black-forest-labs/flux-3/start-end-to-video-draft
black-forest-labs/flux-3/start-end-to-video-draft
black-forest-labs/flux-3/start-end-to-video-draft. 瀏覽圖像、影片與換臉模型 API。先試用任一模型,再透過統一 REST API 整合。
相關模型
完整參數參考、輸出結構與即時價格
| AI 模型 API 市集 | 一個平台,全部完成 | 最受歡迎 | 服務條款 | 瀏覽圖像、影片與換臉模型 API。先試用任一模型,再透過統一 REST API 整合。 |
|---|---|---|---|---|
| prompt *Prompt | textarea | — | ≤ 5000 chars | |
| start_image *Start Image | image_upload | — | image/* · 1–1 items | |
| end_image *End Image | image_upload | — | image/* · 1–1 items | |
| aspect_ratioAspect Ratio | select | — | 21:9 | 2:1 | 16:9 | 4:3 | 1:1 | 3:4 | 9:16 | |
| durationDuration | slider | 5 | 5 ~ 20 · step 1 | |
| generate_audioGenerate Audio | boolean | true | — |
完整參數參考、輸出結構與即時價格
| 深入了解 | 一個平台,全部完成 | 瀏覽圖像、影片與換臉模型 API。先試用任一模型,再透過統一 REST API 整合。 |
|---|---|---|
| videos | array<string> |
API
瀏覽圖像、影片與換臉模型 API。先試用任一模型,再透過統一 REST API 整合。
cURL
# 1) Submit — returns { "task_uuid": "..." }
curl -X POST "https://www.namifusion.com/api/v1/marketplace/run/black-forest-labs/flux-3/start-end-to-video-draft" \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"input": {
"prompt": "A cinematic transition from a quiet sunrise over a misty mountain lake to a vibrant golden-hour city rooftop garden, with the camera gliding smoothly forward as nature gradually transforms into an urban oasis. Soft drifting fog becomes warm floating dust motes, colors shift from cool blue dawn to rich amber sunset, and subtle environmental motion adds realism.",
"start_image": [
"https://d1s3annbwribom.cloudfront.net/marketplace/examples/2026/10/08/05b3f6a21dc6.jpeg"
],
"end_image": [
"https://d1s3annbwribom.cloudfront.net/marketplace/examples/2026/10/08/878a6f06af39.jpeg"
],
"aspect_ratio": "16:9",
"duration": 5,
"generate_audio": true
}
}'
# 2) Poll until status is "completed", then read the output URLs
curl "https://www.namifusion.com/api/v1/marketplace/run/tasks/TASK_UUID" \
-H "Authorization: Bearer YOUR_API_KEY"Python
import time, requests
API_KEY = "YOUR_API_KEY"
HEADERS = {"Authorization": f"Bearer {API_KEY}"}
# 1) Submit
resp = requests.post(
"https://www.namifusion.com/api/v1/marketplace/run/black-forest-labs/flux-3/start-end-to-video-draft",
headers=HEADERS,
json={
"input": {
"prompt": "A cinematic transition from a quiet sunrise over a misty mountain lake to a vibrant golden-hour city rooftop garden, with the camera gliding smoothly forward as nature gradually transforms into an urban oasis. Soft drifting fog becomes warm floating dust motes, colors shift from cool blue dawn to rich amber sunset, and subtle environmental motion adds realism.",
"start_image": [
"https://d1s3annbwribom.cloudfront.net/marketplace/examples/2026/10/08/05b3f6a21dc6.jpeg"
],
"end_image": [
"https://d1s3annbwribom.cloudfront.net/marketplace/examples/2026/10/08/878a6f06af39.jpeg"
],
"aspect_ratio": "16:9",
"duration": 5,
"generate_audio": True
}
},
)
resp.raise_for_status() # 401/402/429/5xx stop here instead of polling a bad task
task = resp.json()
# 2) Poll until a terminal state (completed / failed / cancelled).
# This model is allowed up to 1800s server-side.
deadline = time.time() + 1860
while task.get("status") not in ("completed", "failed", "cancelled"):
if time.time() > deadline:
raise TimeoutError(f"still {task.get('status')} — keep the task_uuid and poll later")
time.sleep(3)
poll = requests.get(f"https://www.namifusion.com/api/v1/marketplace/run/tasks/{task['task_uuid']}", headers=HEADERS)
poll.raise_for_status()
task = poll.json()
print(task["status"], task.get("output"))JavaScript
const API_KEY = "YOUR_API_KEY";
const HEADERS = { Authorization: `Bearer ${API_KEY}` };
// 1) Submit
const resp = await fetch("https://www.namifusion.com/api/v1/marketplace/run/black-forest-labs/flux-3/start-end-to-video-draft", {
method: "POST",
headers: { ...HEADERS, "Content-Type": "application/json" },
body: JSON.stringify({
"input": {
"prompt": "A cinematic transition from a quiet sunrise over a misty mountain lake to a vibrant golden-hour city rooftop garden, with the camera gliding smoothly forward as nature gradually transforms into an urban oasis. Soft drifting fog becomes warm floating dust motes, colors shift from cool blue dawn to rich amber sunset, and subtle environmental motion adds realism.",
"start_image": [
"https://d1s3annbwribom.cloudfront.net/marketplace/examples/2026/10/08/05b3f6a21dc6.jpeg"
],
"end_image": [
"https://d1s3annbwribom.cloudfront.net/marketplace/examples/2026/10/08/878a6f06af39.jpeg"
],
"aspect_ratio": "16:9",
"duration": 5,
"generate_audio": true
}
}),
});
if (!resp.ok) throw new Error(`submit failed: ${resp.status} ${await resp.text()}`);
let task = await resp.json();
// 2) Poll until a terminal state (completed / failed / cancelled).
// This model is allowed up to 1800s server-side.
const deadline = Date.now() + 1860 * 1000;
while (!["completed", "failed", "cancelled"].includes(task.status)) {
if (Date.now() > deadline) throw new Error(`still ${task.status} — keep the task_uuid and poll later`);
await new Promise((r) => setTimeout(r, 3000));
const poll = await fetch(`https://www.namifusion.com/api/v1/marketplace/run/tasks/${task.task_uuid}`, { headers: HEADERS });
if (!poll.ok) throw new Error(`poll failed: ${poll.status}`);
task = await poll.json();
}
console.log(task.status, task.output);API 文件
black-forest-labs/flux-3/start-end-to-video-draft
black-forest-labs/flux-3/start-end-to-video-draft
FLUX 3 Start-End-to-Video Draft quickly generates a transition between required start and end images, with prompt-guided motion, optional synchronized audio, and flexible 5-20 second duration for rapid keyframe iteration.
Parameters
| Parameter | Type | Required | Default | Limits / description |
|---|---|---|---|---|
prompt | string | Yes | — | max 5000 chars; The text prompt describing the video you want to generate. |
start_image | array | Yes | — | 1–1 URLs; Required first frame image. |
end_image | array | Yes | — | 1–1 URLs; Required last frame image. |
aspect_ratio | string | No | — | 21:9, 2:1, 16:9, 4:3, 1:1, 3:4, 9:16; The aspect ratio of the generated media. |
duration | integer | No | 5 | 5–20; step 1; Video length in seconds (5-20). |
generate_audio | boolean | No | true | Whether to generate audio for the video. |
Image inputs use URL arrays in Nami, including single-image fields. Multi-image edit accepts 1–3 URLs.
Pricing
| Mode | USD / second | Credits / second | USD / 5 seconds |
|---|---|---|---|
| Draft | $0.06 | 6 | $0.3 |
Price = rate × min(ceil(duration), 20). duration is an integer from 5 to 20; default 5. generate_audio does not change the price.
WaveSpeed standard list price; USD 1 = 100 credits. Account discounts are separate.
API
curl -X POST https://www.namifusion.com/api/v1/marketplace/run/black-forest-labs/flux-3/start-end-to-video-draft \
-H "Authorization: Bearer $API_KEY" \
-H 'Content-Type: application/json' \
-d '{
"input": {
"prompt": "A cinematic transition from a quiet sunrise over a misty mountain lake to a vibrant golden-hour city rooftop garden, with the camera gliding smoothly forward as nature gradually transforms into an urban oasis. Soft drifting fog becomes warm floating dust motes, colors shift from cool blue dawn to rich amber sunset, and subtle environmental motion adds realism.",
"start_image": [
"https://d1s3annbwribom.cloudfront.net/marketplace/examples/2026/10/08/05b3f6a21dc6.jpeg"
],
"end_image": [
"https://d1s3annbwribom.cloudfront.net/marketplace/examples/2026/10/08/878a6f06af39.jpeg"
],
"aspect_ratio": "16:9",
"duration": 5,
"generate_audio": true
}
}'
curl 'https://www.namifusion.com/api/v1/marketplace/run/tasks/TASK_UUID' \
-H "Authorization: Bearer $API_KEY"
Submit returns task_uuid. Poll until completed or failed. Successful output: output.videos (URL array). This API is asynchronous and returns URLs.
相關模型
xAI Grok Imagine Video v1.5 Image to Video
x-ai/grok-imagine-video-v1.5/image-to-video. 瀏覽圖像、影片與換臉模型 API。先試用任一模型,再透過統一 REST API 整合。
Vidu Q4 Preview Image to Video
vidu/q4-preview/image-to-video. 瀏覽圖像、影片與換臉模型 API。先試用任一模型,再透過統一 REST API 整合。
vidu/q3/image-to-video-spicy
vidu/q3/image-to-video-spicy. 瀏覽圖像、影片與換臉模型 API。先試用任一模型,再透過統一 REST API 整合。
Vidu Q3 Image To Video
vidu/q3/image-to-video. 瀏覽圖像、影片與換臉模型 API。先試用任一模型,再透過統一 REST API 整合。

MiniMax H3 Spicy Image to Video
minimax/h3/image-to-video-spicy. 瀏覽圖像、影片與換臉模型 API。先試用任一模型,再透過統一 REST API 整合。
MiniMax H3 Image to Video
minimax/h3/image-to-video. 瀏覽圖像、影片與換臉模型 API。先試用任一模型,再透過統一 REST API 整合。
ltx-2.5/image-to-video
ltx-2.5/image-to-video. 瀏覽圖像、影片與換臉模型 API。先試用任一模型,再透過統一 REST API 整合。
ai/ltx-2.3-spicy/image-to-video-lora
lightricks/ltx-2.3-spicy/image-to-video-lora. 瀏覽圖像、影片與換臉模型 API。先試用任一模型,再透過統一 REST API 整合。