Loading source
Pulling the file list, source metadata, and syntax-aware rendering for this listing.
Source from repo
Generate images via OpenAI, Google, OpenRouter, DashScope, Jimeng, Seedream, and Replicate APIs with batch support.
Files
Skill
Size
Entrypoint
Format
Open file
Syntax-highlighted preview of this file as included in the skill package.
references/providers/minimax.md
1# MiniMax2Read when the user picks `--provider minimax` or sets `default_model.minimax`. Default model is `image-01`.4## Models6**`image-01`** (recommended default)8- Supports text-to-image and subject-reference image generation10- Supports official `aspect_ratio` values: `1:1`, `16:9`, `4:3`, `3:2`, `2:3`, `3:4`, `9:16`, `21:9`11- Supports documented custom `width` / `height` via `--size <WxH>`12- Both width and height must be in `[512, 2048]` and divisible by `8`13**`image-01-live`** — lower-latency variant15- Use `--ar` for sizing; MiniMax documents custom `width`/`height` only for `image-01`17## Subject Reference19- `--ref` files are sent as MiniMax `subject_reference`21- `subject_reference[].type` is currently `character`22- Official docs say `image_file` supports public URLs or Base64 Data URLs; baoyu-imagine sends local refs as Data URLs23- Recommended refs: front-facing portraits, JPG/JPEG/PNG, under 10MB24## Official References26- [Image Generation Guide](https://platform.minimax.io/docs/guides/image-generation)28- [Text-to-Image API](https://platform.minimax.io/docs/api-reference/image-generation-t2i)29- [Image-to-Image API](https://platform.minimax.io/docs/api-reference/image-generation-i2i)30