Panduan Integrasi
Kesalahan
Harga & Penagihan
Seedream Image Generation
Gunakan CometAPI POST /v1/images/generations untuk generasi text-to-image dan image-to-image Seedream — mendukung output multi-gambar berurutan dan gambar referensi.
{
"created": 123,
"data": [
{
"url": "<string>",
"b64_json": "<string>",
"size": "<string>"
}
],
"usage": {
"generated_images": 123,
"output_tokens": 123,
"total_tokens": 123
},
"model": "<string>"
}Ikhtisar
Hasilkan gambar menggunakan model Seedream dari ByteDance melalui endpoint standar/v1/images/generations yang kompatibel dengan OpenAI. Mendukung generasi text-to-image dan image-to-image.
Untuk daftar model lengkap, lihat halaman Models. Untuk dokumentasi parameter terperinci dari provider, lihat dokumentasi VolcEngine.
sequential_image_generation ke auto dan secara opsional konfigurasikan sequential_image_generation_options.max_images untuk membatasi jumlah gambar output. Jumlah total gambar referensi ditambah gambar yang dihasilkan harus ≤ 15.Image-to-Image
Kirim satu atau lebih gambar referensi melalui parameterimage (array URL atau data URI base64) bersama text prompt. Mendukung hingga 14 gambar referensi.
URL yang Dikembalikan Menampilkan AccessDenied?
url yang dikembalikan adalah tautan object storage bertanda tangan yang mengandung & dan karakter khusus lainnya.Jika Anda menyalin JSON mentah dan langsung menempelkannya ke browser atau script, escaping shell atau pemotongan terminal dapat menghilangkan parameter tanda tangan, sehingga menghasilkan:
\{"Code":"AccessDenied","Message":"Access Denied","EC":"0003-00000015"\}
- curl: pipe melalui
| jq -r '.data[].url'untuk mengekstrak URL dengan bersih. - Python: gunakan
result.data[0].urlatauimage["url"]— string tersebut sudah lengkap; teruskan langsung kerequests.get()atauwebbrowser.open(). - JavaScript: konsepnya sama —
result.data[0].url. - Umum: pastikan
&dan%dalam URL tidak terpotong atau di-escape ganda.
Otorisasi
Bearer token authentication. Use your CometAPI key.
Body
Parameters for Seedream image generation (text-to-image and image-to-image).
Model to use. See the Models page for current Seedream model IDs.
Text prompt describing the image to generate. Supports both Chinese and English. Recommended max 300 Chinese characters or 1000 English characters.
Output format. url returns a temporary image link (valid for 24 hours); b64_json returns base64-encoded image data.
url, b64_json Output resolution. Presets 2K, 4K, or exact pixels like 2048x2048, 2304x1728, 2848x1600, 1600x2848, etc. Default: 2048x2048.
Reference image(s) for image-to-image generation. Each item is a public URL or base64 data URI (data:image/png;base64,...). Supports up to 14 reference images. Supported formats: jpeg, png, webp, bmp, tiff, gif.
When true, adds an 'AI Generated' watermark to the bottom-right corner of the output image.
Controls how closely the output follows the prompt. Higher values increase adherence but may reduce naturalness. Range: 1.0–10.0. Not supported by Seedream 5.0 (ignored).
Random seed for reproducible outputs. Range: -1 to 2147483647. Use -1 (default) for random generation. Legacy parameter — ignored by newer models.
Controls sequential (multi-image) generation mode.
auto: model decides whether to generate a sequence based on the promptdisabled: always generate a single image
auto, disabled Configuration for sequential (multi-image) generation. Only effective when sequential_image_generation is auto.
Show child attributes
Show child attributes
Output image file format. Options: png, jpeg.
png, jpeg Respons
Successful Response
{
"created": 123,
"data": [
{
"url": "<string>",
"b64_json": "<string>",
"size": "<string>"
}
],
"usage": {
"generated_images": 123,
"output_tokens": 123,
"total_tokens": 123
},
"model": "<string>"
}