Seedream 5.5
Text to image · Image editing
Starting price $0.05 / image
Boogu Image turns a detailed written prompt in English or Chinese into one to four images, with a negative prompt and fine control over guidance.
boogu-imageQuote the input, start the generation with the quote, then poll the job. Set RAYWAKE_API_KEY first; see Authentication.
# 1. Price the exact input (quotes are valid for up to 10 minutes)
curl -s https://api.raywake.com/v1/quotes \
-H "Authorization: Bearer $RAYWAKE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "boogu-image",
"input": {
"prompt": "A lantern-lit night market in a narrow old street, steam rising from food stalls, red paper lanterns overhead, wet stones reflecting the light, people in warm coats."
}
}'
# 2. Start the generation with the quote_id from step 1
curl -s https://api.raywake.com/v1/generate \
-H "Authorization: Bearer $RAYWAKE_API_KEY" \
-H "Content-Type: application/json" \
-H "Idempotency-Key: $(uuidgen)" \
-d '{"model": "boogu-image", "quote_id": "QUOTE_ID", "input": {"prompt":"A lantern-lit night market in a narrow old street, steam rising from food stalls, red paper lanterns overhead, wet stones reflecting the light, people in warm coats."}}'
# 3. Poll until the status is terminal
curl -s https://api.raywake.com/v1/jobs/JOB_ID \
-H "Authorization: Bearer $RAYWAKE_API_KEY"| Name | Type | Description |
|---|---|---|
promptrequired | string | The instruction describing the image to generate. Boogu-Image is bilingual — English and Chinese instructions are both supported. Detailed, descriptive prompts produce the best results. |
negative_prompt | string | Describes what should NOT appear in the image. Used for classifier-free guidance; leave empty to disable text negative guidance. |
image_size | string (enum) | The size of the generated image. The model's maximum native resolution is 2K; larger requests are clamped. Dimensions are aligned to multiples of 16. |
num_inference_steps | integer | The number of denoising steps to perform. |
guidance_scale | number | Controls how closely generation follows the text instruction. Higher values stick more closely to the prompt. A value of 1.0 disables text classifier-free guidance. |
cfg_range_start | number | Start of the timestep fraction over which CFG is applied. |
cfg_range_end | number | End of the timestep fraction over which CFG is applied. |
num_images | integer | The number of images to generate. |
seed | integer | The same seed and the same prompt given to the same version of the model will output the same image every time. |
output_format | string (enum) | The format of the generated image. |
sync_mode | boolean | If true, the media is returned as a data URI and the output is not available in the request history. |
A succeeded job lists its results under outputs, stored on our side. See Jobs for every field.
"outputs": [
{ "type": "image", "url": "https://…", "mime_type": "image/png", "thumbnail_url": "https://…" }
]The exact charge for your input comes from a quote. How charges settle
Fields marked * are required. Review the price before generating.
Boogu Image makes one to four images per run in six preset shapes, up to its native 2K, as JPEG or PNG. It reads prompts in English and in Chinese.
A negative prompt keeps unwanted things out of the picture. Steps, guidance scale and the range of the process over which guidance applies are all adjustable.