Free Quota Image Skill

\r

Overview\r

\r Use this skill to run a provider-agnostic text-to-image pipeline with free-quota-first routing, token rotation, and prompt enhancement. \r

Workflow\r

\r

1. Load config from {baseDir}/assets/config.example.yaml or user-provided config.
2. Resolve provider order (--provider auto follows routing.provider_order).
3. Resolve model candidates per provider (requested -> z-image-turbo -> provider default).\r
4. Prepare prompt for each attempt:\r
   • optionally auto-translate for target models\r
   • optionally optimize prompt with provider text model\r
5. Execute generation request.\r
6. On quota/auth failures, rotate token; if exhausted, move to next provider.\r
7. Repeat the generation flow when --count > 1, and rotate provider/token start position per image to spread load.
8. Return stable JSON output fields or direct URL output. \r

Commands\r

\r Install dependencies:

python -m pip install -r {baseDir}/scripts/requirements.txt

\r Run generation:\r \r

python {baseDir}/scripts/run_text2img.py --prompt "cinematic rainy tokyo alley" --json

\r Run with explicit provider/model:\r \r

python {baseDir}/scripts/run_text2img.py --prompt "a fox astronaut" --provider gitee --model flux-2 --json

\r Save image locally:\r \r

python {baseDir}/scripts/run_text2img.py --prompt "retro sci-fi city" --output ./out.png

Generate multiple images in one run:

python {baseDir}/scripts/run_text2img.py --prompt "anime passport portrait" --count 4 --json

\r

CLI contract\r

\r Use {baseDir}/scripts/run_text2img.py with the fixed contract: \r

• --prompt (required)\r
• --provider (auto|huggingface|gitee|modelscope|a4f|openai_compatible, default auto)
• --model (default z-image-turbo)\r
• --aspect-ratio (default 1:1)\r
• --seed (optional int)\r
• --steps (optional int)\r
• --guidance-scale (optional float)\r
• --enable-hd (flag)\r
• --optimize-prompt / --no-optimize-prompt (default on)\r
• --auto-translate / --no-auto-translate (default off)\r
• --config (default {baseDir}/assets/config.example.yaml)
• --output (optional output file path)
• --count (number of images in one run, default 1)
• --json (structured output) \r

Output contract\r

\r When --json is used, output these fields on success:\r \r

• id\r
• url\r
• provider\r
• model\r
• prompt_original\r
• prompt_final\r
• seed\r
• steps\r
• guidance_scale\r
• aspect_ratio\r
• fallback_chain\r
• elapsed_ms\r \r On failure, output structured error fields: \r
• error_type\r
• error\r
• fallback_chain

When --count > 1, JSON output contains:

• count
• images (array of standard success payloads)
• elapsed_ms \r

References\r

\r Read only what is needed:\r \r

• Provider API wiring: references/provider-endpoints.md
• Model coverage and fallback: references/model-matrix.md
• Token rotation and date rules: references/token-rotation-policy.md
• Prompt optimization pipeline: references/prompt-optimization-policy.md
• OpenClaw setup details: references/openclaw-integration.md \r

Scope boundaries\r

\r Keep this skill focused on text-to-image core only.\r \r Do not add image editing, video generation, or cloud storage workflows in this skill.\r