Seedream V5.0 Pro Edit by ByteDance edits and generates images from single-image or multi-reference inputs, supporting up to 10 reference images, aspect ratio selection, and 1K / 2K output tiers. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
Chờ

$0.0405cho mỗi lần chạy·~24 / $1

Transform this image into a premium kitchen appliance commercial. Preserve the chef's face, chef jacket, posture, and kitchen composition. Upgrade the kitchen into a bright, modern luxury kitchen with elegant countertops, warm sunlight, polished appliances, clean reflections, fresh ingredients, and a professional lifestyle advertisement atmosphere. Keep it realistic, clean, warm, and trustworthy.

Turn this sunny old-town street into a rainy night scene. Keep the buildings, windows, flower boxes and perspective exactly the same. Make the cobblestones wet and glossy, reflecting warm glowing street lamps and lit windows, add light rain streaks and a soft blue evening mist, cinematic moody atmosphere.

Create a premium lifestyle ad: the woman from Figure 1 wears the black over-ear headphones from Figure 2 and smiles with her eyes closed, enjoying music in the rain. Keep her face, bob haircut and yellow raincoat unchanged. Keep the headphones design exactly as shown, no logos. Soft cinematic lighting, shallow depth of field.

Turn this pencil sketch into a photorealistic fantasy matte painting. Keep the exact castle layout, towers, cliff and winding path from the sketch. Render it at golden sunset with warm light on stone walls, glowing windows, drifting clouds, a waterfall falling from the cliff and birds in the sky, epic cinematic scale.

Turn this empty storefront into a charming, busy flower shop. Paint the blank sign board dark green with elegant gold lettering that reads "WILDFLOWER & CO.". Fill the windows with colorful bouquets and hanging plants, place buckets of fresh flowers and a small chalkboard stand reading "FRESH TODAY" on the sidewalk. Keep the building architecture and camera angle unchanged.
Seedream V5.0 Pro Edit is a multimodal image editing model built for professional work: interactive precision editing, multi-reference control, photographic realism, and native multilingual text.
Multi-image reference editing
Use up to 10 reference images for complex edits, compositions, and visual guidance.
Natural language editing
Describe the desired edit in plain text and let the model transform the input images accordingly.
Pro image quality
Designed for high-quality image editing with strong prompt adherence and polished visual output.
Flexible resolution tiers
Choose 1k or 1.5k for lower-cost edits, or 2k for higher-resolution output.
Flexible aspect ratios
Supports square, portrait, landscape, tall, and wide aspect ratios.
Standard output formats
Generate edited images in jpeg or png format.
| Parameter | Required | Description |
|---|---|---|
| prompt | Yes | Text description of the desired edit. |
| images | Yes | Reference image URLs or Base64 strings. Supports up to 10 images. |
| aspect_ratio | No | Output aspect ratio. |
| resolution | No | Output resolution tier: 1k, 1.5k, or 2k. |
| output_format | No | Output format: jpeg or png. |
| prompt_optimization_mode | No | Prompt optimization mode: standard (default) or fast. The model rewrites your prompt before generating; fast uses a lighter rewrite that returns several times quicker but follows long or intricate prompts less closely. Reference time: 14s (fast) vs 26s (standard) on the same prompt. |
1k or 1.5k for lower-cost edits, or 2k for higher-resolution output.jpeg or png.Pricing includes the selected output resolution plus reference image input cost. The first input image is included; each additional input image costs $0.003.
| Resolution | Base Price |
|---|---|
| 1k | $0.045 |
| 1.5k | $0.045 |
| 2k | $0.090 |
| Resolution | Input Images | Cost |
|---|---|---|
| 1k | 1 | $0.045 |
| 1k | 2 | $0.048 |
| 1k | 10 | $0.072 |
| 1.5k | 1 | $0.045 |
| 1.5k | 2 | $0.048 |
| 1.5k | 10 | $0.072 |
| 2k | 1 | $0.090 |
| 2k | 2 | $0.093 |
| 2k | 10 | $0.117 |
Use prompt_optimization_mode: fast while iterating on an edit, and standard for the final render — the fast rewrite is several times quicker but follows long instructions less closely.
Use clear prompts that describe both what should change and what should remain unchanged.
Use multiple reference images when identity, product details, or style consistency matters.
Leave aspect_ratio empty when you want the output to follow the closest supported ratio from the first input image.
Choose 1k or 1.5k for lower-cost editing and fast iteration.
Choose 2k when you need higher-resolution final output.
Use jpeg for general-purpose edited images and png when PNG output is needed.
Keep reference images clear, relevant, and visually consistent with the desired edit.
Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/bytedance/seedream-v5.0-pro/edit with your input as JSON. The endpoint returns a prediction id. Start polling the result endpoint around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. On completed, read output values from data.outputs. Examples for Seedream v5.0 Pro Edit below.
set -euo pipefail
: "${WAVESPEED_API_KEY:?Set WAVESPEED_API_KEY}"
REQUEST_BODY=$(cat <<'JSON'
{
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"images": [
"https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg"
],
"aspect_ratio": "1:1",
"resolution": "1k",
"output_format": "jpeg",
"prompt_optimization_mode": "standard"
}
JSON
)
# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
-X POST "https://api.wavespeed.ai/api/v3/bytedance/seedream-v5.0-pro/edit" \
-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-v5.0-pro/edit";
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 ${apiKey}`,
"Content-Type": "application/json",
},
body: JSON.stringify({
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"images": [
"https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg"
],
"aspect_ratio": "1:1",
"resolution": "1k",
"output_format": "jpeg",
"prompt_optimization_mode": "standard"
}),
});
const task = body.data ?? body;
if (!task.id) throw new Error("Submission response did not contain a prediction id");
const resultUrl = `https://api.wavespeed.ai/api/v3/predictions/${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"
],
"aspect_ratio": "1:1",
"resolution": "1k",
"output_format": "jpeg",
"prompt_optimization_mode": "standard"
}
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-v5.0-pro/edit", 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 v5.0 Pro Edit is a ByteDance model for image editing, exposed as a REST API on WaveSpeedAI. Seedream V5.0 Pro Edit by ByteDance edits and generates images from single-image or multi-reference inputs, supporting up to 10 reference images, aspect ratio selection, and 1K / 2K output tiers. Ready-to-use REST inference API, best performance, no coldstarts, 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-v5.0-pro-edit.
Seedream v5.0 Pro Edit starts at $0.0405 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`, `aspect_ratio`, `resolution`, `enable_base64_output`, `enable_sync_mode`. 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-v5.0-pro-edit.
Reported generation time on WaveSpeedAI is around 32 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.