Seedream 5.0 Lite is ByteDance's Doubao Seedream 5.0 Lite, released in February 2026. It does text-to-image, image-to-image and fusion of several reference images, and outputs at 2K or 3K, for example 2048x2048 or 4096x2304. It can return up to 4 images in one call as a consistent series, which helps with carousels and storyboards. There are 8 aspect ratios plus auto, and prompts can be up to 4,000 characters.
Best for
- Instagram carousels and comic panels that share one style
- High-resolution 3K backgrounds and wallpapers
- Merging a product and a scene reference into one image
- Storyboards with the same character across frames
Prompting tips
- Set
num_imagesabove 1 to get a sequential set, and describe how the frames differ: "panel 1: ..., panel 2: ...". autoratio only works with reference images. For text-to-image, pick an explicit ratio.- References must be JPEG or PNG, up to 10 MB and 6000x6000 px, with a ratio between 1:3 and 3:1.
- Use 3k when the image will be cropped or printed.
FAQ
What does Seedream 5.0 Lite cost?
Jantaris charges from $0.077 per image. The estimated cost appears before you submit, and failed generations are not charged.
Can Seedream 5.0 Lite make 1K or 4K images?
No. It supports 2K and 3K only. If you need 4K, look at Nano Banana Pro or Wan 2.7 Image Pro.
Does Seedream 5.0 Lite support 9:21?
No, 9:21 returns an error. Use 9:16 for vertical formats or 21:9 for wide ones.
How to call Seedream 5.0 Lite via API
curl https://jantaris.com/v1/generate?wait=60 \
-H "Authorization: Bearer $JANTARIS_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "seedream-5.0-lite",
"input": {
"prompt": "Product photo of a matte black ceramic coffee cup on a travertine table, soft window light, 50mm",
"aspect_ratio": "1:1",
"resolution": "2k"
}
}'import os, time, requests
API = "https://jantaris.com/v1"
H = {"Authorization": f"Bearer {os.environ['JANTARIS_API_KEY']}"}
task = requests.post(f"{API}/generate", headers=H, json={
"model": "seedream-5.0-lite",
"input": {
"prompt": "Product photo of a matte black ceramic coffee cup on a travertine table, soft window light, 50mm",
"aspect_ratio": "1:1",
"resolution": "2k"
}
}).json()
while task["status"] in ("queued", "running"):
time.sleep(3)
task = requests.get(f"{API}/tasks/{task['id']}", headers=H).json()
print(task["status"], task["cost"], [o["url"] for o in task["output"]])const API = "https://jantaris.com/v1";
const headers = { Authorization: `Bearer ${process.env.JANTARIS_API_KEY}`, "Content-Type": "application/json" };
let task = await (await fetch(`${API}/generate`, {
method: "POST",
headers,
body: JSON.stringify({
"model": "seedream-5.0-lite",
"input": {
"prompt": "Product photo of a matte black ceramic coffee cup on a travertine table, soft window light, 50mm",
"aspect_ratio": "1:1",
"resolution": "2k"
}
}),
})).json();
while (task.status === "queued" || task.status === "running") {
await new Promise((r) => setTimeout(r, 3000));
task = await (await fetch(`${API}/tasks/${task.id}`, { headers })).json();
}
console.log(task.status, task.cost, task.output.map((o) => o.url));
Parameters
| Parameter | Type | Allowed | Default |
|---|---|---|---|
prompt * | string | ≤ 4000 chars | |
aspect_ratio | string | 1:1 4:3 3:4 16:9 9:16 3:2 2:3 21:9 auto | 1:1 |
resolution | string | 2k 3k | 2k |
num_images | integer | 1-4 | 1 |
image_urls | array | max 4 |
The same schema is available from GET /v1/models/seedream-5.0-lite.









