Dža ko lil

Telestyle V2 Style Transfer

Integriruj

Modelosko id telestyle-v2
# 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/telestyle-v2?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "content_image_url": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg",
    "style_image_url": "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"

Kava mangipen: ≈$0.071 71 API krediti Phir les kate

Lel API klidin
Open model Editime e kipesko #stylized#transform#editing

Stiluno transfero savo render-kerel jek content kipo, le lookosa katar jek aver stiluno referenca kipo

Open model · Kip

Tiro prvo rezultato si kate

Ker tele jekh mangipen thaj phir les tire API klidinosa. E rezultatur si kopirime amare arakhipneste, vično vaj 7 dives bilačhes.

Ker jekh mangipen

O kontrolura kerde si katar e schemaske. O kodo thaj e cena menjinen sar tu len menjines.

•trubul
Čhiv jekh fajl, vaj

URL savo sikavel ko kipo savo del o subjekto thaj struktura vaš style transfer. Duj si arakhle kana o kipo lel o stil.

•trubul
Čhiv jekh fajl, vaj

URL e kiposko uživardo te restylil o kontentosko kipo. O referencako kipo del e materijalosko thaj artistikosko stilo, sar-o-kolori thaj svetlo.

image_size

Rezultatoske kiposke dimenzije, save override-in e kontentoske kiposke dimenzije numa kana si dinde.

num_images standardno 1

Manglo kipoqo gin vaš generiripe.

Lučhe negative_prompt · acceleration · output_format · lora_scale · lightning_lora_scale · num_inference_steps · guidance_scale · seed · use_lightning_lora · use_content_description · use_style_description · enable_safety_checker
standardno

Negative prompto kasutime ande keripe.

acceleration standardno none

Modo de aceleración de keripasko kipesko: 'regular' utilizinela o downstreamo acelerime drom 10 pasosar, independentemente katar num_inference_steps. O standardno modo, 'none', phirel pe num_inference_steps; o standardno Lightning setup, kadia, utilizinel leske konfigurime 4 pasos.

output_format standardno png

Fajlo-formato e rezultato kipoqo.

standardno 1

TeleStyleV2 adapteroski zor, savi šaj te avel tele katar e referencaki implementacijaki 1.0 vaš maj lokhano stilosko efekto.

standardno 1

Lightning LoRA-ski zor, savi šaj te avel tele katar e referencaki implementacijaki 1.0 vaš maj lokhano stilosko efekto.

standardno 4

Gin inference steps pala te kerel.

standardno 1

Setin sar paše o keripe ačhel ko tiro prompto, istivasa CFG, so si Classifier Free Guidance.

Seed va repetirime kipeske rezultato. Te reprodukhes o kipo sako data, astar o seed, sa inputo thaj o modelo verziya bilačho.

POST /run/telestyle-v2?wait=20 hesab → $0.071
# 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/telestyle-v2?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "content_image_url": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg",
    "style_image_url": "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"

Phandel kava mangipen

Tiro kluč ačhel kadale browsereste: bičhalel pes numa ko Doitong API thaj šuvav pes (localStorage) numa te tiknes Remember. Le jekh API ključ

Palal Telestyle V2 Style Transfer

Lel jekh `content_image_url`, savo subjektos thaj rasporedos ačhen sajekh, thaj jekh `style_image_url`, savo stil, materialura, svetlost thaj rangi thovena leste. `lora_scale` (0 dži 4) kontrolinel e stiloski zor, thaj optionalno Lightning LoRA si standardno aktivno 4-korakosa. E rezultatoski veličina šaj te ovel setosardi `image_size` presetonca, thaj šaj te kerel 1 dži 4 kipura ko jekh pozivo sar jpeg vaj png.

Parametra

Bičhalav vaj e kanonikano nav vaj e native nav, na duj. Kanonikane nava

NavTip standardnoMuklo Vakeripe
content_image_urltrubul
Tipurl · image
URL savo sikavel ko kipo savo del o subjekto thaj struktura vaš style transfer. Duj si arakhle kana o kipo lel o stil.
style_image_urltrubul
Tipurl · image
URL e kiposko uživardo te restylil o kontentosko kipo. O referencako kipo del e materijalosko thaj artistikosko stilo, sar-o-kolori thaj svetlo.
lora_scaleopcionalno
Tipnumber
standardno1
0 – 4
TeleStyleV2 adapteroski zor, savi šaj te avel tele katar e referencaki implementacijaki 1.0 vaš maj lokhano stilosko efekto.
use_lightning_loraopcionalno
Tipboolean
standardnotrue
Kontrolil te si Lightning LoRA uživardo paš o standardno LoRA kana si true.
lightning_lora_scaleopcionalno
Tipnumber
standardno1
0 – 4
Lightning LoRA-ski zor, savi šaj te avel tele katar e referencaki implementacijaki 1.0 vaš maj lokhano stilosko efekto.
use_content_descriptionopcionalno
Tipboolean
standardnotrue
Barar o prompto deskripcijasa e kontentoske kiposko kana si true; jekh VLM kerel e deskripcijake.
use_style_descriptionopcionalno
Tipboolean
standardnotrue
Barar o prompto deskripcijasa e stilosteske kiposko kana si true; jekh VLM kerel e deskripcijake.
image_sizeopcionalno
Tipobject
square_hdsquareportrait_4_3portrait_16_9landscape_4_3landscape_16_9
Rezultatoske kiposke dimenzije, save override-in e kontentoske kiposke dimenzije numa kana si dinde.
negative_promptopcionalno
Tipstring
standardno
Negative prompto kasutime ande keripe.
num_inference_stepsopcionalno
Tipinteger
standardno4
2 – 50
Gin inference steps pala te kerel.
guidance_scaleopcionalno
Tipnumber
standardno1
0 – 20
Setin sar paše o keripe ačhel ko tiro prompto, istivasa CFG, so si Classifier Free Guidance.
accelerationopcionalno
Tipenum
standardnonone
noneregular
Modo de aceleración de keripasko kipesko: 'regular' utilizinela o downstreamo acelerime drom 10 pasosar, independentemente katar num_inference_steps. O standardno modo, 'none', phirel pe num_inference_steps; o standardno Lightning setup, kadia, utilizinel leske konfigurime 4 pasos.
num_imagesopcionalno num_outputs
Tipinteger
standardno1
1 – 4
Manglo kipoqo gin vaš generiripe.
seedopcionalno
Tipinteger | null
Seed va repetirime kipeske rezultato. Te reprodukhes o kipo sako data, astar o seed, sa inputo thaj o modelo verziya bilačho.
enable_safety_checkeropcionalno
Tipboolean
standardnotrue
Safety-checker aktivacia; true aktivarel checking.
output_formatopcionalno
Tipenum
standardnopng
jpegpng
Fajlo-formato e rezultato kipoqo.
trubul Kanonikano nav, vi akceptime

Fajloske parametra lel jekh publikano https:// URL, jekh data: URI dži 10 MB, vaj e file_url uploadoski. Fajlura

Rezultato

GET /requests/req_8k2m4q7x1z9c3v5b6n0p2r4t
{
  "id": "req_8k2m4q7x1z9c3v5b6n0p2r4t",
  "object": "request",
  "model": "telestyle-v2",
  "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": 71,
    "usd": "0.071",
    "charged": 71,
    "refunded": 0
  },
  "input": {
    "content_image_url": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg",
    "style_image_url": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg"
  },
  "output": {
    "images": [
      {
        "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,
        "width": 1024,
        "height": 768
      }
    ],
    "has_nsfw_concepts": [
      false
    ],
    "prompt": "",
    "seed": 42
  },
  "outputs": [
    {
      "type": "image",
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.jpeg",
      "content_type": "image/jpeg",
      "file_size": 1843200,
      "width": 1024,
      "height": 768,
      "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"
  }
}
Tire fajlura, tiro alosaripenSako outputs[].url si kopija amare arakhipneste: vično (čargeime per GB-mase) vaj 7 dives bilačhes, tiro kontoskere regulaciatar vaj ?storage=.
Sa jekh forma sako modeloθartype, url, content_type, width, height thaj duration, varesave imajinake, video thaj audio-ke. output si o modelosko korkoro resultosko objekto.
Outputoske fieldura
images
array of object {url, content_type, file_name, file_size, width, height}Kipo vaj kipo le stilosa aplikerdo.
has_nsfw_concepts
array of booleanSikavel te si NSFW konceptura ande kerdo kipo.
prompt
stringPrompto kerdo katar o kontentosko kipo thaj o stiloskho kipo.
seed
integerSeed-valoro aplikovano ko generiripe.

AI agentenge: kadija rig sar Markdown si kate https://doitong.com/rom/developers/models/telestyle-v2.md. Sa e modelura thaj e gidura: https://doitong.com/developers/llms.txt