diff --git a/README.md b/README.md index cb7669e..9d88689 100644 --- a/README.md +++ b/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 | diff --git a/README.zh.md b/README.zh.md index 2f70c64..780577e 100644 --- a/README.zh.md +++ b/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 | diff --git a/skills/baoyu-image-gen/SKILL.md b/skills/baoyu-image-gen/SKILL.md index 53d04e9..0eb908e 100644 --- a/skills/baoyu-image-gen/SKILL.md +++ b/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 ` | Size (e.g., `1024x1024`) | | `--quality normal\|2k` | Quality preset (default: `2k`) | | `--imageSize 1K\|2K\|4K` | Image size for Google/OpenRouter (default: from quality) | -| `--ref ` | Reference images. Supported by Google multimodal, OpenAI GPT Image edits, OpenRouter multimodal models, and Replicate. Not supported by Jimeng or Seedream | +| `--ref ` | 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 ` | Number of images | | `--json` | JSON output | diff --git a/skills/baoyu-image-gen/scripts/main.test.ts b/skills/baoyu-image-gen/scripts/main.test.ts index 591a1bf..d886479 100644 --- a/skills/baoyu-image-gen/scripts/main.test.ts +++ b/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); diff --git a/skills/baoyu-image-gen/scripts/main.ts b/skills/baoyu-image-gen/scripts/main.ts index d31e18a..4f746ce 100644 --- a/skills/baoyu-image-gen/scripts/main.ts +++ b/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; + validateArgs?: (model: string, args: CliArgs) => void; + getDefaultOutputExtension?: (model: string, args: CliArgs) => string; }; type PreparedTask = { @@ -78,7 +80,7 @@ Options: --size Size (e.g., 1024x1024) --quality normal|2k Quality preset (default: 2k) --imageSize 1K|2K|4K Image size for Google/OpenRouter (default: from quality) - --ref Reference images (Google multimodal, OpenAI GPT Image edits, OpenRouter multimodal, or Replicate) + --ref Reference images (Google, OpenAI, OpenRouter, Replicate, or Seedream 4.0/4.5/5.0) --n Number of images for the current task (default: 1) --json JSON output -h, --help Show help @@ -560,11 +562,17 @@ async function readPromptFromStdin(): Promise { } } -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 = {}): 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, +): void { + const previous = new Map(); + 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 { + 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; + 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"); +}); diff --git a/skills/baoyu-image-gen/scripts/providers/seedream.ts b/skills/baoyu-image-gen/scripts/providers/seedream.ts index 778f1fe..436a236 100644 --- a/skills/baoyu-image-gen/scripts/providers/seedream.ts +++ b/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 { + 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 { + 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 { + 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 { + 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 ${first.url}...`); + return downloadImage(first.url); + } + + throw new Error("No image URL or base64 data in Seedream response"); +} export async function generateImage( prompt: string, model: string, - args: CliArgs + args: CliArgs, ): Promise { const apiKey = getApiKey(); if (!apiKey) { @@ -61,20 +312,13 @@ export async function generateImage( ); } - const baseUrl = getBaseUrl(); - const size = getSeedreamSize(args.aspectRatio, args.quality, args.imageSize); + validateArgs(model, args); + const imageInput = await buildImageInput(model, args.referenceImages); + const requestBody = buildRequestBody(prompt, model, args, imageInput); - console.error(`Calling Seedream API (${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); }