Loading source

Preparing the source view

Pulling the file list, source metadata, and syntax-aware rendering for this listing.

Source from repo

Image Generation (AI SDK)

Generate images via OpenAI, Google, OpenRouter, DashScope, Jimeng, Seedream, and Replicate APIs with batch support.

jimliuGitHub jimliuSource repo Original GitHub link Publisher page

Files

32

Skill

n/a

Size

218.9 KB

Entrypoint

SKILL.md

Format

git-repo

Repo map

Skill files

references/config/first-time-setup.md

markdown11.8 KB

references/config/preferences-schema.md

references/providers/dashscope.md

references/providers/minimax.md

references/providers/openrouter.md

references/providers/replicate.md

references/providers/zai.md

references/usage-examples.md

scripts/main.test.ts

scripts/main.ts

scripts/providers/azure.test.ts

scripts/providers/azure.ts

scripts/providers/dashscope.test.ts

scripts/providers/dashscope.ts

scripts/providers/google.test.ts

scripts/providers/google.ts

scripts/providers/jimeng.test.ts

scripts/providers/jimeng.ts

scripts/providers/minimax.test.ts

scripts/providers/minimax.ts

scripts/providers/openai.test.ts

scripts/providers/openai.ts

scripts/providers/openrouter.test.ts

scripts/providers/openrouter.ts

scripts/providers/replicate.test.ts

scripts/providers/replicate.ts

scripts/providers/seedream.test.ts

scripts/providers/seedream.ts

scripts/providers/zai.test.ts

scripts/providers/zai.ts

scripts/types.ts

SKILL.md

markdown12.8 KBentry

Open file

references/providers/minimax.md

Syntax-highlighted preview of this file as included in the skill package.

Rendered Source

markdown30 linesFree

MiniMax

Read when the user picks --provider minimax or sets default_model.minimax. Default model is image-01.

Models

image-01 (recommended default)

Supports text-to-image and subject-reference image generation
Supports official aspect_ratio values: 1:1, 16:9, 4:3, 3:2, 2:3, 3:4, 9:16, 21:9
Supports documented custom width / height via --size <WxH>
Both width and height must be in [512, 2048] and divisible by 8

image-01-live — lower-latency variant

Use --ar for sizing; MiniMax documents custom width/height only for image-01

Subject Reference

--ref files are sent as MiniMax subject_reference
subject_reference[].type is currently character
Official docs say image_file supports public URLs or Base64 Data URLs; baoyu-imagine sends local refs as Data URLs
Recommended refs: front-facing portraits, JPG/JPEG/PNG, under 10MB

Official References

Image Generation Guide
Text-to-Image API
Image-to-Image API