Seedream 4.5 Edit Sequential performs multi-image editing while locking character and object identity across shots. It detects main subjects, preserves continuity, and applies controlled edits with up to 4K output. Ready-to-use REST inference API, best performance, no cold starts, affordable pricing.
就緒
/filters:quality(85)/examples/dc99300d091c7cc56ee8fa24c51850b4/35fd69f6-8325-4075-86e9-759fa916a21d-8123d6e00cb0.webp)
/filters:quality(85)/examples/dc99300d091c7cc56ee8fa24c51850b4/2af51087-4afa-4aca-900b-503dd904e872-a01894e29b23.webp)
$0.04每次運行·~25 / $1
/filters:quality(82)/examples/dc99300d091c7cc56ee8fa24c51850b4/35fd69f6-8325-4075-86e9-759fa916a21d-8123d6e00cb0.webp)
I want to generate 2 images. Transform this portrait into a Lovecraftian cosmic horror character poster. Preserve the man's face, identity, pose, coat structure, and exhausted expression. Replace the plain background with a dim, decaying study filled with ancient books, damp walls, and occult notes. Add faint greenish fog, subtle eldritch symbols glowing behind him, and a massive shadowy tentacled silhouette barely visible in the darkness above. Make his eyes look more haunted, as if he has seen something beyond human understanding. Keep it atmospheric, realistic, and psychologically disturbing rather than overly graphic.
/filters:quality(82)/examples/39f507dfc56649e220356251a9f40687/ac463ea8-2fd7-401e-b995-f743b4cf1af1-1e216017acac.webp)
I want to generate 4 images. Show this same golden retriever in four seasons on the same farmhouse porch: spring with cherry blossoms, summer with bright sunshine, autumn with falling orange leaves, and winter with fresh snow. Keep the dog's look consistent in every image.
/filters:quality(82)/examples/cbcc2a841f9bf0a6db5336f2acec047c/4a996ca6-35e6-49d7-9ee0-aeab593be7b5-0439ad666e53.webp)
I want to generate 3 images. Create a storyboard of this man's morning in the city: buying coffee from a street cart, reading a book on a subway train, and arriving at a sunny rooftop office terrace. Keep his face, hairstyle and denim jacket consistent across all frames, cinematic photography.
/filters:quality(82)/examples/845cedcdad2390fa5826e2c2a3e94366/e2ed0802-e481-473c-906b-92b6c7a559d6-0fbf9dac7379.webp)
I want to generate 3 images. Create a social media product campaign for this dropper bottle: one on a sunlit bathroom shelf with green plants, one floating above rippling water with orange slices, and one held in a hand against a soft pastel background. Keep the bottle design identical, no text or logos.
/filters:quality(82)/examples/2d8fb1b430c156378f8f0f535288a5d6/d2d8e6f9-ae63-4d0c-a638-d64f8f7e8254-31fe5aa89973.webp)
I want to generate 4 images. Turn this red panda into the hero of a children's picture book illustrated in soft watercolor style: waking up in a tree hollow, sharing berries with a squirrel, crossing a log bridge over a stream, and falling asleep under the stars. Keep the red panda's appearance consistent, no text.
Seedream 4.5 Edit Sequential is ’s multi-image editing model designed to apply the same edit across a whole set of images. It automatically tracks the main subject through the series, keeps identity stable, and generates clean, high-resolution results—ideal for campaigns, product sets, and character line-ups.
Billing is per output image, scaled by the max_images you request.
Example costs:
| max_images | Total price |
|---|---|
| 1 | $0.04 |
| 4 | $0.16 |
| 8 | $0.32 |
Upload source images Add the images you want to edit sequentially (all should contain the same main subject or product).
Write the edit prompt Describe the shared change you want across the whole set, e.g. “Change outfit to a black suit, add soft studio lighting, keep poses and background the same.”
Set max_images Specify how many edited outputs you want the model to generate from your input set.
Choose size Select the target resolution, up to 8192 × 8192 for maximum detail.
Run and review Submit the job, inspect the edited series, and optionally refine the prompt for another pass.
Please set the max_image first, and then input how many images you want to generate in prompt! Such as:
max_image = 4. Prompt: I want to generate 4 images... + (your prompt)
Google’s ultra, fast text-to-image model for generating many ideas from scratch; great for large batches of new images, not for editing existing photo series.
’s high-resolution text-to-image generator with rich detail and diverse styles; ideal when you want new scenes in the Seedream aesthetic rather than editing your own photos.
Single-image, prompt-based editing with strong semantic understanding; perfect for one-off or small-batch edits where you don’t need strict identity matching across many images.
Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/bytedance/seedream-v4.5/edit-sequential with your input as JSON. The endpoint returns a prediction id. Start polling the result endpoint around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. On completed, read output values from data.outputs. Examples for Seedream v4.5 Edit Sequential below.
set -euo pipefail
: "${WAVESPEED_API_KEY:?Set WAVESPEED_API_KEY}"
REQUEST_BODY=$(cat <<'JSON'
{
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"images": [
"https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg"
],
"max_images": 1
}
JSON
)
# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
-X POST "https://api.wavespeed.ai/api/v3/bytedance/seedream-v4.5/edit-sequential" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $WAVESPEED_API_KEY" \
-d "$REQUEST_BODY")
TASK=$(printf '%s' "$SUBMIT_RESPONSE" | jq 'if has("data") then .data else . end')
PREDICTION_ID=$(printf '%s' "$TASK" | jq -r '.id')
if [ -z "$PREDICTION_ID" ] || [ "$PREDICTION_ID" = "null" ]; then
printf 'Submission response did not contain a prediction id
' >&2
exit 1
fi
RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/$PREDICTION_ID/result"
# 2. Poll until the prediction finishes.
while true; do
RESPONSE=$(curl --silent --show-error --fail-with-body "$RESULT_URL" \
-H "Authorization: Bearer $WAVESPEED_API_KEY")
RESULT=$(printf '%s' "$RESPONSE" | jq 'if has("data") then .data else . end')
STATUS=$(printf '%s' "$RESULT" | jq -r '.status')
case "$STATUS" in
completed) printf '%s\n' "$RESULT" | jq '.outputs'; break ;;
failed|cancelled|timeout|deleted) printf '%s\n' "$RESULT" | jq . >&2; exit 1 ;;
*) sleep 2 ;;
esac
doneconst submitUrl = "https://api.wavespeed.ai/api/v3/bytedance/seedream-v4.5/edit-sequential";
const apiKey = process.env.WAVESPEED_API_KEY;
if (!apiKey) throw new Error('Set WAVESPEED_API_KEY');
async function requestJson(url, options = {}) {
const response = await fetch(url, options);
if (!response.ok) throw new Error(await response.text());
return response.json();
}
// 1. Submit the prediction.
const body = await requestJson(submitUrl, {
method: "POST",
headers: {
"Authorization": `Bearer ${apiKey}`,
"Content-Type": "application/json",
},
body: JSON.stringify({
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"images": [
"https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg"
],
"max_images": 1
}),
});
const task = body.data ?? body;
if (!task.id) throw new Error("Submission response did not contain a prediction id");
const resultUrl = `https://api.wavespeed.ai/api/v3/predictions/${task.id}/result`;
// 2. Poll until the prediction finishes.
while (true) {
const resultBody = await requestJson(resultUrl, {
headers: { "Authorization": `Bearer ${apiKey}` },
});
const result = resultBody.data ?? resultBody;
if (result.status === "completed") {
console.log(result.outputs);
break;
}
if (["failed", "cancelled", "timeout", "deleted"].includes(result.status)) throw new Error(JSON.stringify(result));
await new Promise(resolve => setTimeout(resolve, 2000));
}import json
import os
import time
from urllib.request import Request, urlopen
api_key = os.environ["WAVESPEED_API_KEY"]
headers = {"Authorization": f"Bearer {api_key}", "Content-Type": "application/json"}
payload = {
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"images": [
"https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg"
],
"max_images": 1
}
def request_json(url, data=None):
request = Request(url, data=data, headers=headers, method="POST" if data else "GET")
with urlopen(request) as response:
return json.load(response)
# 1. Submit the prediction.
body = request_json("https://api.wavespeed.ai/api/v3/bytedance/seedream-v4.5/edit-sequential", json.dumps(payload).encode())
task = body.get("data", body)
if not task.get("id"):
raise RuntimeError("Submission response did not contain a prediction id")
result_url = f"https://api.wavespeed.ai/api/v3/predictions/{task['id']}/result"
# 2. Poll until the prediction finishes.
while True:
result_body = request_json(result_url)
result = result_body.get("data", result_body)
status = result.get("status")
if status == "completed":
print(result.get("outputs", []))
break
if status in {"failed", "cancelled", "timeout", "deleted"}:
raise RuntimeError(result)
time.sleep(2)Seedream v4.5 Edit Sequential is a ByteDance model for image editing, exposed as a REST API on WaveSpeedAI. Seedream 4.5 Edit Sequential performs multi-image editing while locking character and object identity across shots. It detects main subjects, preserves continuity, and applies controlled edits with up to 4K output. Ready-to-use REST inference API, best performance, no cold starts, affordable pricing. You can call it programmatically or try it from the playground above.
POST your input parameters to the model's REST endpoint (shown in the API tab of this playground) with your WaveSpeedAI API key in the Authorization header. Submission returns a prediction ID. Poll the result endpoint starting around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. The playground generates Python, JavaScript, and cURL examples for submitting requests and polling results. Full request/response shape is documented at https://wavespeed.ai/docs/docs-api/bytedance/bytedance-seedream-v4.5-edit-sequential.
Seedream v4.5 Edit Sequential starts at $0.04 per run. That figure is the base price — the final charge scales with the parameters you set in the form (output size, length, count, references, or whatever knobs this model exposes), so a higher-quality or larger output costs more than a minimal one. The exact cost for your current input is shown live next to the Generate button before you submit, and the actual per-call charge is recorded on the prediction afterwards.
Key inputs: `prompt`, `images`, `enable_base64_output`, `enable_sync_mode`, `max_images`. The full JSON schema (types, defaults, allowed values) is rendered above the Generate button and mirrored in the API reference at https://wavespeed.ai/docs/docs-api/bytedance/bytedance-seedream-v4.5-edit-sequential.
Reported generation time on WaveSpeedAI is around 65 seconds per request. This is an estimate, not a latency guarantee; queue time and input settings can change the total wait. live status is visible in the prediction record.
Commercial usage rights depend on the model's license, set by its provider (ByteDance). Check the provider's applicable terms and WaveSpeedAI's Terms of Service before commercial use.