Langkau ke kandungan

Seedream · Lite · Text to Image

Integrasikan

ID model bytedance/seedream/v5/lite/text-to-image
# Run the model; wait up to 20 s for the finished result in the same call
curl -X POST "https://api.doitong.com/v1/run/bytedance/seedream/v5/lite/text-to-image?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
  }'

# Still "queued" or "running"? Poll with the id from the response:
curl "https://api.doitong.com/v1/requests/REQUEST_ID?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY"

Permintaan ini: $0.035 35 kredit API Jalankan pada halaman ini

Dapatkan kunci API
ByteDance Teks ke Imej Output 4KPantas #text-to-image#bytedance#seedream-5.0-lite

Teks-ke-imej Seedream 5 Lite dengan tahap saiz 2K hingga 4K dan penjanaan berbilang imej

Dibuat di Doitong

Karya awam yang dibuat dengan Seedream 5.0 oleh komuniti Doitong. Guna semula prompt dengan satu klik.

Karya awam dipaparkan: 16
Создайте 20-секундный анимационный ролик в ярком, мультяшном стиле для Instagram. Сюжет: человек ...

Создайте 20-секундный анимационный ролик в ярком, мультяшном стиле для Instagram. Сюжет: человек с вдохновением собирается начать что-то новое (например, рисовать на холсте). Внезапно появляется его Мозг в виде забавного персонажа, который начинает активно мешать: показывает смешные картинки...

Art style: Cinematic Realistic. A hand gently reaching out to a wooden bookshelf filled with beau...

Art style: Cinematic Realistic. A hand gently reaching out to a wooden bookshelf filled with beautifully bound books. The fingers softly touch the spines. Warm, golden hour lighting. No faces. ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ FINAL STYLE ENFORCEMENT (this is the authoritative rendering...

Art style: Studio Ghibli animation style, lush forest and waterfall setting, warm sunlight filter...

Art style: Studio Ghibli animation style, lush forest and waterfall setting, warm sunlight filtering through trees, cozy wooden treehouse, high detail, 4K.. Studio Ghibli animation style. Close-up of Elara's hands carefully picking one of the glowing mushrooms and placing it into a small woven...

Art style: Cinematic Realistic. Maya standing in the near foreground; Eleanora standing further b...

Art style: Cinematic Realistic. Maya standing in the near foreground; Eleanora standing further back in the frame. Three feet of terracotta floor between them. Maya is standing on terracotta floor in the near foreground in the midground. Torso in three-quarter turn to screen-right. Head in...

A still from a 3D animated feature film, vertical 9:16, stylised appealing characters with expres...

A still from a 3D animated feature film, vertical 9:16, stylised appealing characters with expressive eyes, soft warm cinematic lighting, richly detailed setting, no text, no captions. Nepal, 1993. The main character is a 3-year-old girl, seen in an ordinary modest village setting. Scene: A cake...

A still from a 3D animated feature film, vertical 9:16, stylised appealing characters with expres...

A still from a 3D animated feature film, vertical 9:16, stylised appealing characters with expressive eyes, soft warm cinematic lighting, richly detailed setting, no text, no captions. Mumbai, India, 1996. The main character is a 8-year-old girl, seen in an ordinary poor city setting. Scene: You...

A still from a 3D animated feature film, vertical 9:16, stylised appealing characters with expres...

A still from a 3D animated feature film, vertical 9:16, stylised appealing characters with expressive eyes, soft warm cinematic lighting, richly detailed setting, no text, no captions. Bamenda, Cameroon, 1973. The main character is a 5-year-old boy, seen in an ordinary poor city setting. Scene:...

A cinematic film still, vertical 9:16, natural light, documentary realism, no text, no captions. ...

A cinematic film still, vertical 9:16, natural light, documentary realism, no text, no captions. Bengaluru, India, 1967. The main character is a 3-year-old boy, seen in an ordinary modest city setting. Scene: A cake with candles. You blow so hard that wax lands on the icing, and everyone claps...

Bina permintaan

Kawalan dijana daripada skema model. Kod dan harga dikemas kini apabila anda mengubahnya.

•diperlukan

Arahan teks untuk menjana imej.

lalai auto_2K

Saiz imej yang dijana, diskalakan secara automatik apabila perlu untuk mengekalkan jumlah piksel sekurang-kurangnya 2560×1440 dan tidak melebihi 4096×4096.

num_images lalai 1

Bilangan proses penjanaan model bebas yang menggunakan prompt.

lalai 1

Tetapkan had imej setiap penjanaan dengan `max_images`; nilai melebihi satu mendayakan penjanaan berbilang imej. Merentas `num_images` penjanaan, setiap satu boleh mengembalikan sehingga `max_images` imej, menghasilkan jumlah output daripada `num_images` hingga `max_images*num_images`.

Lanjutan enable_safety_checker · return_byteplus_urls
POST /run/bytedance/seedream/v5/lite/text-to-image?wait=20 sebut harga → $0.035
# Run the model; wait up to 20 s for the finished result in the same call
curl -X POST "https://api.doitong.com/v1/run/bytedance/seedream/v5/lite/text-to-image?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
  }'

# Still "queued" or "running"? Poll with the id from the response:
curl "https://api.doitong.com/v1/requests/REQUEST_ID?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY"

Jalankan permintaan ini

Kunci anda kekal dalam pelayar ini: ia hanya dihantar kepada Doitong API dan disimpan (localStorage) hanya jika anda menanda Ingat. Dapatkan kunci API

Tentang Seedream · Lite · Text to Image

Menjana imej daripada prompt teks. `image_size` menerima pratetap seperti square_hd dan landscape_16_9 atau auto_2K, auto_3K dan auto_4K, dengan jumlah piksel antara 2560x1440 dan 4096x4096. `num_images` menetapkan 1 hingga 6 penjanaan dan `max_images` membolehkan setiap penjanaan mengembalikan beberapa imej. `return_byteplus_urls` secara pilihan mengembalikan URL dipercayai yang luput dalam 24 jam.

Parameter

Hantar sama ada nama kanonik atau nama natif, bukan kedua-duanya. Nama kanonik

NamaJenis LalaiDibenarkan Penerangan
promptdiperlukan
Jenisstring
Arahan teks untuk menjana imej.
image_sizepilihan
Jenisobject
Lalaiauto_2K
square_hdsquareportrait_4_3portrait_16_9landscape_4_3landscape_16_9auto_2Kauto_3Kauto_4K
Saiz imej yang dijana, diskalakan secara automatik apabila perlu untuk mengekalkan jumlah piksel sekurang-kurangnya 2560×1440 dan tidak melebihi 4096×4096.
num_imagespilihan num_outputs
Jenisinteger
Lalai1
1 – 6
Bilangan proses penjanaan model bebas yang menggunakan prompt.
max_imagespilihan
Jenisinteger
Lalai1
1 – 6
Tetapkan had imej setiap penjanaan dengan `max_images`; nilai melebihi satu mendayakan penjanaan berbilang imej. Merentas `num_images` penjanaan, setiap satu boleh mengembalikan sehingga `max_images` imej, menghasilkan jumlah output daripada `num_images` hingga `max_images*num_images`.
enable_safety_checkerpilihan
Jenisboolean
Lalaitrue
Suis pemeriksaan keselamatan yang tetapan matinya memerlukan kebenaran akaun. Tanpa kebenaran itu, setiap permintaan diperiksa tanpa mengira tetapan; true mendayakan pemeriksa.
return_byteplus_urlspilihan
Jenisboolean
Lalaifalse
Dayakan ini untuk menerima URL dipercayai bagi seedance-2 dengan tempoh sah 24 jam.
diperlukan Nama kanonik, turut diterima

Output

GET /requests/req_8k2m4q7x1z9c3v5b6n0p2r4t
{
  "id": "req_8k2m4q7x1z9c3v5b6n0p2r4t",
  "object": "request",
  "model": "bytedance/seedream/v5/lite/text-to-image",
  "status": "succeeded",
  "created_at": "2026-10-20T12:00:00Z",
  "started_at": "2026-10-20T12:00:02Z",
  "completed_at": "2026-10-20T12:00:09Z",
  "queue_position": null,
  "cost": {
    "credits": 35,
    "usd": "0.035",
    "charged": 35,
    "refunded": 0
  },
  "input": {
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
  },
  "output": {
    "images": [
      {
        "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.jpeg",
        "content_type": "image/jpeg",
        "file_name": "0-output.jpeg",
        "file_size": 1843200,
        "width": 1024,
        "height": 768
      }
    ],
    "seed": 42
  },
  "outputs": [
    {
      "type": "image",
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.jpeg",
      "content_type": "image/jpeg",
      "file_size": 1843200,
      "width": 1024,
      "height": 768,
      "stored": true
    }
  ],
  "error": null,
  "metrics": {
    "inference_seconds": 6.8
  },
  "urls": {
    "self": "https://api.doitong.com/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t",
    "cancel": "https://api.doitong.com/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t/cancel"
  }
}
Fail anda, pilihan andaSetiap outputs[].url ialah salinan pada storan kami: disimpan selama-lamanya (dibayar setiap GB-bulan) atau 7 hari secara percuma, mengikut tetapan akaun anda atau ?storage=.
Bentuk yang sama pada setiap modeltype, url, content_type, width, height dan duration, untuk imej, video dan audio. output ialah objek hasil model itu sendiri.
Medan output
images
array of object {url, content_type, file_name, file_size, width, height}Imej yang dihasilkan oleh model.
seed
integerSeed yang digunakan semasa penjanaan.

Lebih banyak model: Teks ke Imej

Untuk ejen AI: halaman ini dalam Markdown tersedia di https://doitong.com/ms/developers/models/bytedance/seedream/v5/lite/text-to-image.md. Semua model dan panduan: https://doitong.com/developers/llms.txt