FLUX 3 Max Text to Video
ਇੰਟੀਗ੍ਰੇਟ ਕਰੋ
blackforestlabs/flux-3-max/text-to-video
# Run the model; wait up to 20 s for the finished result in the same call
curl -X POST "https://vit.doitong.com/api/v1/run/blackforestlabs/flux-3-max/text-to-video?wait=20" \
-H "Authorization: Bearer $DOITONG_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"prompt": "Four-way CCTV-style split-screen showing the same real-time event inside a convenience shop. Divide the frame into four equal security-camera views with timestamps. Top left: wide ceiling-corner view covering aisles, entrance, and cashier. Top right: overhead view above the central aisle. Bottom left: camera facing the checkout counter. Bottom right: camera near the entrance looking inward. At the 2-second mark, a customer takes a boxed item from a shelf, accidentally bumps a display, catches one falling bottle, then places the box on the checkout counter. The cashier turns, scans it, and hands over a receipt as another shopper crosses behind them. All four views must remain perfectly synchronized, showing identical people, movements, object positions, occlusions, timestamps, lighting, and physical reactions. Use realistic low-resolution CCTV footage, slight lens distortion, fixed cameras, and no cinematic camera movement.",
"duration": 5,
"resolution": "720p",
"aspect_ratio": "16:9",
"generate_audio": false
}'
# Still "queued" or "running"? Poll with the id from the response:
curl "https://vit.doitong.com/api/v1/requests/REQUEST_ID?wait=20" \
-H "Authorization: Bearer $DOITONG_API_KEY"
const API = "https://vit.doitong.com/api/v1";
const headers = {
"Authorization": "Bearer " + process.env.DOITONG_API_KEY,
"Content-Type": "application/json",
};
// Run the model; wait up to 20 s for the finished result in the same call
let res = await fetch(API + "/run/blackforestlabs/flux-3-max/text-to-video?wait=20", {
method: "POST",
headers,
body: JSON.stringify({
"prompt": "Four-way CCTV-style split-screen showing the same real-time event inside a convenience shop. Divide the frame into four equal security-camera views with timestamps. Top left: wide ceiling-corner view covering aisles, entrance, and cashier. Top right: overhead view above the central aisle. Bottom left: camera facing the checkout counter. Bottom right: camera near the entrance looking inward. At the 2-second mark, a customer takes a boxed item from a shelf, accidentally bumps a display, catches one falling bottle, then places the box on the checkout counter. The cashier turns, scans it, and hands over a receipt as another shopper crosses behind them. All four views must remain perfectly synchronized, showing identical people, movements, object positions, occlusions, timestamps, lighting, and physical reactions. Use realistic low-resolution CCTV footage, slight lens distortion, fixed cameras, and no cinematic camera movement.",
"duration": 5,
"resolution": "720p",
"aspect_ratio": "16:9",
"generate_audio": false
}),
});
let request = await res.json();
if (!res.ok) throw new Error(request.error.code + ": " + request.error.message);
// Not finished yet: long-poll until it is
while (request.status === "queued" || request.status === "running") {
res = await fetch(API + "/requests/" + request.id + "?wait=20", { headers });
request = await res.json();
}
if (request.status !== "succeeded") throw new Error(JSON.stringify(request.error));
console.log(request.outputs.map((o) => o.url), request.cost.credits + " API credits ($" + request.cost.usd + ")");
import os
import requests
API = "https://vit.doitong.com/api/v1"
headers = {"Authorization": "Bearer " + os.environ["DOITONG_API_KEY"]}
payload = {
"prompt": "Four-way CCTV-style split-screen showing the same real-time event inside a convenience shop. Divide the frame into four equal security-camera views with timestamps. Top left: wide ceiling-corner view covering aisles, entrance, and cashier. Top right: overhead view above the central aisle. Bottom left: camera facing the checkout counter. Bottom right: camera near the entrance looking inward. At the 2-second mark, a customer takes a boxed item from a shelf, accidentally bumps a display, catches one falling bottle, then places the box on the checkout counter. The cashier turns, scans it, and hands over a receipt as another shopper crosses behind them. All four views must remain perfectly synchronized, showing identical people, movements, object positions, occlusions, timestamps, lighting, and physical reactions. Use realistic low-resolution CCTV footage, slight lens distortion, fixed cameras, and no cinematic camera movement.",
"duration": 5,
"resolution": "720p",
"aspect_ratio": "16:9",
"generate_audio": False,
}
# Run the model; wait up to 20 s for the finished result in the same call
r = requests.post(API + "/run/blackforestlabs/flux-3-max/text-to-video", params={"wait": 20}, json=payload, headers=headers)
request = r.json()
if not r.ok:
raise RuntimeError(request["error"]["code"] + ": " + request["error"]["message"])
# Not finished yet: long-poll until it is
while request["status"] in ("queued", "running"):
request = requests.get(API + "/requests/" + request["id"], params={"wait": 20}, headers=headers).json()
if request["status"] != "succeeded":
raise RuntimeError(request["error"])
print([o["url"] for o in request["outputs"]], request["cost"]["credits"], "API credits", "$" + request["cost"]["usd"])
# 1. Connect once (Claude Code; Cursor, VS Code, Claude Desktop: https://doitong.com/pa/developers/docs/mcp)
claude mcp add --transport http doitong-models https://vit.doitong.com/api/v1/mcp \
--header "Authorization: Bearer $DOITONG_API_KEY"
# 2. Your agent calls the "run" tool with:
{
"model_id": "blackforestlabs/flux-3-max/text-to-video",
"input": {
"prompt": "Four-way CCTV-style split-screen showing the same real-time event inside a convenience shop. Divide the frame into four equal security-camera views with timestamps. Top left: wide ceiling-corner view covering aisles, entrance, and cashier. Top right: overhead view above the central aisle. Bottom left: camera facing the checkout counter. Bottom right: camera near the entrance looking inward. At the 2-second mark, a customer takes a boxed item from a shelf, accidentally bumps a display, catches one falling bottle, then places the box on the checkout counter. The cashier turns, scans it, and hands over a receipt as another shopper crosses behind them. All four views must remain perfectly synchronized, showing identical people, movements, object positions, occlusions, timestamps, lighting, and physical reactions. Use realistic low-resolution CCTV footage, slight lens distortion, fixed cameras, and no cinematic camera movement.",
"duration": 5,
"resolution": "720p",
"aspect_ratio": "16:9",
"generate_audio": false
}
}
Doitong API ਰਾਹੀਂ FLUX 3 Max Text to Video ਮਾਡਲ (blackforestlabs/flux-3-max/text-to-video) ਨੂੰ ਕਾਲ ਕਰੋ। ਏਜੰਟਾਂ ਲਈ ਦਸਤਾਵੇਜ਼: https://doitong.com/pa/developers/models/blackforestlabs/flux-3-max/text-to-video.md
POST https://vit.doitong.com/api/v1/run/blackforestlabs/flux-3-max/text-to-video?wait=20
Authorization: Bearer $DOITONG_API_KEY
Content-Type: application/json
{
"prompt": "Four-way CCTV-style split-screen showing the same real-time event inside a convenience shop. Divide the frame into four equal security-camera views with timestamps. Top left: wide ceiling-corner view covering aisles, entrance, and cashier. Top right: overhead view above the central aisle. Bottom left: camera facing the checkout counter. Bottom right: camera near the entrance looking inward. At the 2-second mark, a customer takes a boxed item from a shelf, accidentally bumps a display, catches one falling bottle, then places the box on the checkout counter. The cashier turns, scans it, and hands over a receipt as another shopper crosses behind them. All four views must remain perfectly synchronized, showing identical people, movements, object positions, occlusions, timestamps, lighting, and physical reactions. Use realistic low-resolution CCTV footage, slight lens distortion, fixed cameras, and no cinematic camera movement.",
"duration": 5,
"resolution": "720p",
"aspect_ratio": "16:9",
"generate_audio": false
}
ਜੇ ਜਵਾਬ ਦੀ ਸਥਿਤੀ "queued" ਜਾਂ "running" ਹੈ, ਤਾਂ GET https://vit.doitong.com/api/v1/requests/REQUEST_ID?wait=20 ਨੂੰ ਉਦੋਂ ਤੱਕ ਪੋਲ ਕਰੋ ਜਦੋਂ ਤੱਕ ਇਹ "succeeded" ਨਾ ਹੋ ਜਾਵੇ; ਫ਼ਾਈਲਾਂ outputs[].url ਵਿੱਚ ਹਨ। ਉਸੇ ਬਾਡੀ ਨਾਲ POST https://vit.doitong.com/api/v1/quote/blackforestlabs/flux-3-max/text-to-video ਚਲਾਉਣ ’ਤੇ ਰਨ ਤੋਂ ਪਹਿਲਾਂ ਸਹੀ ਕੀਮਤ ਮਿਲ ਜਾਂਦੀ ਹੈ।
ਉਦਾਹਰਨ ਵਰਗੀਆਂ ਫ਼ਾਈਲਾਂ: $0.425 425 API ਕ੍ਰੈਡਿਟ ਤੁਹਾਡੀਆਂ ਫ਼ਾਈਲਾਂ ਚਲਾਉਣ ਤੋਂ ਪਹਿਲਾਂ ਮਾਪੀਆਂ ਜਾਂਦੀਆਂ ਹਨ ਇਸ ਪੰਨੇ ’ਤੇ ਚਲਾਓ
ਤੁਹਾਡੀ ਨਵੀਂ API ਕੁੰਜੀ। ਇਹ ਸਿਰਫ਼ ਹੁਣ ਦਿਖਾਈ ਜਾਂਦੀ ਹੈ ਅਤੇ ਪਹਿਲਾਂ ਹੀ ਕੋਡ ਅਤੇ ਹੇਠਾਂ ਦਿੱਤੇ API ਕੁੰਜੀ ਖੇਤਰ ਵਿੱਚ ਮੌਜੂਦ ਹੈ। ਇਸਨੂੰ ਗੁਪਤ ਰੱਖੋ: ਇਸਨੂੰ ਕਦੇ ਵੀ ਬ੍ਰਾਊਜ਼ਰ ਵਿੱਚ ਚੱਲਣ ਵਾਲੇ ਕੋਡ ਵਿੱਚ ਨਾ ਰੱਖੋ।
ਉਦਾਹਰਨਾਂ
ਪ੍ਰੌਂਪਟFour-way CCTV-style split-screen showing the same real-time event inside a convenience shop. Divide the frame into four equal security-camera views with timestamps. Top left: wide ceiling-corner view covering aisles, entrance, and cashier. Top right: overhead view above the central aisle. Bottom left: camera facing the checkout counter. Bottom right: camera near the entrance looking inward. At the 2-second mark, a customer takes a boxed item from a shelf, accidentally bumps a display, catches one falling bottle, then places the box on the checkout counter. The cashier turns, scans it, and hands over a receipt as another shopper crosses behind them. All four views must remain perfectly synchronized, showing identical people, movements, object positions, occlusions, timestamps, lighting, and physical reactions. Use realistic low-resolution CCTV footage, slight lens distortion, fixed cameras, and no cinematic camera movement.
ਰਿਕਵੈਸਟ ਬਣਾਓ
ਕੰਟਰੋਲ ਮਾਡਲ ਸਕੀਮਾ ਤੋਂ ਤਿਆਰ ਹੁੰਦੇ ਹਨ। ਤੁਸੀਂ ਬਦਲਾਅ ਕਰਦੇ ਹੀ ਕੋਡ ਅਤੇ ਕੀਮਤ ਅੱਪਡੇਟ ਹੋ ਜਾਂਦੇ ਹਨ।
/run/blackforestlabs/flux-3-max/text-to-video?wait=20
ਕੋਟ → $0.425
# Run the model; wait up to 20 s for the finished result in the same call
curl -X POST "https://vit.doitong.com/api/v1/run/blackforestlabs/flux-3-max/text-to-video?wait=20" \
-H "Authorization: Bearer $DOITONG_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"prompt": "Four-way CCTV-style split-screen showing the same real-time event inside a convenience shop. Divide the frame into four equal security-camera views with timestamps. Top left: wide ceiling-corner view covering aisles, entrance, and cashier. Top right: overhead view above the central aisle. Bottom left: camera facing the checkout counter. Bottom right: camera near the entrance looking inward. At the 2-second mark, a customer takes a boxed item from a shelf, accidentally bumps a display, catches one falling bottle, then places the box on the checkout counter. The cashier turns, scans it, and hands over a receipt as another shopper crosses behind them. All four views must remain perfectly synchronized, showing identical people, movements, object positions, occlusions, timestamps, lighting, and physical reactions. Use realistic low-resolution CCTV footage, slight lens distortion, fixed cameras, and no cinematic camera movement.",
"duration": 5,
"resolution": "720p",
"aspect_ratio": "16:9",
"generate_audio": false
}'
# Still "queued" or "running"? Poll with the id from the response:
curl "https://vit.doitong.com/api/v1/requests/REQUEST_ID?wait=20" \
-H "Authorization: Bearer $DOITONG_API_KEY"
const API = "https://vit.doitong.com/api/v1";
const headers = {
"Authorization": "Bearer " + process.env.DOITONG_API_KEY,
"Content-Type": "application/json",
};
// Run the model; wait up to 20 s for the finished result in the same call
let res = await fetch(API + "/run/blackforestlabs/flux-3-max/text-to-video?wait=20", {
method: "POST",
headers,
body: JSON.stringify({
"prompt": "Four-way CCTV-style split-screen showing the same real-time event inside a convenience shop. Divide the frame into four equal security-camera views with timestamps. Top left: wide ceiling-corner view covering aisles, entrance, and cashier. Top right: overhead view above the central aisle. Bottom left: camera facing the checkout counter. Bottom right: camera near the entrance looking inward. At the 2-second mark, a customer takes a boxed item from a shelf, accidentally bumps a display, catches one falling bottle, then places the box on the checkout counter. The cashier turns, scans it, and hands over a receipt as another shopper crosses behind them. All four views must remain perfectly synchronized, showing identical people, movements, object positions, occlusions, timestamps, lighting, and physical reactions. Use realistic low-resolution CCTV footage, slight lens distortion, fixed cameras, and no cinematic camera movement.",
"duration": 5,
"resolution": "720p",
"aspect_ratio": "16:9",
"generate_audio": false
}),
});
let request = await res.json();
if (!res.ok) throw new Error(request.error.code + ": " + request.error.message);
// Not finished yet: long-poll until it is
while (request.status === "queued" || request.status === "running") {
res = await fetch(API + "/requests/" + request.id + "?wait=20", { headers });
request = await res.json();
}
if (request.status !== "succeeded") throw new Error(JSON.stringify(request.error));
console.log(request.outputs.map((o) => o.url), request.cost.credits + " API credits ($" + request.cost.usd + ")");
import os
import requests
API = "https://vit.doitong.com/api/v1"
headers = {"Authorization": "Bearer " + os.environ["DOITONG_API_KEY"]}
payload = {
"prompt": "Four-way CCTV-style split-screen showing the same real-time event inside a convenience shop. Divide the frame into four equal security-camera views with timestamps. Top left: wide ceiling-corner view covering aisles, entrance, and cashier. Top right: overhead view above the central aisle. Bottom left: camera facing the checkout counter. Bottom right: camera near the entrance looking inward. At the 2-second mark, a customer takes a boxed item from a shelf, accidentally bumps a display, catches one falling bottle, then places the box on the checkout counter. The cashier turns, scans it, and hands over a receipt as another shopper crosses behind them. All four views must remain perfectly synchronized, showing identical people, movements, object positions, occlusions, timestamps, lighting, and physical reactions. Use realistic low-resolution CCTV footage, slight lens distortion, fixed cameras, and no cinematic camera movement.",
"duration": 5,
"resolution": "720p",
"aspect_ratio": "16:9",
"generate_audio": False,
}
# Run the model; wait up to 20 s for the finished result in the same call
r = requests.post(API + "/run/blackforestlabs/flux-3-max/text-to-video", params={"wait": 20}, json=payload, headers=headers)
request = r.json()
if not r.ok:
raise RuntimeError(request["error"]["code"] + ": " + request["error"]["message"])
# Not finished yet: long-poll until it is
while request["status"] in ("queued", "running"):
request = requests.get(API + "/requests/" + request["id"], params={"wait": 20}, headers=headers).json()
if request["status"] != "succeeded":
raise RuntimeError(request["error"])
print([o["url"] for o in request["outputs"]], request["cost"]["credits"], "API credits", "$" + request["cost"]["usd"])
{
"jsonrpc": "2.0",
"id": 1,
"method": "tools/call",
"params": {
"name": "run",
"arguments": {
"model_id": "blackforestlabs/flux-3-max/text-to-video",
"input": {
"prompt": "Four-way CCTV-style split-screen showing the same real-time event inside a convenience shop. Divide the frame into four equal security-camera views with timestamps. Top left: wide ceiling-corner view covering aisles, entrance, and cashier. Top right: overhead view above the central aisle. Bottom left: camera facing the checkout counter. Bottom right: camera near the entrance looking inward. At the 2-second mark, a customer takes a boxed item from a shelf, accidentally bumps a display, catches one falling bottle, then places the box on the checkout counter. The cashier turns, scans it, and hands over a receipt as another shopper crosses behind them. All four views must remain perfectly synchronized, showing identical people, movements, object positions, occlusions, timestamps, lighting, and physical reactions. Use realistic low-resolution CCTV footage, slight lens distortion, fixed cameras, and no cinematic camera movement.",
"duration": 5,
"resolution": "720p",
"aspect_ratio": "16:9",
"generate_audio": false
},
"wait_seconds": 20
}
}
}
ਇਹ ਬੇਨਤੀ ਚਲਾਓ
ਤੁਹਾਡੀ key ਇਸ ਬ੍ਰਾਊਜ਼ਰ ਵਿੱਚ ਰਹਿੰਦੀ ਹੈ: ਇਹ ਸਿਰਫ਼ Doitong API ਨੂੰ ਭੇਜੀ ਜਾਂਦੀ ਹੈ ਅਤੇ ਸਿਰਫ਼ ਤਾਂ ਹੀ (localStorage) ਵਿੱਚ ਸੁਰੱਖਿਅਤ ਹੁੰਦੀ ਹੈ ਜੇ ਤੁਸੀਂ Remember ਚੁਣੋ। API ਕੁੰਜੀ ਪ੍ਰਾਪਤ ਕਰੋ
FLUX 3 Max Text to Video ਬਾਰੇ
FLUX 3 Max FLUX ਦੀ ਦਿੱਖ ਨੂੰ ਵੀਡੀਓ ਵਿੱਚ ਲਿਆਉਂਦਾ ਹੈ: ਵਿਸਤ੍ਰਿਤ, ਚੰਗੀ ਰੌਸ਼ਨੀ ਵਾਲੇ ਫ੍ਰੇਮ, ਕੁਦਰਤੀ ਗਤੀ ਅਤੇ ਸਿਰਜਿਆ ਗਿਆ ਆਡੀਓ। ਇਹ ਰੈਂਡਰ ਕਰਨ ਤੋਂ ਪਹਿਲਾਂ ਪ੍ਰੌਂਪਟ ਬਾਰੇ ਰੀਜ਼ਨਿੰਗ ਕਰਦਾ ਹੈ (ਉੱਚ ਜਾਂ ਘੱਟ ਯਤਨ), 5 ਤੋਂ 20 ਸਕਿੰਟ ਦੀਆਂ ਕਲਿੱਪਾਂ ਅਤੇ 9:16 ਤੋਂ 21:9 ਤੱਕ ਅੱਠ ਆਸਪੈਕਟ ਰੇਸ਼ੋ, 720p ਜਾਂ 1080p 'ਤੇ ਸਮਰਥਿਤ ਹਨ। ਸੀਡ ਰਨ ਨੂੰ ਦੁਹਰਾਉਣਯੋਗ ਬਣਾਉਂਦਾ ਹੈ।
ਪੈਰਾਮੀਟਰ
promptਲੋੜੀਂਦਾ
durationਵਿਕਲਪਿਕ
resolutionਵਿਕਲਪਿਕ
reasoning_levelਵਿਕਲਪਿਕ
aspect_ratioਵਿਕਲਪਿਕ
generate_audioਵਿਕਲਪਿਕ
seedਵਿਕਲਪਿਕ
ਆਉਟਪੁੱਟ
{
"id": "req_8k2m4q7x1z9c3v5b6n0p2r4t",
"object": "request",
"model": "blackforestlabs/flux-3-max/text-to-video",
"status": "succeeded",
"created_at": "2026-10-20T12:00:00Z",
"started_at": "2026-10-20T12:00:02Z",
"completed_at": "2026-10-20T12:00:09Z",
"queue_position": null,
"cost": {
"credits": 425,
"usd": "0.425",
"charged": 425,
"refunded": 0
},
"input": {
"prompt": "A red panda walks along a mossy log in a sunlit forest, pauses to sniff the air, then climbs over a branch",
"duration": 5,
"resolution": "720p"
},
"output": {
"video": {
"url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.mp4",
"content_type": "video/mp4",
"file_name": "0-output.mp4",
"file_size": 1843200,
"width": 1024,
"height": 768,
"fps": 1.0,
"duration": 5,
"num_frames": 1
},
"seed": 42,
"timings": {}
},
"outputs": [
{
"type": "video",
"url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.mp4",
"content_type": "video/mp4",
"file_size": 1843200,
"width": 1280,
"height": 720,
"duration": 5,
"stored": true
}
],
"error": null,
"metrics": {
"inference_seconds": 6.8
},
"urls": {
"self": "https://vit.doitong.com/api/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t",
"cancel": "https://vit.doitong.com/api/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t/cancel"
}
}
ਆਉਟਪੁੱਟ ਦੇ ਫ਼ੀਲਡ
- video
- object {url, content_type, file_name, file_size, width, height, fps, duration, num_frames}ਮਾਡਲ ਵੱਲੋਂ ਤਿਆਰ ਕੀਤੀ ਵੀਡੀਓ।
- seed
- integerਸਿਰਜਣਾ ਦੌਰਾਨ ਵਰਤੀ ਗਈ ਸੀਡ ਕੀਮਤ।
- timings
- object`inference` ਵਿੱਚੋਂ ਪ੍ਰੌਂਪਟ ਵਿਸਤਾਰ, ਡੀਕੋਡਿੰਗ ਅਤੇ ਅਪਲੋਡ ਹਟਾ ਕੇ ਸਮੇਂ ਦਾ ਡੇਟਾ; ਇਹ ਸਿਰਫ਼ ਮਾਡਲ ਦੀ ਵੀਡੀਓ ਡੀਨੋਇਜ਼ਿੰਗ ਨੂੰ ਸਕਿੰਟਾਂ ਵਿੱਚ ਮਾਪਦਾ ਹੈ।
ਹੋਰ FLUX 3 Max ਵੈਰੀਐਂਟ
ਹੋਰ ਮਾਡਲ: ਟੈਕਸਟ ਤੋਂ ਵੀਡੀਓ
AI ਏਜੰਟਾਂ ਲਈ: ਇਹ ਪੰਨਾ Markdown ਵਜੋਂ ਇੱਥੇ ਹੈ https://doitong.com/pa/developers/models/blackforestlabs/flux-3-max/text-to-video.md. ਸਾਰੇ ਮਾਡਲ ਅਤੇ ਗਾਈਡ: https://doitong.com/developers/llms.txt