Merge pull request #114 from modelstudioai/feat/token-plan-default-models

feat: update Token Plan defaults and support local image inputs
2026-09-14 19:49:23 +08:00 · 2026-07-22 10:52:35 +08:00
parent d04012b0a4 81539005cc
commit 440cbfe6ae
29 changed files with 711 additions and 82 deletions
@@ -20,6 +20,9 @@ interface ApiKeyLoginProfile {
  baseUrl: string;
  persistBaseUrl?: string;
  defaultTextModel?: string;
+  defaultVideoModel?: string;
+  defaultImageToVideoModel?: string;
+  defaultReferenceToVideoModel?: string;
  defaultImageModel?: string;
  persistPatch?: AuthPersistPatch;
 }
@@ -54,17 +57,18 @@ export async function validateAndPersistApiKey(
  const persistBaseUrl = profile.persistBaseUrl
    ? normalizeModelBaseUrl(profile.persistBaseUrl)
    : undefined;
+  const validationModel = profile.defaultTextModel || "qwen3.7-max";
  const requestOpts = {
    url: baseUrl + chatPath(),
    method: "POST",
    headers: { Authorization: `Bearer ${key}` },
    timeout: Math.min(deps.settings.timeout, 30),
    body: {
-      model: profile.defaultTextModel || "qwen3.7-max",
+      model: validationModel,
      messages: [{ role: "user", content: "hi" }],
      max_tokens: 1,
      stream: false,
-      enable_thinking: false,
+      enable_thinking: validationModel === "qwen3.8-max-preview",
    },
  };

@@ -88,6 +92,9 @@ export async function validateAndPersistApiKey(
    api_key: key,
    base_url: persistBaseUrl,
    default_text_model: profile.defaultTextModel,
+    default_video_model: profile.defaultVideoModel,
+    default_image_to_video_model: profile.defaultImageToVideoModel,
+    default_reference_to_video_model: profile.defaultReferenceToVideoModel,
    default_image_model: profile.defaultImageModel,
  });
 }
@@ -150,6 +150,9 @@ export default defineCommand({
      baseUrl: resolvedBaseUrl,
      persistBaseUrl,
      defaultTextModel: profilePreset?.defaultTextModel,
+      defaultVideoModel: profilePreset?.defaultVideoModel,
+      defaultImageToVideoModel: profilePreset?.defaultImageToVideoModel,
+      defaultReferenceToVideoModel: profilePreset?.defaultReferenceToVideoModel,
      defaultImageModel: profilePreset?.defaultImageModel,
    });
  },
@@ -13,6 +13,8 @@ export const VALID_KEYS = [
  "security_token",
  "default_text_model",
  "default_video_model",
+  "default_image_to_video_model",
+  "default_reference_to_video_model",
  "default_image_model",
  "default_speech_model",
  "default_omni_model",
@@ -41,6 +43,8 @@ export const KEY_ALIASES: Record<string, string> = {
  "security-token": "security_token",
  "default-text-model": "default_text_model",
  "default-video-model": "default_video_model",
+  "default-image-to-video-model": "default_image_to_video_model",
+  "default-reference-to-video-model": "default_reference_to_video_model",
  "default-image-model": "default_image_model",
  "default-speech-model": "default_speech_model",
  "default-omni-model": "default_omni_model",
@@ -22,6 +22,7 @@ import {
  resolveWatermark,
  ASYNC_FLAG,
  CONCURRENT_FLAG,
+  redactDataUri,
 } from "bailian-cli-core";
 import { poll } from "bailian-cli-runtime";
 import { downloadFile } from "bailian-cli-runtime";
@@ -31,10 +32,15 @@ import { resolveImageSize } from "bailian-cli-runtime";
 import { join } from "path";
 import { BOOL_FLAG_PROMPT_EXTEND_CLI_TRUE, BOOL_FLAG_WATERMARK } from "bailian-cli-runtime";

-const SYNC_MODEL_PREFIXES = ["qwen-image-2.0", "qwen-image-max"];
+const SYNC_MODEL_PREFIXES = ["qwen-image-2.0", "qwen-image-max", "wan2.7-image"];
+const PROMPT_EXTEND_DEFAULT_PREFIXES = ["qwen-image-2.0", "qwen-image-max"];

 function isSyncModel(model: string): boolean {
-  return SYNC_MODEL_PREFIXES.some((p) => model.startsWith(p));
+  return SYNC_MODEL_PREFIXES.some((prefix) => model.startsWith(prefix));
+}
+
+function enablesPromptExtendByDefault(model: string): boolean {
+  return PROMPT_EXTEND_DEFAULT_PREFIXES.some((prefix) => model.startsWith(prefix));
 }

 const EDIT_FLAGS = {
@@ -98,7 +104,7 @@ const EDIT_FLAGS = {
 type EditFlags = ParsedFlags<typeof EDIT_FLAGS>;

 export default defineCommand({
-  description: "Edit an existing image with text instructions (Qwen-Image)",
+  description: "Edit an existing image with text instructions (Qwen-Image / Wan 2.7)",
  auth: "apiKey",
  usageArgs: "--image <url> --prompt <text> [flags]",
  flags: EDIT_FLAGS,
@@ -107,6 +113,7 @@ export default defineCommand({
    '--image https://example.com/logo.png --prompt "Change color to blue" --n 3',
    '--image ./a.png --image ./b.png --prompt "Merge two images into one collage"',
    '--image https://example.com/photo.png --prompt "Remove the person" --model qwen-image-2.0-pro',
+    '--image ./photo.png --prompt "Change the style" --model wan2.7-image',
    '--image ./photo.png --prompt "Replace the background with a beach" --watermark false',
  ],
  async run(ctx) {
@@ -125,13 +132,13 @@ export default defineCommand({

    // Auto-upload local files (resolve all images in parallel)
    const resolvedImages = await Promise.all(
-      rawImages.map((img) => ctx.client.uploadFile(img, model)),
+      rawImages.map((image) => ctx.client.resolveImageInput(image, model)),
    );
    const n = flags.n ?? 1;

    const promptExtend = resolveBooleanFlag(
      flags.promptExtend,
-      useSync ? true : undefined,
+      enablesPromptExtendByDefault(model) ? true : undefined,
      "prompt-extend",
    );

@@ -169,7 +176,18 @@ export default defineCommand({
    const format = detectOutputFormat(settings.output);

    if (settings.dryRun) {
-      emitResult({ request: body, mode: useSync ? "sync" : "async" }, format);
+      const previewBody = {
+        ...body,
+        input: {
+          messages: body.input.messages.map((message) => ({
+            ...message,
+            content: message.content.map((item) =>
+              item.image ? { ...item, image: redactDataUri(item.image) } : item,
+            ),
+          })),
+        },
+      };
+      emitResult({ request: previewBody, mode: useSync ? "sync" : "async" }, format);
      return;
    }

@@ -31,11 +31,16 @@ import { BOOL_FLAG_PROMPT_EXTEND_IMAGE_GENERATE, BOOL_FLAG_WATERMARK } from "bai

 import { join } from "path";

-// qwen-image-2.0 series uses the sync multimodal-generation endpoint
-const SYNC_MODEL_PREFIXES = ["qwen-image-2.0", "qwen-image-max"];
+// Qwen-Image 2.0 and Wan 2.7 use the sync multimodal-generation endpoint.
+const SYNC_MODEL_PREFIXES = ["qwen-image-2.0", "qwen-image-max", "wan2.7-image"];
+const PROMPT_EXTEND_DEFAULT_PREFIXES = ["qwen-image-2.0", "qwen-image-max"];

 function isSyncModel(model: string): boolean {
-  return SYNC_MODEL_PREFIXES.some((p) => model.startsWith(p));
+  return SYNC_MODEL_PREFIXES.some((prefix) => model.startsWith(prefix));
+}
+
+function enablesPromptExtendByDefault(model: string): boolean {
+  return PROMPT_EXTEND_DEFAULT_PREFIXES.some((prefix) => model.startsWith(prefix));
 }

 const GENERATE_FLAGS = {
@@ -121,7 +126,7 @@ export default defineCommand({

    const promptExtend = resolveBooleanFlag(
      flags.promptExtend,
-      useSync ? true : undefined,
+      enablesPromptExtendByDefault(model) ? true : undefined,
      "prompt-extend",
    );

@@ -13,6 +13,7 @@ import {
  resolveWatermark,
  ASYNC_FLAG,
  CONCURRENT_FLAG,
+  redactDataUri,
 } from "bailian-cli-core";
 import { poll } from "bailian-cli-runtime";
 import { downloadFile, formatBytes } from "bailian-cli-runtime";
@@ -103,8 +104,9 @@ export default defineCommand({

    const model =
      flags.model ||
-      settings.defaultVideoModel ||
-      (flags.image ? "happyhorse-1.1-i2v" : "happyhorse-1.1-t2v");
+      (flags.image
+        ? settings.defaultImageToVideoModel || "happyhorse-1.1-i2v"
+        : settings.defaultVideoModel || "happyhorse-1.1-t2v");
    const format = detectOutputFormat(settings.output);

    const imageUrl = flags.image;
@@ -112,7 +114,7 @@ export default defineCommand({
    // Auto-upload local image file for i2v
    let resolvedImageUrl: string | undefined;
    if (imageUrl) {
-      resolvedImageUrl = await ctx.client.uploadFile(imageUrl, model);
+      resolvedImageUrl = await ctx.client.resolveImageInput(imageUrl, model);
    }

    const watermark = resolveWatermark(flags.watermark);
@@ -139,7 +141,16 @@ export default defineCommand({
    };

    if (settings.dryRun) {
-      emitResult({ request: body }, format);
+      const previewBody = resolvedImageUrl
+        ? {
+            ...body,
+            input: {
+              ...body.input,
+              media: [{ type: "first_frame" as const, url: redactDataUri(resolvedImageUrl) }],
+            },
+          }
+        : body;
+      emitResult({ request: previewBody }, format);
      return;
    }

@@ -13,6 +13,7 @@ import {
  resolveWatermark,
  ASYNC_FLAG,
  CONCURRENT_FLAG,
+  redactDataUri,
 } from "bailian-cli-core";
 import { poll } from "bailian-cli-runtime";
 import { downloadFile, formatBytes } from "bailian-cli-runtime";
@@ -117,23 +118,23 @@ export default defineCommand({
    const imageVoices = flags.imageVoice || [];
    const videoVoices = flags.videoVoice || [];

-    const model = flags.model || "happyhorse-1.1-r2v";
+    const model = flags.model || settings.defaultReferenceToVideoModel || "happyhorse-1.1-r2v";
    const format = detectOutputFormat(settings.output);

    // --- Resolve file URLs (auto-upload local files) ---
    const media: DashScopeVideoRefRequest["input"]["media"] = [];

    // Add reference images
-    for (let i = 0; i < images.length; i++) {
-      const resolved = await ctx.client.uploadFile(images[i]!, model);
+    for (let imageIndex = 0; imageIndex < images.length; imageIndex++) {
+      const resolved = await ctx.client.resolveImageInput(images[imageIndex]!, model);
      const entry: DashScopeVideoRefRequest["input"]["media"][number] = {
        type: "reference_image",
        url: resolved,
      };

      // Pair voice by position
-      if (imageVoices[i]) {
-        const resolvedVoice = await ctx.client.uploadFile(imageVoices[i]!, model);
+      if (imageVoices[imageIndex]) {
+        const resolvedVoice = await ctx.client.uploadFile(imageVoices[imageIndex]!, model);
        entry.reference_voice = resolvedVoice;
      }

@@ -141,16 +142,16 @@ export default defineCommand({
    }

    // Add reference videos
-    for (let i = 0; i < refVideos.length; i++) {
-      const resolved = await ctx.client.uploadFile(refVideos[i]!, model);
+    for (let videoIndex = 0; videoIndex < refVideos.length; videoIndex++) {
+      const resolved = await ctx.client.uploadFile(refVideos[videoIndex]!, model);
      const entry: DashScopeVideoRefRequest["input"]["media"][number] = {
        type: "reference_video",
        url: resolved,
      };

      // Pair voice by position
-      if (videoVoices[i]) {
-        const resolvedVoice = await ctx.client.uploadFile(videoVoices[i]!, model);
+      if (videoVoices[videoIndex]) {
+        const resolvedVoice = await ctx.client.uploadFile(videoVoices[videoIndex]!, model);
        entry.reference_voice = resolvedVoice;
      }

@@ -178,7 +179,18 @@ export default defineCommand({
    };

    if (settings.dryRun) {
-      emitResult({ request: body }, format);
+      const previewBody = {
+        ...body,
+        input: {
+          ...body.input,
+          media: body.input.media.map((item) => ({
+            ...item,
+            url: redactDataUri(item.url),
+            reference_voice: item.reference_voice ? redactDataUri(item.reference_voice) : undefined,
+          })),
+        },
+      };
+      emitResult({ request: previewBody }, format);
      return;
    }

@@ -233,11 +245,11 @@ export default defineCommand({
    );

    const videos: Array<{ taskId: string; videoUrl: string }> = [];
-    for (let i = 0; i < results.length; i++) {
-      const result = results[i]!;
+    for (let resultIndex = 0; resultIndex < results.length; resultIndex++) {
+      const result = results[resultIndex]!;
      const videoUrl =
        result.output.video_url || (result.output.results && result.output.results[0]?.url);
-      if (videoUrl) videos.push({ taskId: taskIds[i]!, videoUrl });
+      if (videoUrl) videos.push({ taskId: taskIds[resultIndex]!, videoUrl });
    }

    if (videos.length === 0) {
@@ -8,18 +8,13 @@ import {
  BailianError,
  ExitCode,
  isLocalFile,
+  imageFileToDataUri,
+  redactDataUri,
 } from "bailian-cli-core";
 import { emitResult, emitBare } from "bailian-cli-runtime";
-import { readFileSync, existsSync } from "fs";
+import { existsSync, statSync } from "fs";
 import { extname } from "path";

-const IMAGE_MIME_TYPES: Record<string, string> = {
-  ".jpg": "image/jpeg",
-  ".jpeg": "image/jpeg",
-  ".png": "image/png",
-  ".webp": "image/webp",
-};
-
 const VIDEO_EXTENSIONS = new Set([".mp4", ".mov", ".avi", ".mkv", ".webm", ".flv", ".wmv"]);

 function isVideoInput(input: string): boolean {
@@ -35,18 +30,7 @@ async function toImageUrl(image: string): Promise<string> {
  if (image.startsWith("data:")) return image;
  if (image.startsWith("http://") || image.startsWith("https://")) return image;
  if (image.startsWith("oss://")) return image;
-
-  // Local file → data URI (for small files < 10MB, fallback)
-  if (!existsSync(image)) throw new BailianError(`File not found: ${image}`, ExitCode.USAGE);
-  const ext = extname(image).toLowerCase();
-  const mime = IMAGE_MIME_TYPES[ext];
-  if (!mime)
-    throw new BailianError(
-      `Unsupported image format "${ext}". Supported: jpg, jpeg, png, webp`,
-      ExitCode.USAGE,
-    );
-  const buf = readFileSync(image);
-  return `data:${mime};base64,${buf.toString("base64")}`;
+  return imageFileToDataUri(image);
 }

 export default defineCommand({
@@ -86,7 +70,10 @@ export default defineCommand({
    const { settings, flags } = ctx;
    let image = flags.image;
    const videoInputs = flags.video ?? [];
-    const model = flags.model || "qwen3-vl-plus";
+    const model =
+      flags.model ||
+      (ctx.client.usesTokenPlanEndpoint() ? settings.defaultTextModel : undefined) ||
+      "qwen3-vl-plus";

    // Auto-detect: if --image was given a video file, treat it as --video
    if (image && isVideoInput(image)) {
@@ -102,7 +89,14 @@ export default defineCommand({

    if (settings.dryRun) {
      emitResult(
-        { request: { prompt, image, video: videoInputs.length ? videoInputs : undefined, model } },
+        {
+          request: {
+            prompt,
+            image: image ? redactDataUri(image) : undefined,
+            video: videoInputs.length ? videoInputs.map(redactDataUri) : undefined,
+            model,
+          },
+        },
        format,
      );
      return;
@@ -132,10 +126,9 @@ export default defineCommand({

      let finalImageUrl = imageUrl;
      if (isLocalFile(image) && imageUrl.startsWith("data:")) {
-        const { statSync } = await import("fs");
        const fileSize = statSync(image).size;
        if (fileSize > 5 * 1024 * 1024) {
-          finalImageUrl = await ctx.client.uploadFile(image, model);
+          finalImageUrl = await ctx.client.resolveImageInput(image, model);
        }
      }

@@ -81,6 +81,8 @@ test("GET /api/config 返回全部 profile、明文密钥与持久化激活项",
    expect(res.json.default).toMatchObject({ api_key: "sk-default", output: "json" });
    expect(res.json.named.dev).toMatchObject({ api_key: "sk-dev", access_token: "tok-dev" });
    expect(res.json.secretKeys).toContain("api_key");
+    expect(res.json.keys).toContain("default_image_to_video_model");
+    expect(res.json.keys).toContain("default_reference_to_video_model");
  });
 });

@@ -267,8 +267,11 @@ describe("e2e: auth", () => {
      expect(config["token-plan"]).toMatchObject({
        api_key: "sk-sp-e2e-placeholder",
        base_url: validationServer.baseUrl,
-        default_text_model: "qwen3.7-max",
-        default_image_model: "qwen-image-2.0",
+        default_text_model: "qwen3.8-max-preview",
+        default_video_model: "happyhorse-1.1-t2v",
+        default_image_to_video_model: "happyhorse-1.1-i2v",
+        default_reference_to_video_model: "happyhorse-1.1-r2v",
+        default_image_model: "wan2.7-image",
      });
    } finally {
      await validationServer.close();
@@ -284,6 +287,9 @@ describe("e2e: auth", () => {
        {
          "token-plan": {
            default_text_model: "custom-text-model",
+            default_video_model: "custom-video-model",
+            default_image_to_video_model: "custom-image-to-video-model",
+            default_reference_to_video_model: "custom-reference-to-video-model",
            default_image_model: "custom-image-model",
          },
        },
@@ -309,9 +315,9 @@ describe("e2e: auth", () => {
        authorization: "Bearer sk-sp-e2e-placeholder",
        sourceConfig: expect.any(String),
        body: {
-          model: "qwen3.7-max",
+          model: "qwen3.8-max-preview",
          stream: false,
-          enable_thinking: false,
+          enable_thinking: true,
        },
      });

@@ -324,8 +330,11 @@ describe("e2e: auth", () => {
      expect(config["token-plan"]).toMatchObject({
        api_key: "sk-sp-e2e-placeholder",
        base_url: "https://token-plan.cn-beijing.maas.aliyuncs.com",
-        default_text_model: "qwen3.7-max",
-        default_image_model: "qwen-image-2.0",
+        default_text_model: "qwen3.8-max-preview",
+        default_video_model: "happyhorse-1.1-t2v",
+        default_image_to_video_model: "happyhorse-1.1-i2v",
+        default_reference_to_video_model: "happyhorse-1.1-r2v",
+        default_image_model: "wan2.7-image",
      });
      expect((config["token-plan"] as Record<string, unknown>).base_url).not.toBe(
        validationServer.baseUrl,
@@ -299,6 +299,44 @@ describe("e2e: config", () => {
    expect(data.would_set?.default_text_model).toBe("qwen3.7-max");
  });

+  test("config set --dry-run 支持图生视频默认模型别名", async () => {
+    const { stdout, stderr, exitCode } = await runCommandE2e(CONFIG_ROUTES, [
+      "config",
+      "set",
+      "--dry-run",
+      "--key",
+      "default-image-to-video-model",
+      "--value",
+      "happyhorse-1.1-i2v",
+      "--output",
+      "json",
+    ]);
+    expect(exitCode, stderr).toBe(0);
+    const data = parseStdoutJson<{
+      would_set?: { default_image_to_video_model?: string };
+    }>(stdout);
+    expect(data.would_set?.default_image_to_video_model).toBe("happyhorse-1.1-i2v");
+  });
+
+  test("config set --dry-run 支持参考生视频默认模型别名", async () => {
+    const { stdout, stderr, exitCode } = await runCommandE2e(CONFIG_ROUTES, [
+      "config",
+      "set",
+      "--dry-run",
+      "--key",
+      "default-reference-to-video-model",
+      "--value",
+      "happyhorse-1.1-r2v",
+      "--output",
+      "json",
+    ]);
+    expect(exitCode, stderr).toBe(0);
+    const data = parseStdoutJson<{
+      would_set?: { default_reference_to_video_model?: string };
+    }>(stdout);
+    expect(data.would_set?.default_reference_to_video_model).toBe("happyhorse-1.1-r2v");
+  });
+
  test("config set --dry-run 展示归一化后的 Base URL", async () => {
    const { stdout, stderr, exitCode } = await runCommandE2e(CONFIG_ROUTES, [
      "config",
@@ -1,5 +1,6 @@
 import { describe, expect, test } from "vite-plus/test";
-import { join } from "path";
+import { writeFileSync } from "node:fs";
+import { join } from "node:path";
 import {
  e2eFixturesDir,
  e2eLabelFromMetaUrl,
@@ -46,6 +47,55 @@ describe("e2e: image edit", () => {
    expect(data.mode).toBe("async");
    expect(data.request?.input?.messages?.length).toBeGreaterThan(0);
  });
+
+  test("Token Plan 使用 Base64 传入 wan2.7-image 本地图片", async () => {
+    const configDir = makeE2eOutputDir("image-edit-token-plan-local-image");
+    writeFileSync(
+      join(configDir, "config.json"),
+      JSON.stringify({
+        "token-plan": {
+          api_key: "sk-sp-e2e-placeholder",
+          base_url: "https://token-plan.cn-beijing.maas.aliyuncs.com",
+          default_image_model: "wan2.7-image",
+        },
+      }),
+    );
+
+    const { stdout, stderr, exitCode } = await runCommandE2e(
+      IMAGE_ROUTES,
+      [
+        "image",
+        "edit",
+        "--config",
+        "token-plan",
+        "--image",
+        join(e2eFixturesDir, ".smoke-32.png"),
+        "--prompt",
+        "改成蓝色",
+        "--dry-run",
+        "--output",
+        "json",
+      ],
+      {
+        BAILIAN_CONFIG_DIR: configDir,
+        DASHSCOPE_API_KEY: "",
+        DASHSCOPE_BASE_URL: "",
+      },
+    );
+    expect(exitCode, stderr).toBe(0);
+    const data = parseStdoutJson<{
+      mode?: string;
+      request?: {
+        model?: string;
+        input?: { messages?: Array<{ content?: Array<{ image?: string }> }> };
+      };
+    }>(stdout);
+    expect(data.mode).toBe("sync");
+    expect(data.request?.model).toBe("wan2.7-image");
+    expect(data.request?.input?.messages?.[0]?.content?.[0]?.image).toBe(
+      "data:image/png;base64,<omitted>",
+    );
+  });
 });

 describe.skipIf(!isBailianE2EMediaEnabled() || !isDashScopeE2EReady())("e2e: image edit", () => {
@@ -1,4 +1,6 @@
 import { describe, expect, test } from "vite-plus/test";
+import { writeFileSync } from "node:fs";
+import { join } from "node:path";
 import {
  e2eLabelFromMetaUrl,
  isBailianE2EMediaEnabled,
@@ -21,6 +23,44 @@ describe("e2e: image generate", () => {
    expect(exitCode, stderr).toBe(0);
    expect(stderr).toMatch(/generate|--prompt|--model/i);
  });
+
+  test("Token Plan 默认使用 wan2.7-image 同步接口", async () => {
+    const configDir = makeE2eOutputDir("image-generate-token-plan-default");
+    writeFileSync(
+      join(configDir, "config.json"),
+      JSON.stringify({
+        "token-plan": {
+          api_key: "sk-sp-e2e-placeholder",
+          base_url: "https://token-plan.cn-beijing.maas.aliyuncs.com",
+          default_image_model: "wan2.7-image",
+        },
+      }),
+    );
+
+    const { stdout, stderr, exitCode } = await runCommandE2e(
+      IMAGE_ROUTES,
+      [
+        "image",
+        "generate",
+        "--config",
+        "token-plan",
+        "--prompt",
+        "一只猫",
+        "--dry-run",
+        "--output",
+        "json",
+      ],
+      {
+        BAILIAN_CONFIG_DIR: configDir,
+        DASHSCOPE_API_KEY: "",
+        DASHSCOPE_BASE_URL: "",
+      },
+    );
+    expect(exitCode, stderr).toBe(0);
+    const data = parseStdoutJson<{ mode?: string; request?: { model?: string } }>(stdout);
+    expect(data.mode).toBe("sync");
+    expect(data.request?.model).toBe("wan2.7-image");
+  });
 });

 describe.skipIf(!isBailianE2EMediaEnabled() || !isDashScopeE2EReady())(
@@ -59,6 +59,8 @@ export const VIDEO_ROUTES: E2eRouteExports = {
  "video download": "videoDownload",
 };

+export const VISION_ROUTES: E2eRouteExports = { "vision describe": "visionDescribe" };
+
 export const SPEECH_ROUTES: E2eRouteExports = {
  "speech synthesize": "speechSynthesize",
  "speech recognize": "speechRecognize",
@@ -1,3 +1,4 @@
+import { writeFileSync } from "node:fs";
 import { join } from "node:path";
 import { describe, expect, test } from "vite-plus/test";
 import {
@@ -21,6 +22,96 @@ describe("e2e: video generate (i2v)", () => {
    expect(exitCode, stderr).toBe(0);
    expect(stderr).toMatch(/generate|--prompt|--image|model/i);
  });
+
+  test("Token Plan 使用独立的图生视频默认模型", async () => {
+    const configDir = makeE2eOutputDir("video-i2v-token-plan-default");
+    writeFileSync(
+      join(configDir, "config.json"),
+      JSON.stringify(
+        {
+          "token-plan": {
+            api_key: "sk-sp-e2e-placeholder",
+            base_url: "https://token-plan.cn-beijing.maas.aliyuncs.com",
+            default_video_model: "happyhorse-1.1-t2v",
+            default_image_to_video_model: "custom-image-to-video-model",
+          },
+        },
+        null,
+        2,
+      ) + "\n",
+    );
+
+    const { stdout, stderr, exitCode } = await runCommandE2e(
+      VIDEO_ROUTES,
+      [
+        "video",
+        "generate",
+        "--config",
+        "token-plan",
+        "--dry-run",
+        "--image",
+        "https://example.com/placeholder.png",
+        "--prompt",
+        "干跑校验",
+        "--output",
+        "json",
+      ],
+      {
+        BAILIAN_CONFIG_DIR: configDir,
+        DASHSCOPE_API_KEY: "",
+        DASHSCOPE_BASE_URL: "",
+      },
+    );
+    expect(exitCode, stderr).toBe(0);
+    const data = parseStdoutJson<{
+      request?: { model?: string; input?: { media?: Array<{ type?: string }> } };
+    }>(stdout);
+    expect(data.request?.model).toBe("custom-image-to-video-model");
+    expect(data.request?.input?.media?.[0]?.type).toBe("first_frame");
+  });
+
+  test("Token Plan 图生视频将本地首帧转换为 Base64", async () => {
+    const configDir = makeE2eOutputDir("video-i2v-token-plan-local-image");
+    const imagePath = join(configDir, "first-frame.png");
+    writeFileSync(imagePath, Buffer.from([1, 2, 3]));
+    writeFileSync(
+      join(configDir, "config.json"),
+      JSON.stringify({
+        "token-plan": {
+          api_key: "sk-sp-e2e-placeholder",
+          base_url: "https://token-plan.cn-beijing.maas.aliyuncs.com",
+          default_image_to_video_model: "happyhorse-1.1-i2v",
+        },
+      }),
+    );
+
+    const { stdout, stderr, exitCode } = await runCommandE2e(
+      VIDEO_ROUTES,
+      [
+        "video",
+        "generate",
+        "--config",
+        "token-plan",
+        "--dry-run",
+        "--image",
+        imagePath,
+        "--prompt",
+        "让画面动起来",
+        "--output",
+        "json",
+      ],
+      {
+        BAILIAN_CONFIG_DIR: configDir,
+        DASHSCOPE_API_KEY: "",
+        DASHSCOPE_BASE_URL: "",
+      },
+    );
+    expect(exitCode, stderr).toBe(0);
+    const data = parseStdoutJson<{
+      request?: { input?: { media?: Array<{ url?: string }> } };
+    }>(stdout);
+    expect(data.request?.input?.media?.[0]?.url).toBe("data:image/png;base64,<omitted>");
+  });
 });

 describe.skipIf(!isBailianE2EVideoEnabled() || !isDashScopeE2EReady())(
@@ -1,3 +1,4 @@
+import { writeFileSync } from "node:fs";
 import { join } from "node:path";
 import { describe, expect, test } from "vite-plus/test";
 import {
@@ -43,6 +44,92 @@ describe("e2e: video ref (r2v)", () => {
    );
    expect(data.request?.input?.media?.[0]?.url).toBe("https://example.com/person.png");
  });
+
+  test("Token Plan 使用独立的参考生视频默认模型", async () => {
+    const configDir = makeE2eOutputDir("video-r2v-token-plan-default");
+    writeFileSync(
+      join(configDir, "config.json"),
+      JSON.stringify(
+        {
+          "token-plan": {
+            api_key: "sk-sp-e2e-placeholder",
+            base_url: "https://token-plan.cn-beijing.maas.aliyuncs.com",
+            default_reference_to_video_model: "custom-reference-to-video-model",
+          },
+        },
+        null,
+        2,
+      ) + "\n",
+    );
+
+    const { stdout, stderr, exitCode } = await runCommandE2e(
+      VIDEO_ROUTES,
+      [
+        "video",
+        "ref",
+        "--config",
+        "token-plan",
+        "--dry-run",
+        "--prompt",
+        "Image 1 waves",
+        "--image",
+        "https://example.com/person.png",
+        "--output",
+        "json",
+      ],
+      {
+        BAILIAN_CONFIG_DIR: configDir,
+        DASHSCOPE_API_KEY: "",
+        DASHSCOPE_BASE_URL: "",
+      },
+    );
+    expect(exitCode, stderr).toBe(0);
+    const data = parseStdoutJson<{ request?: { model?: string } }>(stdout);
+    expect(data.request?.model).toBe("custom-reference-to-video-model");
+  });
+
+  test("Token Plan 参考生视频将本地参考图转换为 Base64", async () => {
+    const configDir = makeE2eOutputDir("video-r2v-token-plan-local-image");
+    const imagePath = join(configDir, "reference.png");
+    writeFileSync(imagePath, Buffer.from([1, 2, 3]));
+    writeFileSync(
+      join(configDir, "config.json"),
+      JSON.stringify({
+        "token-plan": {
+          api_key: "sk-sp-e2e-placeholder",
+          base_url: "https://token-plan.cn-beijing.maas.aliyuncs.com",
+          default_reference_to_video_model: "happyhorse-1.1-r2v",
+        },
+      }),
+    );
+
+    const { stdout, stderr, exitCode } = await runCommandE2e(
+      VIDEO_ROUTES,
+      [
+        "video",
+        "ref",
+        "--config",
+        "token-plan",
+        "--dry-run",
+        "--image",
+        imagePath,
+        "--prompt",
+        "Image 1 waves",
+        "--output",
+        "json",
+      ],
+      {
+        BAILIAN_CONFIG_DIR: configDir,
+        DASHSCOPE_API_KEY: "",
+        DASHSCOPE_BASE_URL: "",
+      },
+    );
+    expect(exitCode, stderr).toBe(0);
+    const data = parseStdoutJson<{
+      request?: { input?: { media?: Array<{ url?: string }> } };
+    }>(stdout);
+    expect(data.request?.input?.media?.[0]?.url).toBe("data:image/png;base64,<omitted>");
+  });
 });

 describe.skipIf(!isBailianE2EVideoEnabled() || !isDashScopeE2EReady())(
@@ -0,0 +1,45 @@
+import { writeFileSync } from "node:fs";
+import { join } from "node:path";
+import { describe, expect, test } from "vite-plus/test";
+import { makeE2eOutputDir, parseStdoutJson, runCommandE2e } from "./helpers.ts";
+import { VISION_ROUTES } from "./topic-routes.ts";
+
+describe("e2e: vision describe", () => {
+  test("Token Plan 默认使用支持视觉理解的文本模型", async () => {
+    const configDir = makeE2eOutputDir("vision-describe-token-plan-default");
+    writeFileSync(
+      join(configDir, "config.json"),
+      JSON.stringify({
+        "token-plan": {
+          api_key: "sk-sp-e2e-placeholder",
+          base_url: "https://token-plan.cn-beijing.maas.aliyuncs.com",
+          default_text_model: "qwen3.8-max-preview",
+        },
+      }),
+    );
+
+    const { stdout, stderr, exitCode } = await runCommandE2e(
+      VISION_ROUTES,
+      [
+        "vision",
+        "describe",
+        "--config",
+        "token-plan",
+        "--image",
+        "https://example.com/image.png",
+        "--dry-run",
+        "--output",
+        "json",
+      ],
+      {
+        BAILIAN_CONFIG_DIR: configDir,
+        DASHSCOPE_API_KEY: "",
+        DASHSCOPE_BASE_URL: "",
+      },
+    );
+
+    expect(exitCode, stderr).toBe(0);
+    const data = parseStdoutJson<{ request?: { model?: string } }>(stdout);
+    expect(data.request?.model).toBe("qwen3.8-max-preview");
+  });
+});
@@ -33,6 +33,9 @@ export type AuthPersistPatch = Pick<
  | "console_switch_agent"
  | "workspace_id"
  | "default_text_model"
+  | "default_video_model"
+  | "default_image_to_video_model"
+  | "default_reference_to_video_model"
  | "default_image_model"
 >;

@@ -4,7 +4,7 @@ import { BailianError } from "../errors/base.ts";
 import { ExitCode } from "../errors/codes.ts";
 import { request, requestJson, type HttpDeps, type RequestOpts } from "./http.ts";
 import { buildAcsCanonicalQuery, signAcsRequest, type AcsQueryParams } from "./acs.ts";
-import { isLocalFile, resolveFileUrl } from "../files/upload.ts";
+import { imageFileToDataUri, isLocalFile, resolveFileUrl } from "../files/upload.ts";
 import { McpClient } from "./mcp.ts";
 import { callConsoleGateway } from "../console/gateway.ts";
 import { refreshAccessToken } from "../auth/refresh-token.ts";
@@ -118,6 +118,32 @@ export class Client {
    return resolveFileUrl(source, this.requireApi().token, model, opts);
  }

+  /**
+   * Resolve an image input while keeping Token Plan's upload limitation isolated.
+   * Token Plan local images are sent as Data URIs; every other connection keeps
+   * the established temporary OSS upload flow. URLs and existing Data URIs pass through.
+   */
+  resolveImageInput(
+    source: string,
+    model: string,
+    opts: { signal?: AbortSignal } = {},
+  ): Promise<string> {
+    if (!isLocalFile(source)) return Promise.resolve(source);
+    if (this.usesTokenPlanEndpoint()) {
+      return Promise.resolve(imageFileToDataUri(source));
+    }
+    return this.uploadFile(source, model, { signal: opts.signal });
+  }
+
+  usesTokenPlanEndpoint(): boolean {
+    if (this.deps.settings.configName === "token-plan") return true;
+    try {
+      return /^token-plan\.[a-z0-9-]+\.maas\.aliyuncs\.com$/i.test(new URL(this.baseUrl).hostname);
+    } catch {
+      return false;
+    }
+  }
+
  /** Open an MCP client. Accepts a path (prepended with the model baseUrl) or an absolute URL. */
  mcp(pathOrUrl: string): McpClient {
    const url = /^https?:\/\//.test(pathOrUrl) ? pathOrUrl : this.requireApi().baseUrl + pathOrUrl;
@@ -235,6 +235,8 @@ export function buildSettings(s: ResolutionSources): Settings {
    timeout,
    defaultTextModel: file.default_text_model,
    defaultVideoModel: file.default_video_model,
+    defaultImageToVideoModel: file.default_image_to_video_model,
+    defaultReferenceToVideoModel: file.default_reference_to_video_model,
    defaultImageModel: file.default_image_model,
    defaultSpeechModel: file.default_speech_model,
    defaultOmniModel: file.default_omni_model,
@@ -1,14 +1,20 @@
 interface ModelProfilePreset {
  baseUrl: string;
  defaultTextModel: string;
+  defaultVideoModel: string;
+  defaultImageToVideoModel: string;
+  defaultReferenceToVideoModel: string;
  defaultImageModel: string;
 }

 const MODEL_PROFILE_PRESETS: Readonly<Record<string, ModelProfilePreset>> = {
  "token-plan": {
    baseUrl: "https://token-plan.cn-beijing.maas.aliyuncs.com",
-    defaultTextModel: "qwen3.7-max",
-    defaultImageModel: "qwen-image-2.0",
+    defaultTextModel: "qwen3.8-max-preview",
+    defaultVideoModel: "happyhorse-1.1-t2v",
+    defaultImageToVideoModel: "happyhorse-1.1-i2v",
+    defaultReferenceToVideoModel: "happyhorse-1.1-r2v",
+    defaultImageModel: "wan2.7-image",
  },
 };

@@ -32,6 +32,8 @@ export interface ConfigFile {
  timeout?: number;
  default_text_model?: string;
  default_video_model?: string;
+  default_image_to_video_model?: string;
+  default_reference_to_video_model?: string;
  default_image_model?: string;
  default_speech_model?: string;
  default_omni_model?: string;
@@ -54,6 +56,8 @@ export const CONFIG_FILE_KEYS = [
  "timeout",
  "default_text_model",
  "default_video_model",
+  "default_image_to_video_model",
+  "default_reference_to_video_model",
  "default_image_model",
  "default_speech_model",
  "default_omni_model",
@@ -117,6 +121,16 @@ export function parseConfigFile(raw: unknown): ConfigFile {
    out.default_text_model = obj.default_text_model;
  if (typeof obj.default_video_model === "string" && obj.default_video_model.length > 0)
    out.default_video_model = obj.default_video_model;
+  if (
+    typeof obj.default_image_to_video_model === "string" &&
+    obj.default_image_to_video_model.length > 0
+  )
+    out.default_image_to_video_model = obj.default_image_to_video_model;
+  if (
+    typeof obj.default_reference_to_video_model === "string" &&
+    obj.default_reference_to_video_model.length > 0
+  )
+    out.default_reference_to_video_model = obj.default_reference_to_video_model;
  if (typeof obj.default_image_model === "string" && obj.default_image_model.length > 0)
    out.default_image_model = obj.default_image_model;
  if (typeof obj.default_speech_model === "string" && obj.default_speech_model.length > 0)
@@ -166,6 +180,8 @@ export interface Settings {
  timeout: number;
  defaultTextModel?: string;
  defaultVideoModel?: string;
+  defaultImageToVideoModel?: string;
+  defaultReferenceToVideoModel?: string;
  defaultImageModel?: string;
  defaultSpeechModel?: string;
  defaultOmniModel?: string;
@@ -1 +1,7 @@
-export { uploadFile, isLocalFile, resolveFileUrl } from "./upload.ts";
+export {
+  uploadFile,
+  isLocalFile,
+  resolveFileUrl,
+  imageFileToDataUri,
+  redactDataUri,
+} from "./upload.ts";
@@ -6,7 +6,7 @@
 *   X-DashScope-OssResourceResolve: enable
 */
 import { existsSync, readFileSync, statSync } from "fs";
-import { basename } from "path";
+import { basename, extname } from "path";
 import { BailianError } from "../errors/base.ts";
 import { ExitCode } from "../errors/codes.ts";
 import { trackingHeaders } from "../client/headers.ts";
@@ -112,6 +112,49 @@ export interface UploadOptions {
  signal?: AbortSignal;
 }

+const IMAGE_MIME_TYPES: Readonly<Record<string, string>> = {
+  ".bmp": "image/bmp",
+  ".heic": "image/heic",
+  ".jpe": "image/jpeg",
+  ".jpeg": "image/jpeg",
+  ".jpg": "image/jpeg",
+  ".png": "image/png",
+  ".tif": "image/tiff",
+  ".tiff": "image/tiff",
+  ".webp": "image/webp",
+};
+
+/** Encode a local image as a Data URI. */
+export function imageFileToDataUri(filePath: string): string {
+  if (!existsSync(filePath)) {
+    throw new BailianError(`File not found: ${filePath}`, ExitCode.USAGE);
+  }
+
+  const stat = statSync(filePath);
+  if (!stat.isFile()) {
+    throw new BailianError(`Not a file: ${filePath}`, ExitCode.USAGE);
+  }
+
+  const extension = extname(filePath).toLowerCase();
+  const mimeType = IMAGE_MIME_TYPES[extension];
+  if (!mimeType) {
+    throw new BailianError(
+      `Unsupported image format "${extension || "unknown"}".`,
+      ExitCode.USAGE,
+      "Use an image file with a recognized extension.",
+    );
+  }
+
+  const encoded = readFileSync(filePath).toString("base64");
+  return `data:${mimeType};base64,${encoded}`;
+}
+
+/** Keep dry-run output readable and avoid echoing the complete inline image. */
+export function redactDataUri(input: string): string {
+  const match = /^data:([^;,]+);base64,/i.exec(input);
+  return match ? `data:${match[1]};base64,<omitted>` : input;
+}
+
 /**
 * Upload a local file to DashScope temporary storage and return the oss:// URL.
 * The URL is valid for 48 hours.
@@ -32,8 +32,11 @@ const resolve = (s: Parameters<typeof src>[0]): Settings => buildSettings(src(s)
 test("token-plan Profile 预设保持固定", () => {
  expect(getModelProfilePreset("token-plan")).toEqual({
    baseUrl: "https://token-plan.cn-beijing.maas.aliyuncs.com",
-    defaultTextModel: "qwen3.7-max",
-    defaultImageModel: "qwen-image-2.0",
+    defaultTextModel: "qwen3.8-max-preview",
+    defaultVideoModel: "happyhorse-1.1-t2v",
+    defaultImageToVideoModel: "happyhorse-1.1-i2v",
+    defaultReferenceToVideoModel: "happyhorse-1.1-r2v",
+    defaultImageModel: "wan2.7-image",
  });
 });

@@ -316,10 +319,18 @@ test("openapi 凭证:低优先级来源缺字段时不影响更高优先级成

 test("default*Model / outputDir:仅 file 源", () => {
  const c = resolve({
-    file: { default_text_model: "qwen-max", default_video_model: "wan-x", output_dir: "/tmp/out" },
+    file: parseConfigFile({
+      default_text_model: "qwen-max",
+      default_video_model: "wan-t2v",
+      default_image_to_video_model: "wan-i2v",
+      default_reference_to_video_model: "wan-r2v",
+      output_dir: "/tmp/out",
+    }),
  });
  expect(c.defaultTextModel).toBe("qwen-max");
-  expect(c.defaultVideoModel).toBe("wan-x");
+  expect(c.defaultVideoModel).toBe("wan-t2v");
+  expect(c.defaultImageToVideoModel).toBe("wan-i2v");
+  expect(c.defaultReferenceToVideoModel).toBe("wan-r2v");
  expect(c.outputDir).toBe("/tmp/out");
  expect(resolve({}).defaultTextModel).toBeUndefined();
 });
@@ -0,0 +1,91 @@
+import { mkdtempSync, rmSync, writeFileSync } from "node:fs";
+import { tmpdir } from "node:os";
+import { join } from "node:path";
+import { afterEach, describe, expect, test } from "vite-plus/test";
+import { Client } from "../src/client/client.ts";
+import { imageFileToDataUri, redactDataUri } from "../src/files/upload.ts";
+import type { Settings } from "../src/config/schema.ts";
+
+const tempDirs: string[] = [];
+
+afterEach(() => {
+  for (const tempDir of tempDirs.splice(0)) {
+    rmSync(tempDir, { recursive: true, force: true });
+  }
+});
+
+function makeImage(extension = ".png", content = Buffer.from([1, 2, 3, 4])): string {
+  const tempDir = mkdtempSync(join(tmpdir(), "bailian-image-input-"));
+  tempDirs.push(tempDir);
+  const filePath = join(tempDir, `input${extension}`);
+  writeFileSync(filePath, content);
+  return filePath;
+}
+
+function makeSettings(configName?: string): Settings {
+  return {
+    configName,
+    output: "json",
+    outputExplicit: false,
+    timeout: 30,
+    verbose: false,
+    quiet: true,
+    dryRun: false,
+    telemetry: false,
+  };
+}
+
+function makeClient(baseUrl: string, configName?: string): Client {
+  return new Client({
+    identity: {
+      binName: "bl",
+      version: "test",
+      npmPackage: "bailian-cli",
+      clientName: "bailian-cli-test",
+    },
+    settings: makeSettings(configName),
+    baseUrl,
+  });
+}
+
+describe("Token Plan image input compatibility", () => {
+  test("encodes supported local images and redacts previews", () => {
+    const imagePath = makeImage(".png");
+    const dataUri = imageFileToDataUri(imagePath);
+
+    expect(dataUri).toBe("data:image/png;base64,AQIDBA==");
+    expect(redactDataUri(dataUri)).toBe("data:image/png;base64,<omitted>");
+  });
+
+  test("rejects files whose image MIME type cannot be inferred", () => {
+    const imagePath = makeImage(".unknown");
+    expect(() => imageFileToDataUri(imagePath)).toThrow(/Unsupported image format/);
+  });
+
+  test("uses Data URI for the token-plan profile even through a custom proxy", async () => {
+    const imagePath = makeImage(".webp");
+    const client = makeClient("https://proxy.example.com/bailian", "token-plan");
+
+    await expect(client.resolveImageInput(imagePath, "happyhorse-1.1-i2v")).resolves.toMatch(
+      /^data:image\/webp;base64,/,
+    );
+  });
+
+  test("uses Data URI for an official Token Plan endpoint under any profile name", async () => {
+    const imagePath = makeImage(".jpg");
+    const client = makeClient("https://token-plan.ap-southeast-1.maas.aliyuncs.com", "custom-plan");
+
+    await expect(client.resolveImageInput(imagePath, "wan2.7-image")).resolves.toMatch(
+      /^data:image\/jpeg;base64,/,
+    );
+  });
+
+  test("ordinary endpoints retain the existing upload path", () => {
+    const imagePath = makeImage(".png");
+    const client = makeClient("https://dashscope.aliyuncs.com", "default");
+
+    expect(() => client.resolveImageInput(imagePath, "wan2.7-image")).toThrow(
+      /model-domain API key/,
+    );
+  });
+});
@@ -24,7 +24,7 @@ Verify: `bl --version` (prints `bl X.Y.Z`).
 | Auth               | How                                                                                              | Used by                                       |
 | ------------------ | ------------------------------------------------------------------------------------------------ | --------------------------------------------- |
 | API key            | `export DASHSCOPE_API_KEY=sk-...` or `bl auth login --api-key sk-...`                            | Most DashScope API commands                   |
-| Token Plan API key | `bl auth login --config token-plan --api-key sk-sp-...`                                          | Token Plan text and image model consumption   |
+| Token Plan API key | `bl auth login --config token-plan --api-key sk-sp-...`                                          | Token Plan text, image, and video consumption |
 | Console            | `bl auth login --console --console-site domestic` or `... international`                         | `app list`, `usage free`, `console call`      |
 | OpenAPI AK         | `bl auth login --open-api --access-key-id <id> --access-key-secret <secret>` or Alibaba env vars | Token Plan management commands (`token-plan`) |

@@ -46,6 +46,7 @@ Get or copy the Token Plan API key from the [subscription overview](https://bail
 bl auth login --config token-plan --api-key sk-sp-xxx
 bl text chat --message "Hello"
 bl image generate --prompt "A cat"
+bl video generate --prompt "A horse running through a field"
 ```

 The built-in Profile supplies the Token Plan Base URL. `auth login` tests the key first, then saves
@@ -71,8 +72,11 @@ Activation selects the entire Config for every credential domain, not only model
 The built-in `token-plan` profile defaults to:

 - Base URL: `https://token-plan.cn-beijing.maas.aliyuncs.com`
- Text model: `qwen3.7-max`
- Image model: `qwen-image-2.0`
+- Text model: `qwen3.8-max-preview`
+- Image model: `wan2.7-image`
+- Text-to-video model (`default_video_model`): `happyhorse-1.1-t2v`
+- Image-to-video model (`default_image_to_video_model`): `happyhorse-1.1-i2v`
+- Reference-to-video model (`default_reference_to_video_model`): `happyhorse-1.1-r2v`

 The usual priority applies to this profile too: per-command `--api-key` / `--base-url`, then `DASHSCOPE_API_KEY` / `DASHSCOPE_BASE_URL`, then the selected profile. Unset environment overrides when you want to use the credentials saved in `token-plan`.

@@ -7,20 +7,20 @@ Index: [index.md](index.md)

 ## Commands in this group

-| Command             | Description                                                |
-| ------------------- | ---------------------------------------------------------- |
-| `bl image edit`     | Edit an existing image with text instructions (Qwen-Image) |
-| `bl image generate` | Generate images (Qwen-Image / wan2.x)                      |
+| Command             | Description                                                          |
+| ------------------- | -------------------------------------------------------------------- |
+| `bl image edit`     | Edit an existing image with text instructions (Qwen-Image / Wan 2.7) |
+| `bl image generate` | Generate images (Qwen-Image / wan2.x)                                |

 ## Command details

 ### `bl image edit`

-| Field           | Value                                                      |
-| --------------- | ---------------------------------------------------------- |
-| **Name**        | `image edit`                                               |
-| **Description** | Edit an existing image with text instructions (Qwen-Image) |
-| **Usage**       | `bl image edit --image <url> --prompt <text> [flags]`      |
+| Field           | Value                                                                |
+| --------------- | -------------------------------------------------------------------- |
+| **Name**        | `image edit`                                                         |
+| **Description** | Edit an existing image with text instructions (Qwen-Image / Wan 2.7) |
+| **Usage**       | `bl image edit --image <url> --prompt <text> [flags]`                |

 #### Flags

@@ -61,6 +61,10 @@ bl image edit --image ./a.png --image ./b.png --prompt "Merge two images into on
 bl image edit --image https://example.com/photo.png --prompt "Remove the person" --model qwen-image-2.0-pro
 ```

+```bash
+bl image edit --image ./photo.png --prompt "Change the style" --model wan2.7-image
+```
+
 ```bash
 bl image edit --image ./photo.png --prompt "Replace the background with a beach" --watermark false
 ```
@@ -51,7 +51,7 @@ Use this index for the full quick index and global flags.
 | `bl finetune logs`              | Fetch training logs for a fine-tune job                                                                                         | [finetune.md](finetune.md)     |
 | `bl finetune text create`       | Create a text model fine-tune job (sft \| sft-lora \| dpo \| dpo-lora \| cpt)                                                   | [finetune.md](finetune.md)     |
 | `bl finetune watch`             | Probe a fine-tune job's status (default: single non-blocking fetch). Pass --follow to poll until terminal.                      | [finetune.md](finetune.md)     |
-| `bl image edit`                 | Edit an existing image with text instructions (Qwen-Image)                                                                      | [image.md](image.md)           |
+| `bl image edit`                 | Edit an existing image with text instructions (Qwen-Image / Wan 2.7)                                                            | [image.md](image.md)           |
 | `bl image generate`             | Generate images (Qwen-Image / wan2.x)                                                                                           | [image.md](image.md)           |
 | `bl knowledge chat`             | Chat with a Bailian knowledge base (RAG Q&A with streaming)                                                                     | [knowledge.md](knowledge.md)   |
 | `bl knowledge retrieve`         | Retrieve from a Bailian knowledge base (deprecated, use `search` instead)                                                       | [knowledge.md](knowledge.md)   |