chore: release v1.73.0

.claude-plugin/marketplace.json

@@ -6,7 +6,7 @@
   },
   "metadata": {
     "description": "Skills shared by Baoyu for improving daily work efficiency",
-    "version": "1.70.0"
+    "version": "1.73.0"
   },
   "plugins": [
     {

CHANGELOG.md

@@ -2,6 +2,21 @@
 
 English | [中文](./CHANGELOG.zh.md)
 
+## 1.73.0 - 2026-03-18
+
+### Features
+- `baoyu-danger-x-to-markdown`: add video media support for X articles with poster image and video link rendering
+
+## 1.72.0 - 2026-03-18
+
+### Features
+- `baoyu-danger-x-to-markdown`: add MARKDOWN entity support for rendering embedded markdown/code blocks in X articles
+
+## 1.71.0 - 2026-03-17
+
+### Features
+- `baoyu-image-gen`: add Seedream reference image support for 5.0/4.5/4.0 models with model-specific size validation
+
 ## 1.70.0 - 2026-03-17
 
 ### Features

CHANGELOG.zh.md

@@ -2,6 +2,21 @@
 
 [English](./CHANGELOG.md) | 中文
 
+## 1.73.0 - 2026-03-18
+
+### 新功能
+- `baoyu-danger-x-to-markdown`：支持 X 文章中的视频媒体，渲染封面图和视频链接
+
+## 1.72.0 - 2026-03-18
+
+### 新功能
+- `baoyu-danger-x-to-markdown`：支持渲染 X 文章中嵌入的 MARKDOWN 实体（代码块等）
+
+## 1.71.0 - 2026-03-17
+
+### 新功能
+- `baoyu-image-gen`：为 Seedream 5.0/4.5/4.0 模型添加参考图支持，并增加模型特定的尺寸校验
+
 ## 1.70.0 - 2026-03-17
 
 ### 新功能

CLAUDE.md

@@ -1,6 +1,6 @@
 # CLAUDE.md
 
-Claude Code marketplace plugin providing AI-powered content generation skills. Version: **1.70.0**.
+Claude Code marketplace plugin providing AI-powered content generation skills. Version: **1.73.0**.
 
 ## Architecture
 

README.md

@@ -695,7 +695,7 @@ AI SDK-based image generation using OpenAI, Google, OpenRouter, DashScope (Aliyu
 # Seedream (豆包)
 /baoyu-image-gen --prompt "一只可爱的猫" --image cat.png --provider seedream
 
-# With reference images (Google, OpenAI, OpenRouter, or Replicate)
+# With reference images (Google, OpenAI, OpenRouter, Replicate, or Seedream 5.0/4.5/4.0)
 /baoyu-image-gen --prompt "Make it blue" --image out.png --ref source.png
 ```
 
@@ -710,7 +710,7 @@ AI SDK-based image generation using OpenAI, Google, OpenRouter, DashScope (Aliyu
 | `--ar` | Aspect ratio (e.g., `16:9`, `1:1`, `4:3`) |
 | `--size` | Size (e.g., `1024x1024`) |
 | `--quality` | `normal` or `2k` (default: `2k`) |
-| `--ref` | Reference images (Google, OpenAI, OpenRouter or Replicate) |
+| `--ref` | Reference images (Google, OpenAI, OpenRouter, Replicate, or Seedream 5.0/4.5/4.0) |
 
 **Environment Variables** (see [Environment Configuration](#environment-configuration) for setup):
 | Variable | Description | Default |

README.zh.md

@@ -695,7 +695,7 @@ AI 驱动的生成后端。
 # 豆包（Seedream）
 /baoyu-image-gen --prompt "一只可爱的猫" --image cat.png --provider seedream
 
-# 带参考图（Google、OpenAI、OpenRouter 或 Replicate）
+# 带参考图（Google、OpenAI、OpenRouter、Replicate 或 Seedream 5.0/4.5/4.0）
 /baoyu-image-gen --prompt "把它变成蓝色" --image out.png --ref source.png
 ```
 
@@ -710,7 +710,7 @@ AI 驱动的生成后端。
 | `--ar` | 宽高比（如 `16:9`、`1:1`、`4:3`） |
 | `--size` | 尺寸（如 `1024x1024`） |
 | `--quality` | `normal` 或 `2k`（默认：`2k`） |
-| `--ref` | 参考图片（Google、OpenAI、OpenRouter 或 Replicate） |
+| `--ref` | 参考图片（Google、OpenAI、OpenRouter、Replicate 或 Seedream 5.0/4.5/4.0） |
 
 **环境变量**（配置方法见[环境配置](#环境配置)）：
 | 变量 | 说明 | 默认值 |

skills/baoyu-danger-x-to-markdown/scripts/markdown.test.ts

@@ -0,0 +1,178 @@
+import { expect, test } from "bun:test";
+
+import { formatArticleMarkdown } from "./markdown.js";
+
+test("formatArticleMarkdown renders MARKDOWN entities from atomic blocks", () => {
+  const article = {
+    title: "Atomic Markdown Example",
+    content_state: {
+      blocks: [
+        {
+          type: "unstyled",
+          text: "Before the snippet.",
+          entityRanges: [],
+        },
+        {
+          type: "atomic",
+          text: " ",
+          entityRanges: [{ key: 0, offset: 0, length: 1 }],
+        },
+        {
+          type: "unstyled",
+          text: "After the snippet.",
+          entityRanges: [],
+        },
+      ],
+      entityMap: {
+        "0": {
+          key: "5",
+          value: {
+            type: "MARKDOWN",
+            mutability: "Mutable",
+            data: {
+              markdown: "```python\nprint('hello from x article')\n```\n",
+            },
+          },
+        },
+      },
+    },
+  };
+
+  const { markdown } = formatArticleMarkdown(article);
+
+  expect(markdown).toContain("Before the snippet.");
+  expect(markdown).toContain("```python\nprint('hello from x article')\n```");
+  expect(markdown).toContain("After the snippet.");
+  expect(markdown).toBe(`# Atomic Markdown Example
+
+Before the snippet.
+
+\`\`\`python
+print('hello from x article')
+\`\`\`
+
+After the snippet.`);
+});
+
+test("formatArticleMarkdown renders article video media as poster plus video link", () => {
+  const posterUrl = "https://pbs.twimg.com/amplify_video_thumb/123/img/poster.jpg";
+  const videoUrl = "https://video.twimg.com/amplify_video/123/vid/avc1/720x720/demo.mp4?tag=21";
+  const article = {
+    title: "Video Example",
+    content_state: {
+      blocks: [
+        {
+          type: "unstyled",
+          text: "Intro text.",
+          entityRanges: [],
+        },
+        {
+          type: "atomic",
+          text: " ",
+          entityRanges: [{ key: 0, offset: 0, length: 1 }],
+        },
+      ],
+      entityMap: {
+        "0": {
+          key: "0",
+          value: {
+            type: "MEDIA",
+            mutability: "Immutable",
+            data: {
+              caption: "Demo reel",
+              mediaItems: [{ mediaId: "vid-1" }],
+            },
+          },
+        },
+      },
+    },
+    media_entities: [
+      {
+        media_id: "vid-1",
+        media_info: {
+          __typename: "ApiVideo",
+          preview_image: {
+            original_img_url: posterUrl,
+          },
+          variants: [
+            {
+              content_type: "video/mp4",
+              bit_rate: 256000,
+              url: videoUrl,
+            },
+          ],
+        },
+      },
+    ],
+  };
+
+  const { markdown } = formatArticleMarkdown(article);
+
+  expect(markdown).toContain("Intro text.");
+  expect(markdown).toContain(`![Demo reel](${posterUrl})`);
+  expect(markdown).toContain(`[video](${videoUrl})`);
+  expect(markdown).not.toContain(`![Demo reel](${videoUrl})`);
+  expect(markdown).not.toContain("## Media");
+});
+
+test("formatArticleMarkdown renders unused article videos in trailing media section", () => {
+  const posterUrl = "https://pbs.twimg.com/amplify_video_thumb/456/img/poster.jpg";
+  const videoUrl = "https://video.twimg.com/amplify_video/456/vid/avc1/1080x1080/demo.mp4?tag=21";
+  const article = {
+    title: "Trailing Media Example",
+    plain_text: "Body text.",
+    media_entities: [
+      {
+        media_id: "vid-2",
+        media_info: {
+          __typename: "ApiVideo",
+          preview_image: {
+            original_img_url: posterUrl,
+          },
+          variants: [
+            {
+              content_type: "video/mp4",
+              bit_rate: 832000,
+              url: videoUrl,
+            },
+          ],
+        },
+      },
+    ],
+  };
+
+  const { markdown, coverUrl } = formatArticleMarkdown(article);
+
+  expect(coverUrl).toBeNull();
+  expect(markdown).toContain("## Media");
+  expect(markdown).toContain(`![video](${posterUrl})`);
+  expect(markdown).toContain(`[video](${videoUrl})`);
+});
+
+test("formatArticleMarkdown keeps coverUrl as preview image for video cover media", () => {
+  const posterUrl = "https://pbs.twimg.com/amplify_video_thumb/789/img/poster.jpg";
+  const videoUrl = "https://video.twimg.com/amplify_video/789/vid/avc1/720x720/demo.mp4?tag=21";
+  const article = {
+    title: "Video Cover Example",
+    plain_text: "Body text.",
+    cover_media: {
+      media_info: {
+        __typename: "ApiVideo",
+        preview_image: {
+          original_img_url: posterUrl,
+        },
+        variants: [
+          {
+            content_type: "video/mp4",
+            bit_rate: 1280000,
+            url: videoUrl,
+          },
+        ],
+      },
+    },
+  };
+
+  const { coverUrl } = formatArticleMarkdown(article);
+
+  expect(coverUrl).toBe(posterUrl);
+});

skills/baoyu-danger-x-to-markdown/scripts/markdown.ts

@@ -18,6 +18,17 @@ export type FormatArticleOptions = {
   referencedTweets?: Map<string, ReferencedTweetInfo>;
 };
 
+type ResolvedMediaAsset =
+  | {
+      kind: "image";
+      url: string;
+    }
+  | {
+      kind: "video";
+      url: string;
+      posterUrl?: string;
+    };
+
 function coerceArticleEntity(value: unknown): ArticleEntity | null {
   if (!value || typeof value !== "object") return null;
   const candidate = value as ArticleEntity;
@@ -109,58 +120,127 @@ function resolveEntityEntry(
   return entityMap[String(entityKey)];
 }
 
-function resolveMediaUrl(info?: ArticleMediaInfo): string | undefined {
+function resolveVideoUrl(info?: ArticleMediaInfo): string | undefined {
   if (!info) return undefined;
-  if (info.original_img_url) return info.original_img_url;
-  if (info.preview_image?.original_img_url) return info.preview_image.original_img_url;
   const variants = info.variants ?? [];
   const mp4 = variants
     .filter((variant) => variant?.content_type?.includes("video"))
     .sort((a, b) => (b.bit_rate ?? 0) - (a.bit_rate ?? 0))[0];
-  return mp4?.url ?? variants[0]?.url;
+  return mp4?.url ?? variants.find((variant) => typeof variant?.url === "string")?.url;
 }
 
-function buildMediaById(article: ArticleEntity): Map<string, string> {
-  const map = new Map<string, string>();
+function resolveMediaAsset(info?: ArticleMediaInfo): ResolvedMediaAsset | undefined {
+  if (!info) return undefined;
+
+  const posterUrl = info.preview_image?.original_img_url ?? info.original_img_url;
+  const videoUrl = resolveVideoUrl(info);
+  if (videoUrl) {
+    return {
+      kind: "video",
+      url: videoUrl,
+      posterUrl,
+    };
+  }
+
+  const imageUrl = info.original_img_url ?? info.preview_image?.original_img_url;
+  if (imageUrl) {
+    return {
+      kind: "image",
+      url: imageUrl,
+    };
+  }
+
+  return undefined;
+}
+
+function resolveFallbackMediaAsset(rawUrl?: string): ResolvedMediaAsset | undefined {
+  if (!rawUrl) return undefined;
+
+  if (/^https:\/\/video\.twimg\.com\//i.test(rawUrl) || /\.(mp4|m4v|mov|webm)(?:$|[?#])/i.test(rawUrl)) {
+    return {
+      kind: "video",
+      url: rawUrl,
+    };
+  }
+
+  return {
+    kind: "image",
+    url: rawUrl,
+  };
+}
+
+function resolveCoverUrl(info?: ArticleMediaInfo): string | undefined {
+  if (!info) return undefined;
+  return info.original_img_url ?? info.preview_image?.original_img_url;
+}
+
+function buildMediaIdentity(asset: ResolvedMediaAsset): string {
+  return asset.kind === "video"
+    ? `video:${asset.url}:${asset.posterUrl ?? ""}`
+    : `image:${asset.url}`;
+}
+
+function renderMediaLines(
+  asset: ResolvedMediaAsset,
+  altText: string,
+  usedUrls: Set<string>
+): string[] {
+  if (asset.kind === "video") {
+    const lines: string[] = [];
+    if (asset.posterUrl && !usedUrls.has(asset.posterUrl)) {
+      usedUrls.add(asset.posterUrl);
+      lines.push(`![${altText || "video"}](${asset.posterUrl})`);
+    }
+    if (!usedUrls.has(asset.url)) {
+      usedUrls.add(asset.url);
+      lines.push(`[video](${asset.url})`);
+    }
+    return lines;
+  }
+
+  if (usedUrls.has(asset.url)) {
+    return [];
+  }
+
+  usedUrls.add(asset.url);
+  return [`![${altText}](${asset.url})`];
+}
+
+function buildMediaById(article: ArticleEntity): Map<string, ResolvedMediaAsset> {
+  const map = new Map<string, ResolvedMediaAsset>();
   for (const entity of article.media_entities ?? []) {
     if (!entity?.media_id) continue;
-    const url = resolveMediaUrl(entity.media_info);
-    if (url) {
-      map.set(entity.media_id, url);
+    const asset = resolveMediaAsset(entity.media_info);
+    if (asset) {
+      map.set(entity.media_id, asset);
     }
   }
   return map;
 }
 
-function collectMediaUrls(
-  article: ArticleEntity,
-  usedUrls: Set<string>,
-  excludeUrl?: string
-): string[] {
-  const urls: string[] = [];
-  const addUrl = (url?: string) => {
-    if (!url) return;
-    if (excludeUrl && url === excludeUrl) {
-      usedUrls.add(url);
-      return;
-    }
-    if (usedUrls.has(url)) return;
-    usedUrls.add(url);
-    urls.push(url);
+function collectMediaAssets(article: ArticleEntity): ResolvedMediaAsset[] {
+  const assets: ResolvedMediaAsset[] = [];
+  const seen = new Set<string>();
+  const addAsset = (asset?: ResolvedMediaAsset) => {
+    if (!asset) return;
+    const identity = buildMediaIdentity(asset);
+    if (seen.has(identity)) return;
+    seen.add(identity);
+    assets.push(asset);
   };
 
   for (const entity of article.media_entities ?? []) {
-    addUrl(resolveMediaUrl(entity?.media_info));
+    addAsset(resolveMediaAsset(entity?.media_info));
   }
 
-  return urls;
+  return assets;
 }
 
 function resolveEntityMediaLines(
   entityKey: number | undefined,
   entityMap: ArticleContentState["entityMap"] | undefined,
   entityLookup: EntityLookup,
-  mediaById: Map<string, string>,
+  mediaById: Map<string, ResolvedMediaAsset>,
   usedUrls: Set<string>
 ): string[] {
   if (entityKey === undefined) return [];
@@ -182,17 +262,16 @@ function resolveEntityMediaLines(
         : typeof item?.media_id === "string"
           ? item.media_id
           : undefined;
-    const url = mediaId ? mediaById.get(mediaId) : undefined;
-    if (url && !usedUrls.has(url)) {
-      usedUrls.add(url);
-      lines.push(`![${altText}](${url})`);
+    const asset = mediaId ? mediaById.get(mediaId) : undefined;
+    if (asset) {
+      lines.push(...renderMediaLines(asset, altText, usedUrls));
     }
   }
 
   const fallbackUrl = typeof value.data?.url === "string" ? value.data.url : undefined;
-  if (fallbackUrl && !usedUrls.has(fallbackUrl)) {
-    usedUrls.add(fallbackUrl);
-    lines.push(`![${altText}](${fallbackUrl})`);
+  const fallbackAsset = resolveFallbackMediaAsset(fallbackUrl);
+  if (fallbackAsset) {
+    lines.push(...renderMediaLines(fallbackAsset, altText, usedUrls));
   }
 
   return lines;
@@ -237,6 +316,22 @@ function resolveEntityTweetLines(
   return lines;
 }
 
+function resolveEntityMarkdownLines(
+  entityKey: number | undefined,
+  entityMap: ArticleContentState["entityMap"] | undefined,
+  entityLookup: EntityLookup
+): string[] {
+  if (entityKey === undefined) return [];
+  const entry = resolveEntityEntry(entityKey, entityMap, entityLookup);
+  const value = entry?.value;
+  if (!value || value.type !== "MARKDOWN") return [];
+
+  const markdown = typeof value.data?.markdown === "string" ? value.data.markdown : "";
+  const normalized = markdown.replace(/\r\n/g, "\n").trimEnd();
+  if (!normalized) return [];
+  return normalized.split("\n");
+}
+
 function buildMediaLinkMap(
   entityMap: ArticleContentState["entityMap"] | undefined
 ): Map<number, string> {
@@ -330,7 +425,7 @@ function renderContentBlocks(
   blocks: ArticleBlock[],
   entityMap: ArticleContentState["entityMap"] | undefined,
   entityLookup: EntityLookup,
-  mediaById: Map<string, string>,
+  mediaById: Map<string, ResolvedMediaAsset>,
   usedUrls: Set<string>,
   mediaLinkMap: Map<number, string>,
   referencedTweets?: Map<string, ReferencedTweetInfo>
@@ -397,6 +492,16 @@ function renderContentBlocks(
     return [...new Set(linkLines)];
   };
 
+  const collectMarkdownLines = (block: ArticleBlock): string[] => {
+    const ranges = Array.isArray(block.entityRanges) ? block.entityRanges : [];
+    const markdownLines: string[] = [];
+    for (const range of ranges) {
+      if (typeof range?.key !== "number") continue;
+      markdownLines.push(...resolveEntityMarkdownLines(range.key, entityMap, entityLookup));
+    }
+    return markdownLines;
+  };
+
   const pushTrailingMedia = (mediaLines: string[]) => {
     if (mediaLines.length > 0) {
       pushBlock(mediaLines, "media");
@@ -441,6 +546,11 @@ function renderContentBlocks(
         pushBlock(tweetLines, "quote");
       }
 
+      const markdownLines = collectMarkdownLines(block);
+      if (markdownLines.length > 0) {
+        pushBlock(markdownLines, "text");
+      }
+
       const mediaLines = collectMediaLines(block);
       if (mediaLines.length > 0) {
         pushBlock(mediaLines, "media");
@@ -571,7 +681,7 @@ export function formatArticleMarkdown(
     lines.push(`# ${title}`);
   }
 
-  const coverUrl = resolveMediaUrl(candidate.cover_media?.media_info) ?? null;
+  const coverUrl = resolveCoverUrl(candidate.cover_media?.media_info) ?? null;
   if (coverUrl) {
     usedUrls.add(coverUrl);
   }
@@ -602,12 +712,13 @@ export function formatArticleMarkdown(
     lines.push(candidate.preview_text.trim());
   }
 
-  const mediaUrls = collectMediaUrls(candidate, usedUrls, coverUrl ?? undefined);
-  if (mediaUrls.length > 0) {
+  const trailingMediaLines: string[] = [];
+  for (const asset of collectMediaAssets(candidate)) {
+    trailingMediaLines.push(...renderMediaLines(asset, "", usedUrls));
+  }
+  if (trailingMediaLines.length > 0) {
     lines.push("", "## Media", "");
-    for (const url of mediaUrls) {
-      lines.push(`![](${url})`);
-    }
+    lines.push(...trailingMediaLines);
   }
 
   return { markdown: lines.join("\n").trimEnd(), coverUrl };

skills/baoyu-danger-x-to-markdown/scripts/media-localizer.ts

@@ -202,6 +202,13 @@ function toHighResUrl(rawUrl: string): string {
   }
 }
 
+function isPlausibleMediaUrl(rawUrl: string): boolean {
+  const ext = resolveExtensionFromUrl(rawUrl);
+  if (ext && (IMAGE_EXTENSIONS.has(ext) || VIDEO_EXTENSIONS.has(ext))) return true;
+  if (resolveKindFromHostname(rawUrl) !== undefined) return true;
+  return false;
+}
+
 function collectMarkdownLinkCandidates(markdown: string): MarkdownLinkCandidate[] {
   const candidates: MarkdownLinkCandidate[] = [];
   const seen = new Set<string>();
@@ -221,10 +228,12 @@ function collectMarkdownLinkCandidates(markdown: string): MarkdownLinkCandidate[
     const label = match[1] ?? "";
     const rawUrl = match[3] ?? "";
     if (!rawUrl || seen.has(rawUrl)) continue;
+    const isImage = label.startsWith("![");
+    if (!isImage && !isPlausibleMediaUrl(rawUrl)) continue;
     seen.add(rawUrl);
     candidates.push({
       url: rawUrl,
-      hint: label.startsWith("![") ? "image" : "unknown",
+      hint: isImage ? "image" : "unknown",
     });
   }
 

skills/baoyu-danger-x-to-markdown/scripts/types.ts

@@ -38,6 +38,7 @@ export type ArticleEntityMapEntry = {
     mutability?: string;
     data?: {
       caption?: string;
+      markdown?: string;
       mediaItems?: ArticleEntityMapMediaItem[];
       url?: string;
       tweetId?: string;

skills/baoyu-image-gen/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: baoyu-image-gen
 description: AI image generation with OpenAI, Google, OpenRouter, DashScope, Jimeng, Seedream and Replicate APIs. Supports text-to-image, reference images, aspect ratios, and batch generation from saved prompt files. Sequential by default; use batch parallel generation when the user already has multiple prompts or wants stable multi-image throughput. Use when user asks to generate, create, or draw images.
-version: 1.56.2
+version: 1.56.3
 metadata:
   openclaw:
     homepage: https://github.com/JimLiu/baoyu-skills#baoyu-image-gen
@@ -74,7 +74,7 @@ ${BUN_X} {baseDir}/scripts/main.ts --prompt "A cat" --image out.png --quality 2k
 # From prompt files
 ${BUN_X} {baseDir}/scripts/main.ts --promptfiles system.md content.md --image out.png
 
-# With reference images (Google, OpenAI, OpenRouter, or Replicate)
+# With reference images (Google, OpenAI, OpenRouter, Replicate, or Seedream 4.0/4.5/5.0)
 ${BUN_X} {baseDir}/scripts/main.ts --prompt "Make blue" --image out.png --ref source.png
 
 # With reference images (explicit provider/model)
@@ -153,7 +153,7 @@ Paths in `promptFiles`, `image`, and `ref` are resolved relative to the batch fi
 | `--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. Supported by Google multimodal, OpenAI GPT Image edits, OpenRouter multimodal models, and Replicate. Not supported by Jimeng or Seedream |
+| `--ref <files...>` | Reference images. Supported by Google multimodal, OpenAI GPT Image edits, OpenRouter multimodal models, Replicate, and Seedream 5.0/4.5/4.0. Not supported by Jimeng, Seedream 3.0, or removed SeedEdit 3.0 |
 | `--n <count>` | Number of images |
 | `--json` | JSON output |
 

skills/baoyu-image-gen/scripts/main.test.ts

@@ -216,6 +216,39 @@ test("detectProvider selects an available ref-capable provider for reference-ima
   );
 });
 
+test("detectProvider infers Seedream from model id and allows Seedream reference-image workflows", (t) => {
+  useEnv(t, {
+    GOOGLE_API_KEY: null,
+    OPENAI_API_KEY: null,
+    OPENROUTER_API_KEY: null,
+    DASHSCOPE_API_KEY: null,
+    REPLICATE_API_TOKEN: null,
+    JIMENG_ACCESS_KEY_ID: null,
+    JIMENG_SECRET_ACCESS_KEY: null,
+    ARK_API_KEY: "ark-key",
+  });
+
+  assert.equal(
+    detectProvider(
+      makeArgs({
+        model: "doubao-seedream-4-5-251128",
+        referenceImages: ["ref.png"],
+      }),
+    ),
+    "seedream",
+  );
+
+  assert.equal(
+    detectProvider(
+      makeArgs({
+        provider: "seedream",
+        referenceImages: ["ref.png"],
+      }),
+    ),
+    "seedream",
+  );
+});
+
 test("batch worker and provider-rate-limit configuration prefer env over EXTEND config", (t) => {
   useEnv(t, {
     BAOYU_IMAGE_GEN_MAX_WORKERS: "12",
@@ -294,6 +327,7 @@ test("loadBatchTasks and createTaskArgs resolve batch-relative paths", async (t)
 
 test("path normalization, worker count, and retry classification follow expected rules", () => {
   assert.match(normalizeOutputImagePath("out/sample"), /out[\\/]+sample\.png$/);
+  assert.match(normalizeOutputImagePath("out/sample", ".jpg"), /out[\\/]+sample\.jpg$/);
   assert.match(normalizeOutputImagePath("out/sample.webp"), /out[\\/]+sample\.webp$/);
 
   assert.equal(getWorkerCount(8, null, 3), 3);

skills/baoyu-image-gen/scripts/main.ts

@@ -14,6 +14,8 @@ import type {
 type ProviderModule = {
   getDefaultModel: () => string;
   generateImage: (prompt: string, model: string, args: CliArgs) => Promise<Uint8Array>;
+  validateArgs?: (model: string, args: CliArgs) => void;
+  getDefaultOutputExtension?: (model: string, args: CliArgs) => string;
 };
 
 type PreparedTask = {
@@ -78,7 +80,7 @@ Options:
   --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 multimodal, OpenAI GPT Image edits, OpenRouter multimodal, or Replicate)
+  --ref <files...>          Reference images (Google, OpenAI, OpenRouter, Replicate, 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
@@ -560,11 +562,17 @@ async function readPromptFromStdin(): Promise<string | null> {
   }
 }
 
-export function normalizeOutputImagePath(p: string): string {
+export function normalizeOutputImagePath(p: string, defaultExtension = ".png"): string {
   const full = path.resolve(p);
   const ext = path.extname(full);
   if (ext) return full;
-  return `${full}.png`;
+  return `${full}${defaultExtension}`;
+}
+
+function inferProviderFromModel(model: string | null): Provider | null {
+  if (!model) return null;
+  if (model.includes("seedream") || model.includes("seededit")) return "seedream";
+  return null;
 }
 
 export function detectProvider(args: CliArgs): Provider {
@@ -574,10 +582,11 @@ export function detectProvider(args: CliArgs): Provider {
     args.provider !== "google" &&
     args.provider !== "openai" &&
     args.provider !== "openrouter" &&
-    args.provider !== "replicate"
+    args.provider !== "replicate" &&
+    args.provider !== "seedream"
   ) {
     throw new Error(
-      "Reference images require a ref-capable provider. Use --provider google (Gemini multimodal), --provider openai (GPT Image edits), --provider openrouter (OpenRouter multimodal), or --provider replicate."
+      "Reference images require a ref-capable provider. Use --provider google (Gemini multimodal), --provider openai (GPT Image edits), --provider openrouter (OpenRouter multimodal), --provider replicate, or --provider seedream for supported Seedream models."
     );
   }
 
@@ -590,14 +599,23 @@ export function detectProvider(args: CliArgs): Provider {
   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;
+  const modelProvider = inferProviderFromModel(args.model);
+
+  if (modelProvider === "seedream") {
+    if (!hasSeedream) {
+      throw new Error("Model looks like a Volcengine ARK image model, but ARK_API_KEY is not set.");
+    }
+    return "seedream";
+  }
 
   if (args.referenceImages.length > 0) {
     if (hasGoogle) return "google";
     if (hasOpenai) return "openai";
     if (hasOpenrouter) return "openrouter";
     if (hasReplicate) return "replicate";
+    if (hasSeedream) return "seedream";
     throw new Error(
-      "Reference images require Google, OpenAI, OpenRouter, or Replicate. Set GOOGLE_API_KEY/GEMINI_API_KEY, OPENAI_API_KEY, OPENROUTER_API_KEY, or REPLICATE_API_TOKEN, or remove --ref."
+      "Reference images require Google, OpenAI, OpenRouter, Replicate, or supported Seedream models. Set GOOGLE_API_KEY/GEMINI_API_KEY, OPENAI_API_KEY, OPENROUTER_API_KEY, REPLICATE_API_TOKEN, or ARK_API_KEY, or remove --ref."
     );
   }
 
@@ -701,6 +719,8 @@ async function prepareSingleTask(args: CliArgs, extendConfig: Partial<ExtendConf
   const provider = detectProvider(args);
   const providerModule = await loadProviderModule(provider);
   const model = getModelForProvider(provider, args.model, extendConfig, providerModule);
+  providerModule.validateArgs?.(model, args);
+  const defaultOutputExtension = providerModule.getDefaultOutputExtension?.(model, args) ?? ".png";
 
   return {
     id: "single",
@@ -708,7 +728,7 @@ async function prepareSingleTask(args: CliArgs, extendConfig: Partial<ExtendConf
     args,
     provider,
     model,
-    outputPath: normalizeOutputImagePath(args.imagePath),
+    outputPath: normalizeOutputImagePath(args.imagePath, defaultOutputExtension),
     providerModule,
   };
 }
@@ -784,13 +804,15 @@ async function prepareBatchTasks(
     const provider = detectProvider(taskArgs);
     const providerModule = await loadProviderModule(provider);
     const model = getModelForProvider(provider, taskArgs.model, extendConfig, providerModule);
+    providerModule.validateArgs?.(model, taskArgs);
+    const defaultOutputExtension = providerModule.getDefaultOutputExtension?.(model, taskArgs) ?? ".png";
     prepared.push({
       id: task.id || `task-${String(i + 1).padStart(2, "0")}`,
       prompt,
       args: taskArgs,
       provider,
       model,
-      outputPath: normalizeOutputImagePath(taskArgs.imagePath),
+      outputPath: normalizeOutputImagePath(taskArgs.imagePath, defaultOutputExtension),
       providerModule,
     });
   }

skills/baoyu-image-gen/scripts/providers/seedream.test.ts

@@ -0,0 +1,244 @@
+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 {
+  buildImageInput,
+  buildRequestBody,
+  generateImage,
+  getDefaultOutputExtension,
+  resolveSeedreamSize,
+  validateArgs,
+} from "./seedream.ts";
+
+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,
+  };
+}
+
+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;
+      }
+    }
+  });
+}
+
+async function makeTempPng(t: TestContext, name: string): Promise<string> {
+  const dir = await fs.mkdtemp(path.join(os.tmpdir(), "seedream-test-"));
+  t.after(() => fs.rm(dir, { recursive: true, force: true }));
+
+  const filePath = path.join(dir, name);
+  const png1x1 =
+    "iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAQAAAC1HAwCAAAAC0lEQVR42mP8/x8AAwMCAO+a7m0AAAAASUVORK5CYII=";
+  await fs.writeFile(filePath, Buffer.from(png1x1, "base64"));
+  return filePath;
+}
+
+test("Seedream request body and default extensions follow official model capabilities", () => {
+  const five = buildRequestBody(
+    "A robot illustrator",
+    "doubao-seedream-5-0-260128",
+    makeArgs(),
+  );
+  assert.equal(five.size, "2K");
+  assert.equal(five.response_format, "url");
+  assert.equal(five.output_format, "png");
+  assert.equal(getDefaultOutputExtension("doubao-seedream-5-0-260128"), ".png");
+
+  const fourFive = buildRequestBody(
+    "A robot illustrator",
+    "doubao-seedream-4-5-251128",
+    makeArgs(),
+  );
+  assert.equal(fourFive.size, "2K");
+  assert.equal(fourFive.response_format, "url");
+  assert.ok(!("output_format" in fourFive));
+  assert.equal(getDefaultOutputExtension("doubao-seedream-4-5-251128"), ".jpg");
+
+  assert.throws(
+    () =>
+      buildRequestBody(
+        "Change the bubbles into hearts",
+        "doubao-seededit-3-0-i2i-250628",
+        makeArgs({ referenceImages: ["ref.png"] }),
+        "data:image/png;base64,AAAA",
+      ),
+    /no longer supported/,
+  );
+});
+
+test("Seedream size selection validates model-specific presets", () => {
+  assert.equal(
+    resolveSeedreamSize("doubao-seedream-4-0-250828", makeArgs({ quality: "normal" })),
+    "1K",
+  );
+  assert.equal(
+    resolveSeedreamSize("doubao-seedream-3-0-t2i-250415", makeArgs({ quality: "2k" })),
+    "2048x2048",
+  );
+
+  assert.throws(
+    () =>
+      resolveSeedreamSize("doubao-seedream-5-0-260128", makeArgs({ size: "4K" })),
+    /only supports 2K, 3K/,
+  );
+  assert.throws(
+    () =>
+      resolveSeedreamSize("doubao-seedream-3-0-t2i-250415", makeArgs({ imageSize: "2K" })),
+    /only supports explicit WxH sizes/,
+  );
+  assert.throws(
+    () =>
+      resolveSeedreamSize("doubao-seededit-3-0-i2i-250628", makeArgs({ size: "1024x1024" })),
+    /no longer supported/,
+  );
+});
+
+test("Seedream reference-image support is model-specific", () => {
+  assert.doesNotThrow(() =>
+    validateArgs(
+      "doubao-seedream-5-0-260128",
+      makeArgs({ referenceImages: ["a.png", "b.png"] }),
+    ),
+  );
+
+  assert.throws(
+    () =>
+      validateArgs(
+        "doubao-seedream-3-0-t2i-250415",
+        makeArgs({ referenceImages: ["a.png"] }),
+      ),
+    /does not support reference images/,
+  );
+
+  assert.throws(
+    () =>
+      validateArgs(
+        "doubao-seededit-3-0-i2i-250628",
+        makeArgs(),
+      ),
+    /no longer supported/,
+  );
+
+  assert.throws(
+    () =>
+      validateArgs(
+        "ep-20260315171508-t8br2",
+        makeArgs({ referenceImages: ["a.png"] }),
+      ),
+    /require a known model ID/,
+  );
+});
+
+test("Seedream image input encodes local references as data URLs", async (t) => {
+  const refOne = await makeTempPng(t, "one.png");
+  const refTwo = await makeTempPng(t, "two.png");
+
+  const single = await buildImageInput("doubao-seedream-4-5-251128", [refOne]);
+  assert.match(String(single), /^data:image\/png;base64,/);
+
+  const multiple = await buildImageInput("doubao-seedream-5-0-260128", [refOne, refTwo]);
+  assert.ok(Array.isArray(multiple));
+  assert.equal(multiple.length, 2);
+});
+
+test("Seedream generateImage posts the documented response_format and downloads the returned URL", async (t) => {
+  useEnv(t, { ARK_API_KEY: "test-key", SEEDREAM_BASE_URL: null });
+
+  const originalFetch = globalThis.fetch;
+  t.after(() => {
+    globalThis.fetch = originalFetch;
+  });
+
+  const calls: Array<{
+    input: string;
+    init?: RequestInit;
+  }> = [];
+
+  globalThis.fetch = async (input, init) => {
+    calls.push({
+      input: String(input),
+      init,
+    });
+
+    if (calls.length === 1) {
+      return Response.json({
+        model: "doubao-seedream-4-5-251128",
+        created: 1740000000,
+        data: [
+          {
+            url: "https://example.com/generated-image",
+            size: "2048x2048",
+          },
+        ],
+        usage: {
+          generated_images: 1,
+          output_tokens: 1,
+          total_tokens: 1,
+        },
+      });
+    }
+
+    return new Response(Uint8Array.from([7, 8, 9]), {
+      status: 200,
+      headers: { "Content-Type": "image/jpeg" },
+    });
+  };
+
+  const image = await generateImage(
+    "A robot illustrator",
+    "doubao-seedream-4-5-251128",
+    makeArgs(),
+  );
+
+  assert.deepEqual([...image], [7, 8, 9]);
+  assert.equal(calls.length, 2);
+  assert.equal(
+    calls[0]?.input,
+    "https://ark.cn-beijing.volces.com/api/v3/images/generations",
+  );
+
+  const requestBody = JSON.parse(String(calls[0]?.init?.body)) as Record<string, unknown>;
+  assert.equal(requestBody.model, "doubao-seedream-4-5-251128");
+  assert.equal(requestBody.size, "2K");
+  assert.equal(requestBody.response_format, "url");
+  assert.ok(!("output_format" in requestBody));
+  assert.equal(calls[1]?.input, "https://example.com/generated-image");
+});

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

@@ -1,5 +1,50 @@
+import path from "node:path";
+import { readFile } from "node:fs/promises";
+
 import type { CliArgs } from "../types";
 
+export type SeedreamModelFamily =
+  | "seedream5"
+  | "seedream45"
+  | "seedream40"
+  | "seedream30"
+  | "unknown";
+
+type SeedreamRequestImage = string | string[];
+
+type SeedreamRequestBody = {
+  model: string;
+  prompt: string;
+  size: string;
+  response_format: "url";
+  watermark: boolean;
+  image?: SeedreamRequestImage;
+  output_format?: "png";
+};
+
+type SeedreamImageResponse = {
+  model?: string;
+  created?: number;
+  data?: Array<{
+    url?: string;
+    b64_json?: string;
+    size?: string;
+    error?: {
+      code?: string;
+      message?: string;
+    };
+  }>;
+  usage?: {
+    generated_images: number;
+    output_tokens: number;
+    total_tokens: number;
+  };
+  error?: {
+    code?: string;
+    message?: string;
+  };
+};
+
 export function getDefaultModel(): string {
   return process.env.SEEDREAM_IMAGE_MODEL || "doubao-seedream-5-0-260128";
 }
@@ -12,46 +57,252 @@ function getBaseUrl(): string {
   return process.env.SEEDREAM_BASE_URL || "https://ark.cn-beijing.volces.com/api/v3";
 }
 
-/**
- * Convert aspect ratio to Seedream size format
- * Seedream API accepts: "2k" (default), "3k", or WIDTHxHEIGHT format
- * Note: API uses lowercase "2k"/"3k", not "2K"/"3K"
- */
-function getSeedreamSize(ar: string | null, quality: CliArgs["quality"], imageSize?: string | null): string {
-  // If explicit size is provided
-  if (imageSize) {
-    const upper = imageSize.toUpperCase();
-    if (upper === "2K" || upper === "3K") {
-      return upper.toLowerCase(); // API expects "2k" or "3k"
-    }
-    // For widthxheight format, pass through as-is
-    if (imageSize.includes("x")) {
-      return imageSize;
-    }
+function parsePixelSize(value: string): { width: number; height: number } | null {
+  const match = value.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;
   }
 
-  // Default to 2k (smallest option supported by API)
-  return "2k";
+  return { width, height };
 }
 
-type SeedreamImageResponse = {
-  model: string;
-  created: number;
-  data: Array<{
-    url: string;
-    size: string;
-  }>;
-  usage: {
-    generated_images: number;
-    output_tokens: number;
-    total_tokens: number;
+function normalizePixelSize(value: string): string | null {
+  const parsed = parsePixelSize(value);
+  if (!parsed) return null;
+  return `${parsed.width}x${parsed.height}`;
+}
+
+function normalizeSizePreset(value: string): string | null {
+  const upper = value.trim().toUpperCase();
+  if (upper === "ADAPTIVE") return "adaptive";
+  if (upper === "1K" || upper === "2K" || upper === "3K" || upper === "4K") return upper;
+  return null;
+}
+
+function normalizeSizeValue(value: string): string | null {
+  return normalizeSizePreset(value) ?? normalizePixelSize(value);
+}
+
+function getMimeType(filename: string): string {
+  const ext = path.extname(filename).toLowerCase();
+  if (ext === ".jpg" || ext === ".jpeg") return "image/jpeg";
+  if (ext === ".webp") return "image/webp";
+  if (ext === ".gif") return "image/gif";
+  if (ext === ".bmp") return "image/bmp";
+  if (ext === ".tiff" || ext === ".tif") return "image/tiff";
+  return "image/png";
+}
+
+async function readImageAsDataUrl(filePath: string): Promise<string> {
+  const bytes = await readFile(filePath);
+  return `data:${getMimeType(filePath)};base64,${bytes.toString("base64")}`;
+}
+
+export function getModelFamily(model: string): SeedreamModelFamily {
+  const normalized = model.trim();
+  if (/^doubao-seedream-5-0(?:-lite)?-\d+$/.test(normalized)) return "seedream5";
+  if (/^doubao-seedream-4-5-\d+$/.test(normalized)) return "seedream45";
+  if (/^doubao-seedream-4-0-\d+$/.test(normalized)) return "seedream40";
+  if (/^doubao-seedream-3-0-t2i-\d+$/.test(normalized)) return "seedream30";
+  return "unknown";
+}
+
+function isRemovedSeededitModel(model: string): boolean {
+  return /^doubao-seededit-3-0-i2i-\d+$/.test(model.trim());
+}
+
+function assertSupportedModel(model: string): void {
+  if (isRemovedSeededitModel(model)) {
+    throw new Error(
+      `${model} is no longer supported. SeedEdit 3.0 support has been removed from this tool; use Seedream 5.0/4.5/4.0/3.0 instead.`
+    );
+  }
+}
+
+export function supportsReferenceImages(model: string): boolean {
+  const family = getModelFamily(model);
+  return family === "seedream5" || family === "seedream45" || family === "seedream40";
+}
+
+function supportsOutputFormat(model: string): boolean {
+  return getModelFamily(model) === "seedream5";
+}
+
+export function getDefaultOutputExtension(model: string): ".png" | ".jpg" {
+  assertSupportedModel(model);
+  return supportsOutputFormat(model) ? ".png" : ".jpg";
+}
+
+export function getDefaultSeedreamSize(model: string, args: CliArgs): string {
+  assertSupportedModel(model);
+  const family = getModelFamily(model);
+
+  if (family === "seedream5") return "2K";
+  if (family === "seedream45") return "2K";
+  if (family === "seedream40") return args.quality === "normal" ? "1K" : "2K";
+  if (family === "seedream30") return args.quality === "2k" ? "2048x2048" : "1024x1024";
+  return "2K";
+}
+
+export function resolveSeedreamSize(model: string, args: CliArgs): string {
+  assertSupportedModel(model);
+  const family = getModelFamily(model);
+  const requested = args.size || args.imageSize || null;
+  const normalized = requested ? normalizeSizeValue(requested) : null;
+
+  if (!normalized) {
+    return getDefaultSeedreamSize(model, args);
+  }
+
+  if (family === "seedream30") {
+    const pixelSize = normalizePixelSize(normalized);
+    if (!pixelSize) {
+      throw new Error("Seedream 3.0 only supports explicit WxH sizes such as 1024x1024.");
+    }
+    return pixelSize;
+  }
+
+  if (family === "seedream5") {
+    if (normalized === "4K" || normalized === "1K" || normalized === "adaptive") {
+      throw new Error("Seedream 5.0 only supports 2K, 3K, or explicit WxH sizes.");
+    }
+    return normalized;
+  }
+
+  if (family === "seedream45") {
+    if (normalized === "1K" || normalized === "3K" || normalized === "adaptive") {
+      throw new Error("Seedream 4.5 only supports 2K, 4K, or explicit WxH sizes.");
+    }
+    return normalized;
+  }
+
+  if (family === "seedream40") {
+    if (normalized === "3K" || normalized === "adaptive") {
+      throw new Error("Seedream 4.0 only supports 1K, 2K, 4K, or explicit WxH sizes.");
+    }
+    return normalized;
+  }
+
+  if (normalized === "adaptive") {
+    throw new Error("Adaptive size is not supported by Seedream image generation.");
+  }
+
+  if (normalized === "1K" || normalized === "3K" || normalized === "4K") {
+    throw new Error(
+      "Unknown Seedream model ID. Use a documented model ID or pass an explicit WxH size instead of preset imageSize."
+    );
+  }
+
+  return normalized;
+}
+
+export function validateArgs(model: string, args: CliArgs): void {
+  assertSupportedModel(model);
+  const family = getModelFamily(model);
+  const refCount = args.referenceImages.length;
+
+  if (refCount === 0) {
+    resolveSeedreamSize(model, args);
+    return;
+  }
+
+  if (family === "unknown") {
+    throw new Error(
+      "Reference images with Seedream require a known model ID. Use Seedream 5.0/4.5/4.0 model IDs instead of an endpoint ID."
+    );
+  }
+
+  if (!supportsReferenceImages(model)) {
+    throw new Error(`${model} does not support reference images.`);
+  }
+
+  if ((family === "seedream5" || family === "seedream45" || family === "seedream40") && refCount > 14) {
+    throw new Error(`${model} supports at most 14 reference images.`);
+  }
+
+  resolveSeedreamSize(model, args);
+}
+
+export async function buildImageInput(
+  model: string,
+  referenceImages: string[],
+): Promise<SeedreamRequestImage | undefined> {
+  if (referenceImages.length === 0) return undefined;
+  assertSupportedModel(model);
+
+  const encoded = await Promise.all(referenceImages.map((refPath) => readImageAsDataUrl(refPath)));
+
+  return encoded.length === 1 ? encoded[0]! : encoded;
+}
+
+export function buildRequestBody(
+  prompt: string,
+  model: string,
+  args: CliArgs,
+  imageInput?: SeedreamRequestImage,
+): SeedreamRequestBody {
+  validateArgs(model, args);
+
+  const requestBody: SeedreamRequestBody = {
+    model,
+    prompt,
+    size: resolveSeedreamSize(model, args),
+    response_format: "url",
+    watermark: false,
   };
-};
+
+  if (imageInput) {
+    requestBody.image = imageInput;
+  }
+
+  if (supportsOutputFormat(model)) {
+    requestBody.output_format = "png";
+  }
+
+  return requestBody;
+}
+
+async function downloadImage(url: string): Promise<Uint8Array> {
+  const imgResponse = await fetch(url);
+  if (!imgResponse.ok) {
+    throw new Error(`Failed to download image from ${url}`);
+  }
+
+  const buffer = await imgResponse.arrayBuffer();
+  return new Uint8Array(buffer);
+}
+
+export async function extractImageFromResponse(result: SeedreamImageResponse): Promise<Uint8Array> {
+  const first = result.data?.find((item) => item.url || item.b64_json || item.error);
+
+  if (!first) {
+    throw new Error("No image data in Seedream response");
+  }
+
+  if (first.error) {
+    throw new Error(first.error.message || "Seedream returned an image generation error");
+  }
+
+  if (first.b64_json) {
+    return Uint8Array.from(Buffer.from(first.b64_json, "base64"));
+  }
+
+  if (first.url) {
+    console.error(`Downloading image from ${first.url}...`);
+    return downloadImage(first.url);
+  }
+
+  throw new Error("No image URL or base64 data in Seedream response");
+}
 
 export async function generateImage(
   prompt: string,
   model: string,
-  args: CliArgs
+  args: CliArgs,
 ): Promise<Uint8Array> {
   const apiKey = getApiKey();
   if (!apiKey) {
@@ -61,20 +312,13 @@ export async function generateImage(
     );
   }
 
-  const baseUrl = getBaseUrl();
-  const size = getSeedreamSize(args.aspectRatio, args.quality, args.imageSize);
+  validateArgs(model, args);
+  const imageInput = await buildImageInput(model, args.referenceImages);
+  const requestBody = buildRequestBody(prompt, model, args, imageInput);
 
-  console.error(`Calling Seedream API (${model}) with size: ${size}`);
+  console.error(`Calling Seedream API (${model}) with size: ${requestBody.size}`);
 
-  const requestBody = {
-    model,
-    prompt,
-    size,
-    output_format: "png",
-    watermark: false,
-  };
-
-  const response = await fetch(`${baseUrl}/images/generations`, {
+  const response = await fetch(`${getBaseUrl()}/images/generations`, {
     method: "POST",
     headers: {
       "Content-Type": "application/json",
@@ -89,23 +333,9 @@ export async function generateImage(
   }
 
   const result = (await response.json()) as SeedreamImageResponse;
-
-  if (!result.data || result.data.length === 0) {
-    throw new Error("No image data in Seedream response");
+  if (result.error) {
+    throw new Error(result.error.message || "Seedream API returned an error");
   }
 
-  const imageUrl = result.data[0].url;
-  if (!imageUrl) {
-    throw new Error("No image URL in Seedream response");
-  }
-
-  // Download image from URL
-  console.error(`Downloading image from ${imageUrl}...`);
-  const imgResponse = await fetch(imageUrl);
-  if (!imgResponse.ok) {
-    throw new Error(`Failed to download image from ${imageUrl}`);
-  }
-
-  const buffer = await imgResponse.arrayBuffer();
-  return new Uint8Array(buffer);
+  return extractImageFromResponse(result);
 }