Seedream 5.0 Flash is a ByteDance image model released in September 2026 that goes beyond plain generation. Besides text-to-image and fusion of up to 10 reference images, it can edit areas you mark by hand on the reference image. Output is 1K, 1.5K or 2K in 10 aspect ratios plus auto, all at one price. ByteDance also offers transparent-background output, exact pixel sizes and layer decomposition into PNG layers, but Jantaris does not expose those options yet. A 1K image takes about 90 seconds, 2K about 160.
Best for
- Changing one object in a photo while the rest stays untouched
- Wide banners at 2:1 or 21:9
- Composites that combine products, people and scenes
Prompting tips
- Every size tier costs the same, so render at 2K unless turnaround matters.
- Set the frame with
aspect_ratio(for example"16:9"or"2:1"); exact pixel sizes are not accepted on Jantaris. - Name the marked region in the prompt and state what should stay as it is.
- Jobs take a minute or more, so use a webhook or poll
/v1/tasks/{id}instead of holding a connection open.
FAQ
How much does Seedream 5.0 Flash cost?
One price covers 1K, 1.5K and 2K: $0.0343 per image. Failed generations are not charged.
Can I use layer decomposition in Seedream 5.0 Flash?
Not yet. ByteDance's model can split an image into a base plus up to 16 transparent PNG layers, but Jantaris does not expose that mode, so every request returns one regular image.
Which reference image formats does it accept?
JPEG, PNG, WebP, BMP, TIFF, GIF, HEIC and HEIF, each up to 30 MB and 36 MP. You can send up to 10 per request.
How to call Seedream 5.0 Flash 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-flash",
"input": {
"prompt": "Product photo of a matte black ceramic coffee cup on a travertine table, soft window light, 50mm",
"aspect_ratio": "auto",
"resolution": "1K"
}
}'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-flash",
"input": {
"prompt": "Product photo of a matte black ceramic coffee cup on a travertine table, soft window light, 50mm",
"aspect_ratio": "auto",
"resolution": "1K"
}
}).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-flash",
"input": {
"prompt": "Product photo of a matte black ceramic coffee cup on a travertine table, soft window light, 50mm",
"aspect_ratio": "auto",
"resolution": "1K"
}
}),
})).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 | ≤ 32000 chars | |
aspect_ratio | string | auto 1:1 4:3 3:4 16:9 9:16 3:2 2:3 2:1 1:2 21:9 | auto |
resolution | string | 1K 1.5K 2K | 1K |
num_images | integer | 1-1 | 1 |
image_urls | array | max 10 |
The same schema is available from GET /v1/models/seedream-5.0-flash.
