feat: add qwen dashscope api compatibility with model routing

skills/baoyu-image-gen/scripts/providers/dashscope.ts

@@ -45,6 +45,14 @@ const STANDARD_SIZES_2K: [number, number][] = [
   [2048, 2048],
 ];
 
+const QWEN_SIZES: [number, number][] = [
+  [1664, 928],
+  [1472, 1104],
+  [1328, 1328],
+  [1104, 1472],
+  [928, 1664],
+];
+
 function getSizeFromAspectRatio(ar: string | null, quality: CliArgs["quality"]): string {
   const is2k = quality === "2k";
   const defaultSize = is2k ? "1536*1536" : "1024*1024";
@@ -75,21 +83,40 @@ function normalizeSize(size: string): string {
   return size.replace("x", "*");
 }
 
-export async function generateImage(
-  prompt: string,
-  model: string,
-  args: CliArgs
-): Promise<Uint8Array> {
-  const apiKey = getApiKey();
-  if (!apiKey) throw new Error("DASHSCOPE_API_KEY is required");
+function isQwenModel(model: string): boolean {
+  return model.startsWith("qwen-image-");
+}
 
-  if (args.referenceImages.length > 0) {
-    throw new Error(
-      "Reference images are not supported with DashScope provider in baoyu-image-gen. Use --provider google with a Gemini multimodal model."
-    );
+function getQwenSizeFromAspectRatio(ar: string | null): string {
+  const defaultSize = "1328*1328";
+
+  if (!ar) return defaultSize;
+
+  const parsed = parseAspectRatio(ar);
+  if (!parsed) return defaultSize;
+
+  const targetRatio = parsed.width / parsed.height;
+
+  let best = defaultSize;
+  let bestDiff = Infinity;
+
+  for (const [w, h] of QWEN_SIZES) {
+    const diff = Math.abs(w / h - targetRatio);
+    if (diff < bestDiff) {
+      bestDiff = diff;
+      best = `${w}*${h}`;
+    }
   }
 
-  const size = args.size ? normalizeSize(args.size) : getSizeFromAspectRatio(args.aspectRatio, args.quality);
+  return best;
+}
+
+async function generateWithQwenApi(
+  prompt: string,
+  model: string,
+  size: string,
+  apiKey: string
+): Promise<Uint8Array> {
   const url = `${getBaseUrl()}/api/v1/services/aigc/multimodal-generation/generation`;
 
   const body = {
@@ -104,11 +131,12 @@ export async function generateImage(
     },
     parameters: {
       prompt_extend: false,
+      watermark: false,
       size,
     },
   };
 
-  console.log(`Generating image with DashScope (${model})...`, { size });
+  console.log(`Generating image with DashScope Qwen API (${model})...`, { size });
 
   const res = await fetch(url, {
     method: "POST",
@@ -163,3 +191,106 @@ export async function generateImage(
 
   return Uint8Array.from(Buffer.from(imageData, "base64"));
 }
+
+async function generateWithLegacyApi(
+  prompt: string,
+  model: string,
+  size: string,
+  apiKey: string
+): Promise<Uint8Array> {
+  const url = `${getBaseUrl()}/api/v1/services/aigc/multimodal-generation/generation`;
+
+  const body = {
+    model,
+    input: {
+      messages: [
+        {
+          role: "user",
+          content: [{ text: prompt }],
+        },
+      ],
+    },
+    parameters: {
+      prompt_extend: false,
+      size,
+    },
+  };
+
+  console.log(`Generating image with DashScope Legacy API (${model})...`, { size });
+
+  const res = await fetch(url, {
+    method: "POST",
+    headers: {
+      "Content-Type": "application/json",
+      Authorization: `Bearer ${apiKey}`,
+    },
+    body: JSON.stringify(body),
+  });
+
+  if (!res.ok) {
+    const err = await res.text();
+    throw new Error(`DashScope API error (${res.status}): ${err}`);
+  }
+
+  const result = await res.json() as {
+    output?: {
+      result_image?: string;
+      choices?: Array<{
+        message?: {
+          content?: Array<{ image?: string }>;
+        };
+      }>;
+    };
+  };
+
+  let imageData: string | null = null;
+
+  if (result.output?.result_image) {
+    imageData = result.output.result_image;
+  } else if (result.output?.choices?.[0]?.message?.content) {
+    const content = result.output.choices[0].message.content;
+    for (const item of content) {
+      if (item.image) {
+        imageData = item.image;
+        break;
+      }
+    }
+  }
+
+  if (!imageData) {
+    console.error("Response:", JSON.stringify(result, null, 2));
+    throw new Error("No image in response");
+  }
+
+  if (imageData.startsWith("http://") || imageData.startsWith("https://")) {
+    const imgRes = await fetch(imageData);
+    if (!imgRes.ok) throw new Error("Failed to download image");
+    const buf = await imgRes.arrayBuffer();
+    return new Uint8Array(buf);
+  }
+
+  return Uint8Array.from(Buffer.from(imageData, "base64"));
+}
+
+export async function generateImage(
+  prompt: string,
+  model: string,
+  args: CliArgs
+): Promise<Uint8Array> {
+  const apiKey = getApiKey();
+  if (!apiKey) throw new Error("DASHSCOPE_API_KEY is required");
+
+  if (args.referenceImages.length > 0) {
+    throw new Error(
+      "Reference images are not supported with DashScope provider in baoyu-image-gen. Use --provider google with a Gemini multimodal model."
+    );
+  }
+
+  if (isQwenModel(model)) {
+    const size = args.size ? normalizeSize(args.size) : getQwenSizeFromAspectRatio(args.aspectRatio);
+    return generateWithQwenApi(prompt, model, size, apiKey);
+  } else {
+    const size = args.size ? normalizeSize(args.size) : getSizeFromAspectRatio(args.aspectRatio, args.quality);
+    return generateWithLegacyApi(prompt, model, size, apiKey);
+  }
+}