Pixal3d

Unganisha

Kitambulisho cha modeli pixal3d

# Run the model; wait up to 20 s for the finished result in the same call
curl -X POST "https://api.doitong.com/v1/run/pixal3d?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "image": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg"
  }'

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

const API = "https://api.doitong.com/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/pixal3d?wait=20", {
  method: "POST",
  headers,
  body: JSON.stringify({
    "image": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg"
  }),
});
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.com/v1"
headers = {"Authorization": "Bearer " + os.environ["DOITONG_API_KEY"]}

payload = {
    "image": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg",
}

# Run the model; wait up to 20 s for the finished result in the same call
r = requests.post(API + "/run/pixal3d", 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.com/v1/mcp \
  --header "Authorization: Bearer $DOITONG_API_KEY"

# 2. Your agent calls the "run" tool with:
{
  "model_id": "pixal3d",
  "input": {
    "image": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg"
  }
}

Piga modeli ya Pixal3d (pixal3d) kupitia Doitong API. Nyaraka za mawakala: https://doitong.com/sw/developers/models/pixal3d.md

POST https://api.doitong.com/v1/run/pixal3d?wait=20
Authorization: Bearer $DOITONG_API_KEY
Content-Type: application/json

{
  "image": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg"
}

Ikiwa hali ya jibu ni "queued" au "running", piga GET https://api.doitong.com/v1/requests/REQUEST_ID?wait=20 mara kwa mara hadi iwe "succeeded"; faili ziko kwenye outputs[].url. POST https://api.doitong.com/v1/quote/pixal3d yenye mwili uleule hurejesha bei kamili kabla ya kuendesha.

Ombi hili: $ 0.30 salio za API 300 Iendeshe kwenye ukurasa huu

Pata ufunguo wa API

Open model Picha hadi 3D #stylized#transform

Hubadilisha picha moja kuwa modeli ya 3D ya GLB yenye tekstura na udhibiti wa kina wa kila hatua ya uzalishaji

OpenAPI Markdown

Open model · 3D

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

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

image •inahitajika image_url

Dondosha faili, au

URL inayoelekeza kwenye picha chanzo kwa ubadilishaji wa 3D.

resolution chaguomsingi 1024

Mwonekano wa tokeo; kuuongeza huongeza maelezo lakini huchukua muda zaidi.

Ya kina texture_size · ss_guidance_strength · ss_guidance_rescale · ss_sampling_steps · ss_rescale_t · shape_slat_guidance_strength · shape_slat_guidance_rescale · shape_slat_sampling_steps · shape_slat_rescale_t · tex_slat_guidance_strength · tex_slat_guidance_rescale · tex_slat_sampling_steps · tex_slat_rescale_t · mesh_scale · max_num_tokens · decimation_target · seed · remesh · enable_safety_checker

texture_size chaguomsingi 2048

Mwonekano wa texture ya mesh kwa baking. Maelezo bora ya uso huja na faili kubwa zaidi mwonekano huu unapoongezwa.

ss_guidance_strength chaguomsingi 7.5

Udhibiti wa uaminifu wa muundo wa awali wa 3D: kuuongeza hupendelea ulinganifu wa karibu na picha ya ingizo, kwa hatari ya noise zaidi.

ss_guidance_rescale chaguomsingi 0.7

Udhibiti wa vizalia vya mwongozo wa hatua ya 1, ukibadilisha athari thabiti za mwongozo katika mipangilio ya chini kwa tokeo thabiti zaidi katika mipangilio ya juu.

ss_sampling_steps chaguomsingi 12

Idadi ya hatua za kuondoa noise ya muundo wa awali: maboresho yanayowezekana ya ubora kutokana na hatua za ziada huambatana na uchakataji wa polepole.

ss_rescale_t chaguomsingi 5

Weka ukali wa mabadiliko kupitia ratiba ya noise ya uzalishaji wa muundo: kuongeza thamani hii hufanya mabadiliko kuwa makali zaidi.

shape_slat_guidance_strength chaguomsingi 7.5

Udhibiti wa uaminifu wa jiometri ya kina: kuongeza ufuasi wa picha ya ingizo huleta maelezo zaidi, kwa hatari ya noise iliyoongezwa.

shape_slat_guidance_rescale chaguomsingi 0.5

Ongeza mpangilio huu jiometri inapoonekana kuwa na noise: hupunguza vizalia vinavyosababishwa na mwongozo thabiti wakati wa hatua ya umbo.

shape_slat_sampling_steps chaguomsingi 12

Idadi ya hatua za kuondoa noise za uboreshaji wa umbo: jiometri laini zaidi inayowezekana hugharimu kasi wakati wa kutumia hatua za ziada.

shape_slat_rescale_t chaguomsingi 3

Weka ukali wa maelezo ya jiometri kupitia ratiba ya noise ya uboreshaji wa umbo; kuongeza thamani hii hutoa maelezo makali zaidi.

tex_slat_guidance_strength chaguomsingi 1

Udhibiti wa uaminifu wa rangi ya texture: ufuasi wa karibu zaidi wa rangi katika picha ya ingizo kwenye mipangilio ya juu huongeza uangavu lakini unaweza kusababisha rangi kuzidi.

tex_slat_guidance_rescale chaguomsingi 0

Ongeza mpangilio huu kushughulikia textures zenye noise au color banding: hupunguza vizalia vinavyosababishwa na mwongozo thabiti wakati wa hatua ya texture.

tex_slat_sampling_steps chaguomsingi 12

Idadi ya hatua za kuondoa noise zinazotumika kuzalisha textures. Kuongeza idadi ya hatua huchukua muda zaidi lakini kunaweza kutoa textures safi zaidi.

tex_slat_rescale_t chaguomsingi 3

Weka ukali wa maelezo ya texture kupitia ratiba ya noise ya uzalishaji wa texture; kuongeza thamani hii hutoa maelezo makali zaidi.

mesh_scale chaguomsingi 1

Pima mesh iliyokadiriwa ili kuathiri makadirio ya umbali wa kamera yanayotumiwa na modeli.

max_num_tokens chaguomsingi 49152

Kikomo cha tokeni za HR kwa sampler ya umbo ya cascaded, kikisawazisha jiometri laini zaidi katika mipangilio ya juu dhidi ya kuokoa kumbukumbu na muda wa uchakataji katika mipangilio ya chini.

decimation_target chaguomsingi 200000

Lengo la utata wa mesh, linaloonyeshwa kama idadi ya vertices za tokeo la mwisho. Kupunguza ukubwa wa faili kwa kushusha lengo hili pia hupunguza maelezo.

seed

Seed inayotumika kwa uzalishaji wa nasibu unaoweza kurudiwa.

POST /run/pixal3d?wait=20 makadirio → $ 0.30

# Run the model; wait up to 20 s for the finished result in the same call
curl -X POST "https://api.doitong.com/v1/run/pixal3d?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "image": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg"
  }'

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

const API = "https://api.doitong.com/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/pixal3d?wait=20", {
  method: "POST",
  headers,
  body: JSON.stringify({
    "image": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg"
  }),
});
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.com/v1"
headers = {"Authorization": "Bearer " + os.environ["DOITONG_API_KEY"]}

payload = {
    "image": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg",
}

# Run the model; wait up to 20 s for the finished result in the same call
r = requests.post(API + "/run/pixal3d", 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": "pixal3d",
      "input": {
        "image": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg"
      },
      "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 Pixal3d

Huchukua picha moja na kurejesha modeli ya GLB pamoja na mbegu iliyotumika. Hatua za muundo, umbo na tekstura zina mipangilio yake ya mwongozo, rescale, idadi ya hatua na ratiba ya kelele. `resolution` ni 1024 au 1536, `texture_size` ni 1024, 2048 au 4096, na `decimation_target` huweka idadi ya vertex kutoka 5000 hadi 1586021. `remesh` huunda upya topolojia.

Vigezo

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

JinaAina ChaguomsingiInaruhusiwa Maelezo

image_urlinahitajika image

Ainaurl · image

URL inayoelekeza kwenye picha chanzo kwa ubadilishaji wa 3D.

seedsi lazima

Ainainteger | null

Seed inayotumika kwa uzalishaji wa nasibu unaoweza kurudiwa.

resolutionsi lazima

Ainaenum

Chaguomsingi1024

10241536

Mwonekano wa tokeo; kuuongeza huongeza maelezo lakini huchukua muda zaidi.

ss_guidance_strengthsi lazima

Ainanumber

Chaguomsingi7.5

0 – 10

Udhibiti wa uaminifu wa muundo wa awali wa 3D: kuuongeza hupendelea ulinganifu wa karibu na picha ya ingizo, kwa hatari ya noise zaidi.

ss_guidance_rescalesi lazima

Ainanumber

Chaguomsingi0.7

0 – 1

Udhibiti wa vizalia vya mwongozo wa hatua ya 1, ukibadilisha athari thabiti za mwongozo katika mipangilio ya chini kwa tokeo thabiti zaidi katika mipangilio ya juu.

ss_sampling_stepssi lazima

Ainainteger

Chaguomsingi12

1 – 50

Idadi ya hatua za kuondoa noise ya muundo wa awali: maboresho yanayowezekana ya ubora kutokana na hatua za ziada huambatana na uchakataji wa polepole.

ss_rescale_tsi lazima

Ainanumber

Chaguomsingi5

1 – 6

Weka ukali wa mabadiliko kupitia ratiba ya noise ya uzalishaji wa muundo: kuongeza thamani hii hufanya mabadiliko kuwa makali zaidi.

shape_slat_guidance_strengthsi lazima

Ainanumber

Chaguomsingi7.5

0 – 10

Udhibiti wa uaminifu wa jiometri ya kina: kuongeza ufuasi wa picha ya ingizo huleta maelezo zaidi, kwa hatari ya noise iliyoongezwa.

shape_slat_guidance_rescalesi lazima

Ainanumber

Chaguomsingi0.5

0 – 1

Ongeza mpangilio huu jiometri inapoonekana kuwa na noise: hupunguza vizalia vinavyosababishwa na mwongozo thabiti wakati wa hatua ya umbo.

shape_slat_sampling_stepssi lazima

Ainainteger

Chaguomsingi12

1 – 50

Idadi ya hatua za kuondoa noise za uboreshaji wa umbo: jiometri laini zaidi inayowezekana hugharimu kasi wakati wa kutumia hatua za ziada.

shape_slat_rescale_tsi lazima

Ainanumber

Chaguomsingi3

1 – 6

Weka ukali wa maelezo ya jiometri kupitia ratiba ya noise ya uboreshaji wa umbo; kuongeza thamani hii hutoa maelezo makali zaidi.

tex_slat_guidance_strengthsi lazima

Ainanumber

Chaguomsingi1

0 – 10

Udhibiti wa uaminifu wa rangi ya texture: ufuasi wa karibu zaidi wa rangi katika picha ya ingizo kwenye mipangilio ya juu huongeza uangavu lakini unaweza kusababisha rangi kuzidi.

tex_slat_guidance_rescalesi lazima

Ainanumber

Chaguomsingi0

0 – 1

Ongeza mpangilio huu kushughulikia textures zenye noise au color banding: hupunguza vizalia vinavyosababishwa na mwongozo thabiti wakati wa hatua ya texture.

tex_slat_sampling_stepssi lazima

Ainainteger

Chaguomsingi12

1 – 50

Idadi ya hatua za kuondoa noise zinazotumika kuzalisha textures. Kuongeza idadi ya hatua huchukua muda zaidi lakini kunaweza kutoa textures safi zaidi.

tex_slat_rescale_tsi lazima

Ainanumber

Chaguomsingi3

1 – 6

Weka ukali wa maelezo ya texture kupitia ratiba ya noise ya uzalishaji wa texture; kuongeza thamani hii hutoa maelezo makali zaidi.

mesh_scalesi lazima

Ainanumber

Chaguomsingi1

0.1 – 4

Pima mesh iliyokadiriwa ili kuathiri makadirio ya umbali wa kamera yanayotumiwa na modeli.

max_num_tokenssi lazima

Ainainteger

Chaguomsingi49152

4,096 – 131,072

Kikomo cha tokeni za HR kwa sampler ya umbo ya cascaded, kikisawazisha jiometri laini zaidi katika mipangilio ya juu dhidi ya kuokoa kumbukumbu na muda wa uchakataji katika mipangilio ya chini.

decimation_targetsi lazima

Ainainteger

Chaguomsingi200000

5,000 – 1,586,021

Lengo la utata wa mesh, linaloonyeshwa kama idadi ya vertices za tokeo la mwisho. Kupunguza ukubwa wa faili kwa kushusha lengo hili pia hupunguza maelezo.

texture_sizesi lazima

Ainaenum

Chaguomsingi2048

102420484096

Mwonekano wa texture ya mesh kwa baking. Maelezo bora ya uso huja na faili kubwa zaidi mwonekano huu unapoongezwa.

remeshsi lazima

Ainaboolean

Chaguomsingitrue

Uundaji upya wa topolojia ya mesh ambao kwa kawaida hufaidi matumizi ya baadaye kwa kuunda pembetatu safi zaidi, kwa gharama ya uchakataji mrefu zaidi.

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": "pixal3d",
  "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": 300,
    "usd": "0.30",
    "charged": 300,
    "refunded": 0
  },
  "input": {
    "image_url": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg"
  },
  "output": {
    "model_glb": {
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.jpeg",
      "content_type": "image/jpeg",
      "file_name": "0-output.jpeg",
      "file_size": 1843200
    },
    "seed": 42
  },
  "outputs": [
    {
      "type": "file",
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.jpeg",
      "content_type": "image/jpeg",
      "file_size": 1843200,
      "stored": true
    }
  ],
  "error": null,
  "metrics": {
    "inference_seconds": 6.8
  },
  "urls": {
    "self": "https://api.doitong.com/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t",
    "cancel": "https://api.doitong.com/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

model_glb: object {url, content_type, file_name, file_size}Modeli ya 3D inayozalishwa katika muundo wa GLB.
seed: integerThamani ya seed iliyotumika kweli.

Kwa mawakala wa AI: ukurasa huu katika Markdown unapatikana kwenye https://doitong.com/sw/developers/models/pixal3d.md. Modeli na miongozo yote: https://doitong.com/developers/llms.txt

Tokeo lako la kwanza linaonekana hapa

Unda ombi

Endesha ombi hili

Kuhusu Pixal3d

Vigezo

Tokeo

Miundo zaidi: Picha hadi 3D

ReconViaGen 0.5

Hi3D Image to 3D Tofauti: 6

Hi3D Image to 3D · v3.0 Tofauti: 2

Hi3D Multiview to 3D · Multi View to 3D Tofauti: 6