 / 10:16 / 16:10 / 21:9 auto Aspect ratio
size STRING No auto / 1K / 2K / 4K / 512 auto Resolution
output_format STRING No jpeg / png / webp png Output format
enhance_prompt BOOLEAN No true / false false Whether to optimize prompt (recommended to enable when the description is <15 characters)
enhance_template STRING No -- -- Optimization template (only effective when enhance_prompt=true)

Tool invocation

meitu image-poster-generate --prompt "<desc>" [--model Praline_2] [--ratio 9:16] [--size auto] [--image_list <url>] --json --download-dir {output_dir} --skill_name skill_image-poster-generate

Error fallback

Scenario Handling method
prompt missing Prompt "Please describe the poster content you want"
model invalid Fall back to default Praline_2
ratio out of range Select the closest available value, or fall back to auto
size out of range Fall back to auto
image_list invalid image URL in Do not retry, prompt "Please provide a valid image link"
image_poster_generate call failed Retry once; if still failing, return error
Timeout (1200s) Retry once; if still timing out, return error
Content compliance interception Return the compliance prompt directly, do not retry
User description < 15 characters Recommended to enable enhance_prompt=true

Deliver

  • Use the output_dir parsed 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-poster-generate.{ext}

Output

  • Format: PNG (default) / JPEG / WebP
  • Location: project → ./output/, one-time → $VISUAL/output/image-poster-generate/

Baseline Task ID

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