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

2026-08-07 17:33:03 +08:00 · 2026-03-25 15:39:40 -05:00
parent 86a3d6521b
commit ad8781c1c5
10 changed files with 702 additions and 34 deletions
@@ -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);
+}