模型市场支持← 返回应用

Seedream

Seedream 模型通过一个统一的异步任务 API 调用。用 POST /api/generate 发起任务，再轮询 GET /api/generate/{taskId} 直到完成。本系列提供 11 个端点。

概览

每个端点共享相同的外层结构 —— 只有 model 和 input 字段不同。可在模型市场的 playground 中运行任意一个。

认证

在 /api-keys 创建 API 密钥，然后作为 Bearer token 发送。已登录时从浏览器发起的请求也可通过会话 cookie 生效。

Authorization: Bearer <YOUR_API_KEY>

创建任务

POST
POST https://api.lithovas.com/api/generate

请求体：{ "model": "<slug>", "input": { … } }

响应：{ "taskId": "<id>", "state": "waiting" }

查询结果

GET
GET https://api.lithovas.com/api/generate/<taskId>

响应：{ "taskId", "state": "waiting" | "success" | "fail", "resultUrls": [ … ], "creditsConsumed", "failMsg", "balance" }

异步
创建任务返回 200 只表示任务已被接受 —— 并非已完成。请轮询此端点，直到 state 变为 success 或 fail。失败任务不计费。

端点

模型任务model slug
SeedreamText to Imageseedream/seedream
Seedream V4Text to Imageseedream/seedream-v4-text-to-image
Seedream V4 EditImage Editingseedream/seedream-v4-edit
Seedream 4.5Text to Imageseedream/4-5-text-to-image
Seedream 4.5 EditImage Editingseedream/4-5-edit
Seedream 5 LiteText to Imageseedream/5-lite-text-to-image
Seedream 5 LiteImage to Imageseedream/5-lite-image-to-image
Seedream 5 ProText to Imageseedream/5-pro-text-to-image
Seedream 5 ProImage to Imageseedream/5-pro-image-to-image
Seedream 5 Pro Layer DecompositionImage Editingseedream/5-pro-layer-decomposition
Seedream V3Text to Imageseedream/seedream-v3

Seedream · Text to Image

POSTText to Imageseedream/seedream
input 字段
promptstring必填

Text prompt for image generation (max 5000 characters)

image_sizeenum<string>可选

Output image dimensions and aspect ratio

guidance_scalenumber可选

Controls prompt alignment strength; range 1-10 (step 0.1)

seedinteger可选

Random seed for controlling generation stochasticity

示例
cURL
curl -X POST https://api.lithovas.com/api/generate \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "seedream/seedream",
  "input": {
    "prompt": "A cinematic red panda surfing through neon rain at dusk.",
    "image_size": "square_hd",
    "guidance_scale": 2.5,
    "seed": 42
  }
}'

Seedream V4 · Text to Image

POSTText to Imageseedream/seedream-v4-text-to-image
input 字段
promptstring必填

Text prompt for image generation (max 5000 characters)

image_sizeenum<string>可选

Aspect ratio of generated image

image_resolutionenum<string>可选

Pixel scale determining final resolution

max_imagesnumber可选

Number of images to generate per run (1-6)

seedinteger可选

Random seed for controlling generation stochasticity

nsfw_checkerboolean可选

Enable/disable content filtering on results

示例
cURL
curl -X POST https://api.lithovas.com/api/generate \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "seedream/seedream-v4-text-to-image",
  "input": {
    "prompt": "A cinematic red panda surfing through neon rain at dusk.",
    "image_size": "square_hd",
    "image_resolution": "1K",
    "max_images": 1,
    "seed": 42,
    "nsfw_checker": false
  }
}'

Seedream V4 Edit · Image Editing

POSTImage Editingseedream/seedream-v4-edit
input 字段
promptstring必填

Text prompt for image editing (max 5000 characters)

image_urlsarray<string>必填

URLs of input images for editing (up to 10 images, max 10MB each)

image_sizeenum<string>可选

Aspect ratio of generated image

image_resolutionenum<string>可选

Pixel scale determining final resolution

max_imagesnumber可选

Number of images to generate per run (1-6)

seedinteger可选

Random seed for controlling generation stochasticity

nsfw_checkerboolean可选

Enable/disable content filtering on results

示例
cURL
curl -X POST https://api.lithovas.com/api/generate \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "seedream/seedream-v4-edit",
  "input": {
    "prompt": "A cinematic red panda surfing through neon rain at dusk.",
    "image_urls": [
      "https://example.com/input.jpg"
    ],
    "image_size": "square_hd",
    "image_resolution": "1K",
    "max_images": 1,
    "seed": 42,
    "nsfw_checker": false
  }
}'

Seedream 4.5 · Text to Image

POSTText to Imageseedream/4-5-text-to-image
input 字段
promptstring必填

Text description of the image to generate (max 3000 characters)

aspect_ratioenum<string>必填

Width-height ratio determining the image's visual form

qualityenum<string>必填

Output resolution: basic (2K) or high (4K)

nsfw_checkerboolean可选

Content filtering toggle; false disables filtering

示例
cURL
curl -X POST https://api.lithovas.com/api/generate \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "seedream/4-5-text-to-image",
  "input": {
    "prompt": "A cinematic red panda surfing through neon rain at dusk.",
    "aspect_ratio": "1:1",
    "quality": "basic",
    "nsfw_checker": false
  }
}'

Seedream 4.5 Edit · Image Editing

POSTImage Editingseedream/4-5-edit
input 字段
promptstring必填

Text description of the image to generate (max 3000 chars)

image_urlsarray<string>必填

Input image files for the API (max 14 images, 10MB each)

aspect_ratioenum<string>必填

Width-height ratio of the image, determining its visual form

qualityenum<string>必填

Basic outputs 2K images, High outputs 4K images

nsfw_checkerboolean可选

Toggle content filtering; disabled when false

示例
cURL
curl -X POST https://api.lithovas.com/api/generate \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "seedream/4-5-edit",
  "input": {
    "prompt": "A cinematic red panda surfing through neon rain at dusk.",
    "image_urls": [
      "https://example.com/input.jpg"
    ],
    "aspect_ratio": "1:1",
    "quality": "basic",
    "nsfw_checker": false
  }
}'

Seedream 5 Lite · Text to Image

POSTText to Imageseedream/5-lite-text-to-image
input 字段
promptstring必填

Text description of the image to generate (3-3000 characters)

aspect_ratioenum<string>必填

Width-height ratio of the image, determining its visual form

qualityenum<string>必填

Basic outputs 2K images; High outputs 4K images

output_formatenum<string>可选

Format of the output image

nsfw_checkerboolean可选

Disable content filtering when false

示例
cURL
curl -X POST https://api.lithovas.com/api/generate \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "seedream/5-lite-text-to-image",
  "input": {
    "prompt": "A cinematic red panda surfing through neon rain at dusk.",
    "aspect_ratio": "1:1",
    "quality": "basic",
    "output_format": "png",
    "nsfw_checker": false
  }
}'

Seedream 5 Lite · Image to Image

POSTImage to Imageseedream/5-lite-image-to-image
input 字段
promptstring必填

Text prompt describing the desired output.

image_urlsstring[]必填

One or more source image URLs to condition on.

示例
cURL
curl -X POST https://api.lithovas.com/api/generate \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "seedream/5-lite-image-to-image",
  "input": {
    "prompt": "a red panda",
    "image_urls": [
      "https://example.com/in.jpg"
    ]
  }
}'

Seedream 5 Pro · Text to Image

POSTText to Imageseedream/5-pro-text-to-image
input 字段
promptstring必填

Text description of the image to generate (3-5000 characters)

aspect_ratiostring必填

Width-height ratio of the image, determining its visual form

qualitystring必填

Basic outputs 1K images, while High outputs 2K images

output_formatstring可选

Format of the output image

nsfw_checkerboolean可选

Content filtering toggle; when false, filtering is disabled

示例
cURL
curl -X POST https://api.lithovas.com/api/generate \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "seedream/5-pro-text-to-image",
  "input": {
    "prompt": "A cinematic red panda surfing through neon rain at dusk.",
    "aspect_ratio": "1:1",
    "quality": "basic",
    "output_format": "png",
    "nsfw_checker": false
  }
}'

Seedream 5 Pro · Image to Image

POSTImage to Imageseedream/5-pro-image-to-image
input 字段
promptstring必填

Text description of image to generate (3-5000 characters)

image_urlsarray<string>必填

Input image file URLs (JPEG/PNG/WebP, max 10MB each, up to 10 images)

aspect_ratiostring必填

Width-height ratio determining visual form

qualitystring必填

Output resolution: basic (1K) or high (2K)

output_formatstring可选

Format of output image

nsfw_checkerboolean可选

Enable content filtering; false disables filtering

示例
cURL
curl -X POST https://api.lithovas.com/api/generate \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "seedream/5-pro-image-to-image",
  "input": {
    "prompt": "A cinematic red panda surfing through neon rain at dusk.",
    "image_urls": [
      "https://example.com/input.jpg"
    ],
    "aspect_ratio": "1:1",
    "quality": "basic",
    "output_format": "png",
    "nsfw_checker": false
  }
}'

Seedream 5 Pro Layer Decomposition · Image Editing

POSTImage Editingseedream/5-pro-layer-decomposition
input 字段
promptstring必填

Instructions describing which visual elements to separate into independent layers. Supports bbox references such as <bbox>179 58 809 197</bbox>.

image_urlstring必填

Source image URL to decompose into editable layers.

sizeenum<string>可选

Output resolution tier.

output_formatenum<string>可选

Generated layer image format.

示例
cURL
curl -X POST https://api.lithovas.com/api/generate \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "seedream/5-pro-layer-decomposition",
  "input": {
    "prompt": "A cinematic red panda surfing through neon rain at dusk.",
    "image_url": "https://example.com/input.jpg",
    "size": "auto",
    "output_format": "jpeg"
  }
}'

Seedream V3 · Text to Image

POSTText to Imageseedream/seedream-v3
input 字段
promptstring必填

Text prompt describing the desired output.

aspect_ratiostring可选

Output aspect ratio, e.g. "1:1", "16:9".

示例
cURL
curl -X POST https://api.lithovas.com/api/generate \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "seedream/seedream-v3",
  "input": {
    "prompt": "a red panda",
    "aspect_ratio": "1:1"
  }
}'