Skip to content

Bytedance Seedream V4.5 Text To Image

Integrate

Model id bytedance/seedream/v4.5/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/v4.5/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"

This request: $0.04 40 API credits Run it on this page

Get API key
ByteDance Text to Image 4K output #stylized#transform

Text-to-image generation at 2K to 4K sizes with optional multi-image output per request

Made on Doitong

Public works made with Bytedance Seedream V4.5 by the Doitong community. Reuse a prompt in one click.

Public works shown: 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...

Build a request

Controls are generated from the model schema. The code and the price update as you change them.

•required

Text instructions for generating the image.

image_size default {"height":2048,"width...

Generated image size must satisfy either of two conditions: a total pixel count from 2560*1440 through 4096*4096, or width and height each within 1920–4096.

num_images default 1

Count of independent model generation runs using the prompt.

default 1

Set the per-generation image ceiling with `max_images`; values above one enable multi-image generation. Across `num_images` generations, each may return up to `max_images` images, giving a total output count from `num_images` through `max_images*num_images`.

Advanced seed · enable_safety_checker

Random seed governing randomness during image generation.

POST /run/bytedance/seedream/v4.5/text-to-image?wait=20 quote → $0.04
# 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/v4.5/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"

Run this request

Your key stays in this browser: it is sent only to the Doitong API and saved (localStorage) only if you tick Remember. Get an API key

About Bytedance Seedream V4.5 Text To Image

Text-only generation variant of Seedream 4.5, with no input image required. Set `prompt` and choose an `image_size` preset such as landscape_16_9, auto_2K or auto_4K, or give custom dimensions. `num_images` and `max_images` each allow up to 6, and a `seed` makes results repeatable. The response includes the seed used.

Parameters

Send either the canonical name or the native name, not both. Canonical names

NameType DefaultAllowed Description
promptrequired
Typestring
Text instructions for generating the image.
image_sizeoptional
Typeobject
Default{"height":2048,"width":2048}
square_hdsquareportrait_4_3portrait_16_9landscape_4_3landscape_16_9auto_2Kauto_4K
Generated image size must satisfy either of two conditions: a total pixel count from 2560*1440 through 4096*4096, or width and height each within 1920–4096.
num_imagesoptional num_outputs
Typeinteger
Default1
1 – 6
Count of independent model generation runs using the prompt.
max_imagesoptional
Typeinteger
Default1
1 – 6
Set the per-generation image ceiling with `max_images`; values above one enable multi-image generation. Across `num_images` generations, each may return up to `max_images` images, giving a total output count from `num_images` through `max_images*num_images`.
seedoptional
Typeinteger | null
Random seed governing randomness during image generation.
enable_safety_checkeroptional
Typeboolean
Defaulttrue
Safety-checking switch whose off setting requires account authorization. Without that authorization, every request is checked regardless of the setting; true enables the checker.
required Canonical name, also accepted

Output

GET /requests/req_8k2m4q7x1z9c3v5b6n0p2r4t
{
  "id": "req_8k2m4q7x1z9c3v5b6n0p2r4t",
  "object": "request",
  "model": "bytedance/seedream/v4.5/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": 40,
    "usd": "0.04",
    "charged": 40,
    "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"
  }
}
Your files, your choiceEvery outputs[].url is a copy on our storage: kept forever (paid per GB-month) or 7 days for free, by your account setting or ?storage=.
Same shape on every modeltype, url, content_type, width, height and duration, for images, video and audio alike. output is the model’s own result object.
Fields of output
images
array of object {url, content_type, file_name, file_size, width, height}Images produced by the model.
seed
integerSeed value used during generation.

More models: Text to Image

For AI agents: this page as Markdown is at https://doitong.com/developers/models/bytedance/seedream/v4.5/text-to-image.md. All models and guides: https://doitong.com/developers/llms.txt