Seedream 5.5
Text to image · Image editing
Starting price $0.05 / image
By NVIDIA
Turn a scene description into large images with Sana Sprint. Try the same prompt with two preset styles to compare the look while keeping the subject fixed.
sana/sprintQuote 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": "sana/sprint",
"input": {
"prompt": "A wide panorama of a desert canyon at golden hour, a river winding through red rock walls, a small hot air balloon drifting above."
}
}'
# 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": "sana/sprint", "quote_id": "QUOTE_ID", "input": {"prompt":"A wide panorama of a desert canyon at golden hour, a river winding through red rock walls, a small hot air balloon drifting above."}}'
# 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 prompt to generate an image from. |
negative_prompt | string | The negative prompt to use. Use it to address details that you don't want in the image. This could be colors, objects, scenery and even the small details (e.g. moustache, blurry, low resolution). |
image_size | enum | The size of the generated image. |
num_inference_steps | integer | The number of inference steps to perform. |
seed | integer | The same seed and the same prompt given to the same version of the model will output the same image every time. |
guidance_scale | number | The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt when looking for a related image to show you. |
sync_mode | boolean | If `True`, the media will be returned as a data URI and the output data won't be available in the request history. |
num_images | integer | The number of images to generate. |
output_format | string (enum) | The format of the generated image. |
style_name | string (enum) | The style to generate the image in. |
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.
Sana Sprint runs two steps by default and at most 20, and gives one to four images per run. Its default size is a wide 3840 × 2160 frame; smaller square, portrait and landscape presets are there too. A style list adds a look such as Cinematic, Photographic, Anime, Pixel art or Neonpunk, and a negative prompt keeps things out.
Check object shapes, texture and whether the composition follows your brief.