Luma Ray 3.2 Video to Video

Unganisha

Kitambulisho cha modeli luma/agent/ray/v3.2/video-to-video

# Run the model; wait up to 20 s for the finished result in the same call
curl -X POST "https://api.doitong.ru/v1/run/luma/agent/ray/v3.2/video-to-video?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
    "video": "https://content.doitong.com/video/showcase/v3/gen_fox_cartoon.mp4"
  }'

# Still "queued" or "running"? Poll with the id from the response:
curl "https://api.doitong.ru/v1/requests/REQUEST_ID?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY"

const API = "https://api.doitong.ru/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/luma/agent/ray/v3.2/video-to-video?wait=20", {
  method: "POST",
  headers,
  body: JSON.stringify({
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
    "video": "https://content.doitong.com/video/showcase/v3/gen_fox_cartoon.mp4"
  }),
});
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://api.doitong.ru/v1"
headers = {"Authorization": "Bearer " + os.environ["DOITONG_API_KEY"]}

payload = {
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
    "video": "https://content.doitong.com/video/showcase/v3/gen_fox_cartoon.mp4",
}

# Run the model; wait up to 20 s for the finished result in the same call
r = requests.post(API + "/run/luma/agent/ray/v3.2/video-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/sw/developers/docs/mcp)
claude mcp add --transport http doitong-models https://api.doitong.ru/v1/mcp \
  --header "Authorization: Bearer $DOITONG_API_KEY"

# 2. Your agent calls the "run" tool with:
{
  "model_id": "luma/agent/ray/v3.2/video-to-video",
  "input": {
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
    "video": "https://content.doitong.com/video/showcase/v3/gen_fox_cartoon.mp4"
  }
}

Piga modeli ya Luma Ray 3.2 Video to Video (luma/agent/ray/v3.2/video-to-video) kupitia Doitong API. Nyaraka za mawakala: https://doitong.com/sw/developers/models/luma/agent/ray/v3.2/video-to-video.md

POST https://api.doitong.ru/v1/run/luma/agent/ray/v3.2/video-to-video?wait=20
Authorization: Bearer $DOITONG_API_KEY
Content-Type: application/json

{
  "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
  "video": "https://content.doitong.com/video/showcase/v3/gen_fox_cartoon.mp4"
}

Ikiwa hali ya jibu ni "queued" au "running", piga GET https://api.doitong.ru/v1/requests/REQUEST_ID?wait=20 mara kwa mara hadi iwe "succeeded"; faili ziko kwenye outputs[].url. POST https://api.doitong.ru/v1/quote/luma/agent/ray/v3.2/video-to-video yenye mwili uleule hurejesha bei kamili kabla ya kuendesha.

Ombi hili: $ 0.72 salio za API 720 · ≈ ₽ 77.27 Iendeshe kwenye ukurasa huu

Pata ufunguo wa API

Luma AI Video hadi Video Usawazishaji wa midomo5–10 shadi 1080p #stylized#transform#lipsync

Uhariri wa video wa Ray 3.2 unaobadilisha mtindo wa video chanzo kwa mipangilio ya nguvu ya uhariri, vidhibiti na fremu muhimu

OpenAPI Markdown

Luma AI · Video

Tokeo lako la kwanza linaonekana hapa

Unda ombi hapa chini na uliendeshe kwa ufunguo wako wa API. Matokeo yanakiliwa kwenye hifadhi yetu, yakihifadhiwa milele au 7 siku bila malipo.

Unda ombi

Bei

Bei halisi

kuanzia $ 0.144 / sekunde

salio za API 144 / sekunde · ≈ ₽ 15.45

5 s ≈ $ 0.72

Ombi hili: sekunde 5 × $ 0.144 $ 0.72 salio za API 720 · ≈ ₽ 77.27

Endesha · $ 0.72

Hutozwa tu ikifanikiwa, na kurejeshewa kiotomatiki ikishindwa.

resolution chaguomsingi 540p

duration 5 s

Sheria za bei

Wakati exr_export = true na hdr = true na resolution = 1080p: $ 1.296 / sekunde
Wakati exr_export = true na hdr = true: $ 0.648 / sekunde
Wakati hdr = true na resolution = 1080p: $ 0.864 / sekunde
Wakati hdr = true: $ 0.432 / sekunde
Wakati resolution = 1080p: $ 0.432 / sekunde
Wakati resolution = 720p: $ 0.216 / sekunde

Hutozwa kwa kila sekunde ya matokeo (duration).

Endpoint ya makadirio: POST /quote/{id}

Unda ombi

Vidhibiti vinazalishwa kutoka kwenye schema ya modeli. Msimbo na bei husasishwa unapovibadilisha.

prompt •inahitajika 88 / 6000

Maelekezo ya maandishi ya kuhariri video chanzi.

video •inahitajika video_url

Dondosha faili, au

URL ya video inayohaririwa.

duration 5 s

Urefu wa video baada ya kuhariri.

resolution chaguomsingi 540p

Mwonekano wa tokeo baada ya kuhariri.

Ya kina image · user · edit_strength · auto_controls · enable_safety_checker · keyframes · controls · keyframe_indexes

image start_image_url

Dondosha faili, au

Ubadilishaji wa fremu ya kwanza wa video iliyohaririwa, uliotolewa kama URL ya hiari ya picha; ukiachwa, modeli hupata fremu hiyo kutoka video chanzi. Kwa mfano, kutoa picha ya mwanzo iliyobadilishwa mtindo kutoka chanzo kunaweza kuongoza mwonekano wa uhariri.

user

Kitambulishi cha opaque cha hiari kinachomtambulisha mtumiaji wa mwisho anayetuma ombi.

edit_strength

Mpangilio wa kuhifadhi chanzo kwa uhariri, unaopatikana tu wakati auto_controls haijatumika; kuacha huchagua chaguo chaguomsingi la modeli. Kuanzia mabadiliko makubwa hadi ufuasi wa karibu, chaguo ni 'reimagine_*', 'flex_*' kwa tokeo lenye uwiano, na 'adhere_*'.

keyframes

Miongozo ya uhariri yenye keyframe nyingi iliyotolewa kama URL za picha badala ya start_image_url. Toa keyframes pamoja na safu ya urefu sawa ya keyframe_indexes ili kubandika kila picha kwenye nafasi ya fremu yake katika video chanzi; URL zisizozidi 64 zinaruhusiwa.

controls

Mbadala wa kina wa edit_strength unaoweka masharti kando kwa mkao, kina, normals, trajectory na uso. Kutumia vidhibiti hivi huzuia auto_controls.

keyframe_indexes

Uchoraji wa ramani wa fremu chanzi uliooanishwa moja kwa moja na keyframes: ingizo [i] hubainisha nafasi ya nanga ya keyframes[i]. Safu zote mbili lazima ziwe na urefu sawa, na nafasi ziwe tofauti na zisizo hasi.

POST /run/luma/agent/ray/v3.2/video-to-video?wait=20 makadirio → $ 0.72

# Run the model; wait up to 20 s for the finished result in the same call
curl -X POST "https://api.doitong.ru/v1/run/luma/agent/ray/v3.2/video-to-video?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
    "video": "https://content.doitong.com/video/showcase/v3/gen_fox_cartoon.mp4"
  }'

# Still "queued" or "running"? Poll with the id from the response:
curl "https://api.doitong.ru/v1/requests/REQUEST_ID?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY"

const API = "https://api.doitong.ru/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/luma/agent/ray/v3.2/video-to-video?wait=20", {
  method: "POST",
  headers,
  body: JSON.stringify({
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
    "video": "https://content.doitong.com/video/showcase/v3/gen_fox_cartoon.mp4"
  }),
});
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://api.doitong.ru/v1"
headers = {"Authorization": "Bearer " + os.environ["DOITONG_API_KEY"]}

payload = {
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
    "video": "https://content.doitong.com/video/showcase/v3/gen_fox_cartoon.mp4",
}

# Run the model; wait up to 20 s for the finished result in the same call
r = requests.post(API + "/run/luma/agent/ray/v3.2/video-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": "luma/agent/ray/v3.2/video-to-video",
      "input": {
        "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
        "video": "https://content.doitong.com/video/showcase/v3/gen_fox_cartoon.mp4"
      },
      "wait_seconds": 20
    }
  }
}

Endesha ombi hili

Ufunguo wa API

Key yako inabaki kwenye kivinjari hiki: inatumwa kwa Doitong API pekee na kuhifadhiwa (localStorage) tu ukiweka tiki kwenye Kumbuka. Kumbuka katika kivinjari hiki Pata ufunguo wa API

Kuhusu Luma Ray 3.2 Video to Video

Huhariri `video_url` kulingana na `prompt`, kwa hiari ikiwa na `start_image_url` ya kuongoza fremu ya kwanza. `edit_strength` hutoa viwango vya adhere, flex na reimagine kuanzia 1 hadi 3, huku `auto_controls` au kitu cha `controls` kikitoa masharti mbadala. Hadi `keyframes` 64 zinaweza kutiwa nanga kwa `keyframe_indexes`. Matokeo ni 540p hadi 1080p, 5s au 10s, yakiwa na `hdr` na `exr_export` kwa hiari.

Vigezo

Tuma jina rasmi au jina asilia, si yote mawili. Majina rasmi

JinaAina ChaguomsingiInaruhusiwa Maelezo

promptinahitajika

Ainastring

≤ herufi 6,000

Maelekezo ya maandishi ya kuhariri video chanzi.

video_urlinahitajika video

Ainaurl · video

URL ya video inayohaririwa.

usersi lazima

Ainastring | null

Kitambulishi cha opaque cha hiari kinachomtambulisha mtumiaji wa mwisho anayetuma ombi.

start_image_urlsi lazima image

Ainaurl · image

resolutionsi lazima

Ainaenum

Chaguomsingi540p

540p720p1080p

Mwonekano wa tokeo baada ya kuhariri.

durationsi lazima

Ainaenum

Chaguomsingi5s

5s10s

Urefu wa video baada ya kuhariri.

edit_strengthsi lazima

Ainaenum

adhere_1adhere_2adhere_3flex_1flex_2flex_3reimagine_1reimagine_2reimagine_3

auto_controlssi lazima

Ainaboolean

Chaguomsingifalse

Uwekaji wa masharti wa uhariri wa kiotomatiki: modeli hutumia video chanzi kubainisha ratiba badala ya kukubali edit_strength pamoja na chaguo hili.

hdrsi lazima

Ainaboolean

Chaguomsingifalse

Usimbaji wa HDR kwa tokeo la MP4 katika 720p au 1080p, unaopatikana tu kwa akaunti zenye ufikiaji wa HDR.

exr_exportsi lazima

Ainaboolean

Chaguomsingifalse

Utoaji wa ziada wa EXR unaoambatana na MP4, unaopatikana tu kwa ufikiaji wa HDR pamoja na hdr=true.

controlssi lazima

Ainaobject

Mbadala wa kina wa edit_strength unaoweka masharti kando kwa mkao, kina, normals, trajectory na uso. Kutumia vidhibiti hivi huzuia auto_controls.

controls.posesi lazima

Ainaobject

Uwekaji wa masharti unaotegemea mkao au mifupa.

controls.pose.enabledsi lazima

Ainaboolean

Chaguomsingitrue

Kigeuza cha uwekaji wa masharti ya mkao au mifupa wakati wa kuhariri.

controls.pose.strengthsi lazima

Ainaenum

precisecoarse

Uteuzi wa usahihi wa masharti ya mkao: acha chaguo chaguomsingi kwa kutokubainisha, chagua 'coarse' kwa uhuru zaidi, au tumia 'precise' kufuatilia mkao chanzi kwa ukaribu.

controls.depthsi lazima

Ainaobject

Uwekaji wa masharti unaotegemea kina au jiometri ya mandhari.

controls.depth.enabledsi lazima

Ainaboolean

Chaguomsingitrue

Kigeuza cha uwekaji wa masharti ya kina au jiometri ya mandhari wakati wa kuhariri.

controls.depth.blursi lazima

Ainanumber | null

0 – 1

Mpangilio wa ukungu wa kina, unaoachwa bila kubainishwa ili kuhifadhi chaguo chaguomsingi au kuongezwa ili kuipa jiometri uhuru zaidi.

controls.normalssi lazima

Ainaobject

Uwekaji wa masharti unaotegemea normals za uso.

controls.normals.enabledsi lazima

Ainaboolean

Chaguomsingitrue

Kigeuza cha uwekaji wa masharti ya normals za uso wakati wa kuhariri.

controls.normals.augmentationsi lazima

Ainanumber | null

0 – 1

Mpangilio wa uongezaji wa normals za uso; hifadhi chaguo chaguomsingi kwa kuacha, au uongeze ili kuruhusu tafsiri upya kubwa ya jiometri ya uso.

controls.trajectorysi lazima

Ainaobject

Uwekaji wa masharti unaotegemea njia za mwendo.

controls.trajectory.enabledsi lazima

Ainaboolean

Chaguomsingitrue

Kigeuza cha uwekaji wa masharti ya njia za mwendo wakati wa kuhariri.

controls.trajectory.sparsitysi lazima

Ainanumber | null

0 – 1

Mpangilio wa uchache wa njia za mwendo; uache ili kuhifadhi chaguo chaguomsingi, au uongeze ili kupunguza idadi ya nanga za mwendo zinazotumika.

controls.facesi lazima

Ainaobject

Uwekaji wa masharti unaotegemea utambulisho wa uso.

controls.face.enabledsi lazima

Ainaboolean

Chaguomsingitrue

Kigeuza cha uwekaji wa masharti ya utambulisho wa uso wakati wa kuhariri.

keyframessi lazima

Ainastring[]

≤ vipengee 64

keyframe_indexessi lazima

Ainainteger[]

≤ vipengee 64

enable_safety_checkersi lazima

Ainaboolean

Chaguomsingitrue

Ukaguzi unaweza kulegezwa kwa kuweka false, ikiwa mpigaji simu ameidhinishwa.

inahitajika Jina rasmi, pia linakubalika

Vigezo vya faili vinakubali URL ya umma ya https://, data: URI ya hadi 10 MB, au file_url ya upakiaji. Faili

Tokeo

GET /requests/req_8k2m4q7x1z9c3v5b6n0p2r4t

{
  "id": "req_8k2m4q7x1z9c3v5b6n0p2r4t",
  "object": "request",
  "model": "luma/agent/ray/v3.2/video-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": 720,
    "usd": "0.72",
    "charged": 720,
    "refunded": 0
  },
  "input": {
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
    "video_url": "https://content.doitong.com/video/showcase/v3/gen_fox_cartoon.mp4"
  },
  "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
    },
    "exr_file": {
      "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
    }
  },
  "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://api.doitong.ru/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t",
    "cancel": "https://api.doitong.ru/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t/cancel"
  }
}

Faili zako, chaguo lakoKila outputs[].url ni nakala kwenye hifadhi yetu: huhifadhiwa milele (hutozwa kwa GB kwa mwezi) au 7 siku bila malipo, kulingana na mpangilio wa akaunti yako au ?storage=.

Muundo uleule kwenye kila modelitype, url, content_type, width, height na duration, kwa picha, video na sauti. output ni kitu cha matokeo cha modeli yenyewe.

Sehemu za tokeo

video: object {url, content_type, file_name, file_size}Video iliyozalishwa na modeli.
exr_file: object {url, content_type, file_name, file_size} | nullEXR sidecar katika umbo linalotolewa na Luma: faili moja ya EXR au kumbukumbu ya ZIP. Huzalishwa wakati exr_export ni true.

Miundo zaidi: Video hadi Video

Kwa mawakala wa AI: ukurasa huu katika Markdown unapatikana kwenye https://doitong.com/sw/developers/models/luma/agent/ray/v3.2/video-to-video.md. Modeli na miongozo yote: https://doitong.com/developers/llms.txt

Tokeo lako la kwanza linaonekana hapa

Unda ombi

Endesha ombi hili

Kuhusu Luma Ray 3.2 Video to Video

Vigezo

Tokeo

Tofauti nyingine za Luma Ray 3.2

Luma Ray 3.2 Text to Video Tofauti: 4

Luma Ray 3.2 Image to Video Tofauti: 4

Luma Ray 3.2 Reframe Tofauti: 4

Miundo zaidi: Video hadi Video

AMT Interpolation Tofauti: 2

AnimateDiff Turbo · Video to Video Tofauti: 2

AnimateDiff · Video to Video Tofauti: 2

Auto-Captioner