feat(baoyu-image-gen): add MiniMax provider with subject reference and custom sizes

2026-08-07 09:23:04 +08:00 · 2026-03-25 15:39:40 -05:00
parent 86a3d6521b
commit ad8781c1c5
10 changed files with 702 additions and 34 deletions
@@ -124,6 +124,7 @@ default_model:
  google: gemini-3-pro-image-preview
  openai: gpt-image-1.5
  azure: image-prod
+  minimax: image-01
 batch:
  max_workers: 8
  provider_limits:
@@ -132,6 +133,9 @@ batch:
      start_interval_ms: 900
    openai:
      concurrency: 4
+    minimax:
+      concurrency: 2
+      start_interval_ms: 1400
    azure:
      concurrency: 1
      start_interval_ms: 1500
@@ -147,6 +151,7 @@ batch:
  assert.equal(config.default_model?.google, "gemini-3-pro-image-preview");
  assert.equal(config.default_model?.openai, "gpt-image-1.5");
  assert.equal(config.default_model?.azure, "image-prod");
+  assert.equal(config.default_model?.minimax, "image-01");
  assert.equal(config.batch?.max_workers, 8);
  assert.deepEqual(config.batch?.provider_limits?.google, {
    concurrency: 2,
@@ -155,6 +160,10 @@ batch:
  assert.deepEqual(config.batch?.provider_limits?.openai, {
    concurrency: 4,
  });
+  assert.deepEqual(config.batch?.provider_limits?.minimax, {
+    concurrency: 2,
+    start_interval_ms: 1400,
+  });
  assert.deepEqual(config.batch?.provider_limits?.azure, {
    concurrency: 1,
    start_interval_ms: 1500,
@@ -200,6 +209,7 @@ test("detectProvider rejects non-ref-capable providers and prefers Google first
    OPENAI_API_KEY: "openai-key",
    OPENROUTER_API_KEY: null,
    DASHSCOPE_API_KEY: null,
+    MINIMAX_API_KEY: null,
    REPLICATE_API_TOKEN: null,
    JIMENG_ACCESS_KEY_ID: null,
    JIMENG_SECRET_ACCESS_KEY: null,
@@ -216,6 +226,7 @@ test("detectProvider selects an available ref-capable provider for reference-ima
    AZURE_OPENAI_BASE_URL: null,
    OPENROUTER_API_KEY: null,
    DASHSCOPE_API_KEY: null,
+    MINIMAX_API_KEY: null,
    REPLICATE_API_TOKEN: null,
    JIMENG_ACCESS_KEY_ID: null,
    JIMENG_SECRET_ACCESS_KEY: null,
@@ -235,6 +246,7 @@ test("detectProvider selects Azure when only Azure credentials are configured",
    AZURE_OPENAI_BASE_URL: "https://example.openai.azure.com",
    OPENROUTER_API_KEY: null,
    DASHSCOPE_API_KEY: null,
+    MINIMAX_API_KEY: null,
    REPLICATE_API_TOKEN: null,
    JIMENG_ACCESS_KEY_ID: null,
    JIMENG_SECRET_ACCESS_KEY: null,
@@ -254,6 +266,7 @@ test("detectProvider infers Seedream from model id and allows Seedream reference
    OPENAI_API_KEY: null,
    OPENROUTER_API_KEY: null,
    DASHSCOPE_API_KEY: null,
+    MINIMAX_API_KEY: null,
    REPLICATE_API_TOKEN: null,
    JIMENG_ACCESS_KEY_ID: null,
    JIMENG_SECRET_ACCESS_KEY: null,
@@ -281,6 +294,26 @@ test("detectProvider infers Seedream from model id and allows Seedream reference
  );
 });

+test("detectProvider selects MiniMax when only MiniMax credentials are configured or the model id matches", (t) => {
+  useEnv(t, {
+    GOOGLE_API_KEY: null,
+    OPENAI_API_KEY: null,
+    AZURE_OPENAI_API_KEY: null,
+    AZURE_OPENAI_BASE_URL: null,
+    OPENROUTER_API_KEY: null,
+    DASHSCOPE_API_KEY: null,
+    MINIMAX_API_KEY: "minimax-key",
+    REPLICATE_API_TOKEN: null,
+    JIMENG_ACCESS_KEY_ID: null,
+    JIMENG_SECRET_ACCESS_KEY: null,
+    ARK_API_KEY: null,
+  });
+
+  assert.equal(detectProvider(makeArgs()), "minimax");
+  assert.equal(detectProvider(makeArgs({ referenceImages: ["ref.png"] })), "minimax");
+  assert.equal(detectProvider(makeArgs({ model: "image-01-live" })), "minimax");
+});
+
 test("batch worker and provider-rate-limit configuration prefer env over EXTEND config", (t) => {
  useEnv(t, {
    BAOYU_IMAGE_GEN_MAX_WORKERS: "12",
@@ -296,6 +329,10 @@ test("batch worker and provider-rate-limit configuration prefer env over EXTEND
          concurrency: 2,
          start_interval_ms: 900,
        },
+        minimax: {
+          concurrency: 1,
+          start_interval_ms: 1500,
+        },
      },
    },
  };
@@ -305,6 +342,10 @@ test("batch worker and provider-rate-limit configuration prefer env over EXTEND
    concurrency: 5,
    startIntervalMs: 450,
  });
+  assert.deepEqual(getConfiguredProviderRateLimits(extendConfig).minimax, {
+    concurrency: 1,
+    startIntervalMs: 1500,
+  });
 });

 test("loadBatchTasks and createTaskArgs resolve batch-relative paths", async (t) => {
@@ -58,6 +58,7 @@ const DEFAULT_PROVIDER_RATE_LIMITS: Record<Provider, ProviderRateLimit> = {
  openai: { concurrency: 3, startIntervalMs: 1100 },
  openrouter: { concurrency: 3, startIntervalMs: 1100 },
  dashscope: { concurrency: 3, startIntervalMs: 1100 },
+  minimax: { concurrency: 3, startIntervalMs: 1100 },
  jimeng: { concurrency: 3, startIntervalMs: 1100 },
  seedream: { concurrency: 3, startIntervalMs: 1100 },
  azure: { concurrency: 3, startIntervalMs: 1100 },
@@ -75,13 +76,13 @@ Options:
  --image <path>            Output image path (required in single-image mode)
  --batchfile <path>        JSON batch file for multi-image generation
  --jobs <count>            Worker count for batch mode (default: auto, max from config, built-in default 10)
-  --provider google|openai|openrouter|dashscope|replicate|jimeng|seedream|azure  Force provider (auto-detect by default)
+  --provider google|openai|openrouter|dashscope|minimax|replicate|jimeng|seedream|azure  Force provider (auto-detect by default)
  -m, --model <id>          Model ID
  --ar <ratio>              Aspect ratio (e.g., 16:9, 1:1, 4:3)
  --size <WxH>              Size (e.g., 1024x1024)
  --quality normal|2k       Quality preset (default: 2k)
  --imageSize 1K|2K|4K      Image size for Google/OpenRouter (default: from quality)
-  --ref <files...>          Reference images (Google, OpenAI, Azure, OpenRouter, Replicate, or Seedream 4.0/4.5/5.0)
+  --ref <files...>          Reference images (Google, OpenAI, Azure, OpenRouter, Replicate, MiniMax, or Seedream 4.0/4.5/5.0)
  --n <count>               Number of images for the current task (default: 1)
  --json                    JSON output
  -h, --help                Show help
@@ -112,6 +113,7 @@ Environment variables:
  GOOGLE_API_KEY            Google API key
  GEMINI_API_KEY            Gemini API key (alias for GOOGLE_API_KEY)
  DASHSCOPE_API_KEY         DashScope API key
+  MINIMAX_API_KEY           MiniMax API key
  REPLICATE_API_TOKEN       Replicate API token
  JIMENG_ACCESS_KEY_ID      Jimeng Access Key ID
  JIMENG_SECRET_ACCESS_KEY  Jimeng Secret Access Key
@@ -120,6 +122,7 @@ Environment variables:
  OPENROUTER_IMAGE_MODEL    Default OpenRouter model (google/gemini-3.1-flash-image-preview)
  GOOGLE_IMAGE_MODEL        Default Google model (gemini-3-pro-image-preview)
  DASHSCOPE_IMAGE_MODEL     Default DashScope model (qwen-image-2.0-pro)
+  MINIMAX_IMAGE_MODEL       Default MiniMax model (image-01)
  REPLICATE_IMAGE_MODEL     Default Replicate model (google/nano-banana-pro)
  JIMENG_IMAGE_MODEL        Default Jimeng model (jimeng_t2i_v40)
  SEEDREAM_IMAGE_MODEL      Default Seedream model (doubao-seedream-5-0-260128)
@@ -130,6 +133,7 @@ Environment variables:
  OPENROUTER_TITLE          Optional app name for OpenRouter attribution
  GOOGLE_BASE_URL           Custom Google endpoint
  DASHSCOPE_BASE_URL        Custom DashScope endpoint
+  MINIMAX_BASE_URL          Custom MiniMax endpoint
  REPLICATE_BASE_URL        Custom Replicate endpoint
  JIMENG_BASE_URL           Custom Jimeng endpoint
  AZURE_OPENAI_API_KEY      Azure OpenAI API key
@@ -235,6 +239,7 @@ export function parseArgs(argv: string[]): CliArgs {
        v !== "openai" &&
        v !== "openrouter" &&
        v !== "dashscope" &&
+        v !== "minimax" &&
        v !== "replicate" &&
        v !== "jimeng" &&
        v !== "seedream" &&
@@ -390,6 +395,7 @@ export function parseSimpleYaml(yaml: string): Partial<ExtendConfig> {
          openai: null,
          openrouter: null,
          dashscope: null,
+          minimax: null,
          replicate: null,
          jimeng: null,
          seedream: null,
@@ -417,6 +423,7 @@ export function parseSimpleYaml(yaml: string): Partial<ExtendConfig> {
          key === "openai" ||
          key === "openrouter" ||
          key === "dashscope" ||
+          key === "minimax" ||
          key === "replicate" ||
          key === "jimeng" ||
          key === "seedream" ||
@@ -434,6 +441,7 @@ export function parseSimpleYaml(yaml: string): Partial<ExtendConfig> {
          key === "openai" ||
          key === "openrouter" ||
          key === "dashscope" ||
+          key === "minimax" ||
          key === "replicate" ||
          key === "jimeng" ||
          key === "seedream" ||
@@ -528,12 +536,13 @@ export function getConfiguredProviderRateLimits(
    openai: { ...DEFAULT_PROVIDER_RATE_LIMITS.openai },
    openrouter: { ...DEFAULT_PROVIDER_RATE_LIMITS.openrouter },
    dashscope: { ...DEFAULT_PROVIDER_RATE_LIMITS.dashscope },
+    minimax: { ...DEFAULT_PROVIDER_RATE_LIMITS.minimax },
    jimeng: { ...DEFAULT_PROVIDER_RATE_LIMITS.jimeng },
    seedream: { ...DEFAULT_PROVIDER_RATE_LIMITS.seedream },
    azure: { ...DEFAULT_PROVIDER_RATE_LIMITS.azure },
  };

-  for (const provider of ["replicate", "google", "openai", "openrouter", "dashscope", "jimeng", "seedream", "azure"] as Provider[]) {
+  for (const provider of ["replicate", "google", "openai", "openrouter", "dashscope", "minimax", "jimeng", "seedream", "azure"] as Provider[]) {
    const envPrefix = `BAOYU_IMAGE_GEN_${provider.toUpperCase()}`;
    const extendLimit = extendConfig.batch?.provider_limits?.[provider];
    configured[provider] = {
@@ -582,7 +591,9 @@ export function normalizeOutputImagePath(p: string, defaultExtension = ".png"):

 function inferProviderFromModel(model: string | null): Provider | null {
  if (!model) return null;
-  if (model.includes("seedream") || model.includes("seededit")) return "seedream";
+  const normalized = model.trim();
+  if (normalized.includes("seedream") || normalized.includes("seededit")) return "seedream";
+  if (normalized === "image-01" || normalized === "image-01-live") return "minimax";
  return null;
 }

@@ -595,10 +606,11 @@ export function detectProvider(args: CliArgs): Provider {
    args.provider !== "azure" &&
    args.provider !== "openrouter" &&
    args.provider !== "replicate" &&
-    args.provider !== "seedream"
+    args.provider !== "seedream" &&
+    args.provider !== "minimax"
  ) {
    throw new Error(
-      "Reference images require a ref-capable provider. Use --provider google (Gemini multimodal), --provider openai (GPT Image edits), --provider azure (Azure OpenAI), --provider openrouter (OpenRouter multimodal), --provider replicate, or --provider seedream for supported Seedream models."
+      "Reference images require a ref-capable provider. Use --provider google (Gemini multimodal), --provider openai (GPT Image edits), --provider azure (Azure OpenAI), --provider openrouter (OpenRouter multimodal), --provider replicate, --provider seedream for supported Seedream models, or --provider minimax for MiniMax subject-reference workflows."
    );
  }

@@ -609,6 +621,7 @@ export function detectProvider(args: CliArgs): Provider {
  const hasOpenai = !!process.env.OPENAI_API_KEY;
  const hasOpenrouter = !!process.env.OPENROUTER_API_KEY;
  const hasDashscope = !!process.env.DASHSCOPE_API_KEY;
+  const hasMinimax = !!process.env.MINIMAX_API_KEY;
  const hasReplicate = !!process.env.REPLICATE_API_TOKEN;
  const hasJimeng = !!(process.env.JIMENG_ACCESS_KEY_ID && process.env.JIMENG_SECRET_ACCESS_KEY);
  const hasSeedream = !!process.env.ARK_API_KEY;
@@ -621,6 +634,13 @@ export function detectProvider(args: CliArgs): Provider {
    return "seedream";
  }

+  if (modelProvider === "minimax") {
+    if (!hasMinimax) {
+      throw new Error("Model looks like a MiniMax image model, but MINIMAX_API_KEY is not set.");
+    }
+    return "minimax";
+  }
+
  if (args.referenceImages.length > 0) {
    if (hasGoogle) return "google";
    if (hasOpenai) return "openai";
@@ -628,8 +648,9 @@ export function detectProvider(args: CliArgs): Provider {
    if (hasOpenrouter) return "openrouter";
    if (hasReplicate) return "replicate";
    if (hasSeedream) return "seedream";
+    if (hasMinimax) return "minimax";
    throw new Error(
-      "Reference images require Google, OpenAI, Azure, OpenRouter, Replicate, or supported Seedream models. Set GOOGLE_API_KEY/GEMINI_API_KEY, OPENAI_API_KEY, AZURE_OPENAI_API_KEY+AZURE_OPENAI_BASE_URL, OPENROUTER_API_KEY, REPLICATE_API_TOKEN, or ARK_API_KEY, or remove --ref."
+      "Reference images require Google, OpenAI, Azure, OpenRouter, Replicate, supported Seedream models, or MiniMax. Set GOOGLE_API_KEY/GEMINI_API_KEY, OPENAI_API_KEY, AZURE_OPENAI_API_KEY+AZURE_OPENAI_BASE_URL, OPENROUTER_API_KEY, REPLICATE_API_TOKEN, ARK_API_KEY, or MINIMAX_API_KEY, or remove --ref."
    );
  }

@@ -639,6 +660,7 @@ export function detectProvider(args: CliArgs): Provider {
    hasAzure && "azure",
    hasOpenrouter && "openrouter",
    hasDashscope && "dashscope",
+    hasMinimax && "minimax",
    hasReplicate && "replicate",
    hasJimeng && "jimeng",
    hasSeedream && "seedream",
@@ -648,7 +670,7 @@ export function detectProvider(args: CliArgs): Provider {
  if (available.length > 1) return available[0]!;

  throw new Error(
-    "No API key found. Set GOOGLE_API_KEY, GEMINI_API_KEY, OPENAI_API_KEY, AZURE_OPENAI_API_KEY+AZURE_OPENAI_BASE_URL, OPENROUTER_API_KEY, DASHSCOPE_API_KEY, REPLICATE_API_TOKEN, JIMENG keys, or ARK_API_KEY.\n" +
+    "No API key found. Set GOOGLE_API_KEY, GEMINI_API_KEY, OPENAI_API_KEY, AZURE_OPENAI_API_KEY+AZURE_OPENAI_BASE_URL, OPENROUTER_API_KEY, DASHSCOPE_API_KEY, MINIMAX_API_KEY, REPLICATE_API_TOKEN, JIMENG keys, or ARK_API_KEY.\n" +
      "Create ~/.baoyu-skills/.env or <cwd>/.baoyu-skills/.env with your keys."
  );
 }
@@ -687,6 +709,7 @@ export function isRetryableGenerationError(error: unknown): boolean {
 async function loadProviderModule(provider: Provider): Promise<ProviderModule> {
  if (provider === "google") return (await import("./providers/google")) as ProviderModule;
  if (provider === "dashscope") return (await import("./providers/dashscope")) as ProviderModule;
+  if (provider === "minimax") return (await import("./providers/minimax")) as ProviderModule;
  if (provider === "replicate") return (await import("./providers/replicate")) as ProviderModule;
  if (provider === "openrouter") return (await import("./providers/openrouter")) as ProviderModule;
  if (provider === "jimeng") return (await import("./providers/jimeng")) as ProviderModule;
@@ -717,6 +740,7 @@ function getModelForProvider(
      return extendConfig.default_model.openrouter;
    }
    if (provider === "dashscope" && extendConfig.default_model.dashscope) return extendConfig.default_model.dashscope;
+    if (provider === "minimax" && extendConfig.default_model.minimax) return extendConfig.default_model.minimax;
    if (provider === "replicate" && extendConfig.default_model.replicate) return extendConfig.default_model.replicate;
    if (provider === "jimeng" && extendConfig.default_model.jimeng) return extendConfig.default_model.jimeng;
    if (provider === "seedream" && extendConfig.default_model.seedream) return extendConfig.default_model.seedream;
@@ -0,0 +1,171 @@
+import assert from "node:assert/strict";
+import fs from "node:fs/promises";
+import os from "node:os";
+import path from "node:path";
+import test, { type TestContext } from "node:test";
+
+import type { CliArgs } from "../types.ts";
+import {
+  buildMinimaxUrl,
+  buildRequestBody,
+  buildSubjectReference,
+  extractImageFromResponse,
+  parsePixelSize,
+  validateArgs,
+} from "./minimax.ts";
+
+function useEnv(
+  t: TestContext,
+  values: Record<string, string | null>,
+): void {
+  const previous = new Map<string, string | undefined>();
+  for (const [key, value] of Object.entries(values)) {
+    previous.set(key, process.env[key]);
+    if (value == null) {
+      delete process.env[key];
+    } else {
+      process.env[key] = value;
+    }
+  }
+
+  t.after(() => {
+    for (const [key, value] of previous.entries()) {
+      if (value == null) {
+        delete process.env[key];
+      } else {
+        process.env[key] = value;
+      }
+    }
+  });
+}
+
+function makeArgs(overrides: Partial<CliArgs> = {}): CliArgs {
+  return {
+    prompt: null,
+    promptFiles: [],
+    imagePath: null,
+    provider: null,
+    model: null,
+    aspectRatio: null,
+    size: null,
+    quality: null,
+    imageSize: null,
+    referenceImages: [],
+    n: 1,
+    batchFile: null,
+    jobs: null,
+    json: false,
+    help: false,
+    ...overrides,
+  };
+}
+
+test("MiniMax URL builder normalizes /v1 suffixes", (t) => {
+  useEnv(t, { MINIMAX_BASE_URL: "https://api.minimax.io" });
+  assert.equal(buildMinimaxUrl(), "https://api.minimax.io/v1/image_generation");
+
+  process.env.MINIMAX_BASE_URL = "https://proxy.example.com/custom/v1/";
+  assert.equal(buildMinimaxUrl(), "https://proxy.example.com/custom/v1/image_generation");
+});
+
+test("MiniMax size parsing and validation follow documented constraints", () => {
+  assert.deepEqual(parsePixelSize("1536x1024"), { width: 1536, height: 1024 });
+  assert.deepEqual(parsePixelSize("1536*1024"), { width: 1536, height: 1024 });
+  assert.equal(parsePixelSize("wide"), null);
+
+  validateArgs("image-01", makeArgs({ size: "1536x1024", n: 9 }));
+
+  assert.throws(
+    () => validateArgs("image-01-live", makeArgs({ size: "1536x1024" })),
+    /only supported with model image-01/,
+  );
+  assert.throws(
+    () => validateArgs("image-01", makeArgs({ size: "1537x1024" })),
+    /divisible by 8/,
+  );
+  assert.throws(
+    () => validateArgs("image-01", makeArgs({ aspectRatio: "2.35:1" })),
+    /aspect_ratio must be one of/,
+  );
+  assert.throws(
+    () => validateArgs("image-01", makeArgs({ n: 10 })),
+    /at most 9 images/,
+  );
+});
+
+test("MiniMax request body maps aspect ratio, size, n, and subject references", async (t) => {
+  const dir = await fs.mkdtemp(path.join(os.tmpdir(), "minimax-test-"));
+  t.after(() => fs.rm(dir, { recursive: true, force: true }));
+
+  const refPath = path.join(dir, "portrait.png");
+  await fs.writeFile(refPath, Buffer.from("portrait"));
+
+  const ratioBody = await buildRequestBody(
+    "A portrait by the window",
+    "image-01",
+    makeArgs({ aspectRatio: "16:9", n: 2, referenceImages: [refPath] }),
+  );
+  assert.equal(ratioBody.aspect_ratio, "16:9");
+  assert.equal(ratioBody.n, 2);
+  assert.equal(ratioBody.response_format, "base64");
+  assert.match(ratioBody.subject_reference?.[0]?.image_file || "", /^data:image\/png;base64,/);
+
+  const sizeBody = await buildRequestBody(
+    "A portrait by the window",
+    "image-01",
+    makeArgs({ size: "1536x1024" }),
+  );
+  assert.equal(sizeBody.width, 1536);
+  assert.equal(sizeBody.height, 1024);
+  assert.equal(sizeBody.aspect_ratio, undefined);
+});
+
+test("MiniMax subject references require supported file types", async (t) => {
+  const dir = await fs.mkdtemp(path.join(os.tmpdir(), "minimax-ref-"));
+  t.after(() => fs.rm(dir, { recursive: true, force: true }));
+
+  const good = path.join(dir, "portrait.jpg");
+  const bad = path.join(dir, "portrait.webp");
+  await fs.writeFile(good, Buffer.from("portrait"));
+  await fs.writeFile(bad, Buffer.from("portrait"));
+
+  const subjectReference = await buildSubjectReference([good]);
+  assert.equal(subjectReference?.[0]?.type, "character");
+
+  await assert.rejects(
+    () => buildSubjectReference([bad]),
+    /only supports JPG, JPEG, or PNG/,
+  );
+});
+
+test("MiniMax response extraction supports base64 and URL payloads", async (t) => {
+  const originalFetch = globalThis.fetch;
+  t.after(() => {
+    globalThis.fetch = originalFetch;
+  });
+
+  const fromBase64 = await extractImageFromResponse({
+    data: {
+      image_base64: [Buffer.from("hello").toString("base64")],
+    },
+  });
+  assert.equal(Buffer.from(fromBase64).toString("utf8"), "hello");
+
+  globalThis.fetch = async () =>
+    new Response(Uint8Array.from([1, 2, 3]), {
+      status: 200,
+      headers: { "Content-Type": "image/jpeg" },
+    });
+
+  const fromUrl = await extractImageFromResponse({
+    data: {
+      image_urls: ["https://example.com/output.jpg"],
+    },
+  });
+  assert.deepEqual([...fromUrl], [1, 2, 3]);
+
+  await assert.rejects(
+    () => extractImageFromResponse({ base_resp: { status_code: 1001, status_msg: "blocked" } }),
+    /blocked/,
+  );
+});
@@ -0,0 +1,220 @@
+import path from "node:path";
+import { readFile } from "node:fs/promises";
+
+import type { CliArgs } from "../types";
+
+const DEFAULT_MODEL = "image-01";
+const MAX_REFERENCE_IMAGE_BYTES = 10 * 1024 * 1024;
+const SUPPORTED_ASPECT_RATIOS = new Set(["1:1", "16:9", "4:3", "3:2", "2:3", "3:4", "9:16", "21:9"]);
+
+type MinimaxSubjectReference = {
+  type: "character";
+  image_file: string;
+};
+
+type MinimaxRequestBody = {
+  model: string;
+  prompt: string;
+  response_format: "base64";
+  aspect_ratio?: string;
+  width?: number;
+  height?: number;
+  n?: number;
+  subject_reference?: MinimaxSubjectReference[];
+};
+
+type MinimaxResponse = {
+  id?: string;
+  data?: {
+    image_urls?: string[];
+    image_base64?: string[];
+  };
+  base_resp?: {
+    status_code?: number;
+    status_msg?: string;
+  };
+};
+
+export function getDefaultModel(): string {
+  return process.env.MINIMAX_IMAGE_MODEL || DEFAULT_MODEL;
+}
+
+function getApiKey(): string | null {
+  return process.env.MINIMAX_API_KEY || null;
+}
+
+export function buildMinimaxUrl(): string {
+  const base = (process.env.MINIMAX_BASE_URL || "https://api.minimax.io").replace(/\/+$/g, "");
+  return base.endsWith("/v1") ? `${base}/image_generation` : `${base}/v1/image_generation`;
+}
+
+function getMimeType(filename: string): "image/jpeg" | "image/png" {
+  const ext = path.extname(filename).toLowerCase();
+  if (ext === ".jpg" || ext === ".jpeg") return "image/jpeg";
+  if (ext === ".png") return "image/png";
+  throw new Error(
+    `MiniMax subject_reference only supports JPG, JPEG, or PNG files: ${filename}`
+  );
+}
+
+export function parsePixelSize(size: string): { width: number; height: number } | null {
+  const match = size.trim().match(/^(\d+)\s*[xX*]\s*(\d+)$/);
+  if (!match) return null;
+
+  const width = parseInt(match[1]!, 10);
+  const height = parseInt(match[2]!, 10);
+  if (!Number.isFinite(width) || !Number.isFinite(height) || width <= 0 || height <= 0) {
+    return null;
+  }
+
+  return { width, height };
+}
+
+function validatePixelSize(width: number, height: number): void {
+  if (width < 512 || width > 2048 || height < 512 || height > 2048) {
+    throw new Error("MiniMax custom size must keep width and height between 512 and 2048.");
+  }
+  if (width % 8 !== 0 || height % 8 !== 0) {
+    throw new Error("MiniMax custom size requires width and height divisible by 8.");
+  }
+}
+
+export function validateArgs(model: string, args: CliArgs): void {
+  if (args.n > 9) {
+    throw new Error("MiniMax supports at most 9 images per request.");
+  }
+
+  if (args.aspectRatio && !SUPPORTED_ASPECT_RATIOS.has(args.aspectRatio)) {
+    throw new Error(
+      `MiniMax aspect_ratio must be one of: ${Array.from(SUPPORTED_ASPECT_RATIOS).join(", ")}.`
+    );
+  }
+
+  if (args.size && !args.aspectRatio) {
+    if (model !== "image-01") {
+      throw new Error("MiniMax custom --size is only supported with model image-01. Use --model image-01 or pass --ar instead.");
+    }
+    const parsed = parsePixelSize(args.size);
+    if (!parsed) {
+      throw new Error("MiniMax --size must be in WxH format, for example 1536x1024.");
+    }
+    validatePixelSize(parsed.width, parsed.height);
+  }
+}
+
+export async function buildSubjectReference(
+  referenceImages: string[],
+): Promise<MinimaxSubjectReference[] | undefined> {
+  if (referenceImages.length === 0) return undefined;
+
+  const subjectReference: MinimaxSubjectReference[] = [];
+  for (const refPath of referenceImages) {
+    const bytes = await readFile(refPath);
+    if (bytes.length > MAX_REFERENCE_IMAGE_BYTES) {
+      throw new Error(`MiniMax subject_reference images must be smaller than 10MB: ${refPath}`);
+    }
+
+    subjectReference.push({
+      type: "character",
+      image_file: `data:${getMimeType(refPath)};base64,${bytes.toString("base64")}`,
+    });
+  }
+
+  return subjectReference;
+}
+
+export async function buildRequestBody(
+  prompt: string,
+  model: string,
+  args: CliArgs,
+): Promise<MinimaxRequestBody> {
+  validateArgs(model, args);
+
+  const body: MinimaxRequestBody = {
+    model,
+    prompt,
+    response_format: "base64",
+  };
+
+  if (args.aspectRatio) {
+    body.aspect_ratio = args.aspectRatio;
+  } else if (args.size) {
+    const parsed = parsePixelSize(args.size);
+    if (!parsed) {
+      throw new Error("MiniMax --size must be in WxH format, for example 1536x1024.");
+    }
+    body.width = parsed.width;
+    body.height = parsed.height;
+  }
+
+  if (args.n > 1) {
+    body.n = args.n;
+  }
+
+  const subjectReference = await buildSubjectReference(args.referenceImages);
+  if (subjectReference) {
+    body.subject_reference = subjectReference;
+  }
+
+  return body;
+}
+
+async function downloadImage(url: string): Promise<Uint8Array> {
+  const response = await fetch(url);
+  if (!response.ok) {
+    throw new Error(`Failed to download image from MiniMax: ${response.status}`);
+  }
+  return new Uint8Array(await response.arrayBuffer());
+}
+
+export async function extractImageFromResponse(result: MinimaxResponse): Promise<Uint8Array> {
+  const baseResp = result.base_resp;
+  if (baseResp && baseResp.status_code !== undefined && baseResp.status_code !== 0) {
+    throw new Error(baseResp.status_msg || `MiniMax API returned status_code=${baseResp.status_code}`);
+  }
+
+  const base64Image = result.data?.image_base64?.[0];
+  if (base64Image) {
+    return Uint8Array.from(Buffer.from(base64Image, "base64"));
+  }
+
+  const url = result.data?.image_urls?.[0];
+  if (url) {
+    return downloadImage(url);
+  }
+
+  throw new Error("No image data in MiniMax response");
+}
+
+export function getDefaultOutputExtension(): ".jpg" {
+  return ".jpg";
+}
+
+export async function generateImage(
+  prompt: string,
+  model: string,
+  args: CliArgs
+): Promise<Uint8Array> {
+  const apiKey = getApiKey();
+  if (!apiKey) {
+    throw new Error("MINIMAX_API_KEY is required. Get one from https://platform.minimax.io/");
+  }
+
+  const body = await buildRequestBody(prompt, model, args);
+  const response = await fetch(buildMinimaxUrl(), {
+    method: "POST",
+    headers: {
+      "Content-Type": "application/json",
+      Authorization: `Bearer ${apiKey}`,
+    },
+    body: JSON.stringify(body),
+  });
+
+  if (!response.ok) {
+    const err = await response.text();
+    throw new Error(`MiniMax API error (${response.status}): ${err}`);
+  }
+
+  const result = (await response.json()) as MinimaxResponse;
+  return extractImageFromResponse(result);
+}
@@ -1,4 +1,13 @@
-export type Provider = "google" | "openai" | "openrouter" | "dashscope" | "replicate" | "jimeng" | "seedream" | "azure";
+export type Provider =
+  | "google"
+  | "openai"
+  | "openrouter"
+  | "dashscope"
+  | "minimax"
+  | "replicate"
+  | "jimeng"
+  | "seedream"
+  | "azure";
 export type Quality = "normal" | "2k";

 export type CliArgs = {
@@ -52,6 +61,7 @@ export type ExtendConfig = {
    openai: string | null;
    openrouter: string | null;
    dashscope: string | null;
+    minimax: string | null;
    replicate: string | null;
    jimeng: string | null;
    seedream: string | null;