Vai al contenuto

Recraft V4.1 Text to Image

Integra

ID del modello recraft/v4.1/text-to-image
# 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/recraft/v4.1/text-to-image?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "Full-body fashion shot with the character framed in a close-up, cropped from mid-thigh or waist up so the figure dominates the composition, neutral pose, muted outfit, solid grey background (flat, no gradient). Minimal scribbles with one large graphic element (e.g. oversized abstract shape or drawn eye) placed behind and partially overlapping the figure. Bold oversized typography integrated tightly around the subject: '\''MAKE IT BREAK / MAKE IT WORK'\'' (large serif, slightly distorted, crossing the upper body), '\''no perfect version exists'\'' (small subtle line). Add stickers: minimal icons, checkmarks, soft scribbles, small tape details. Clean but expressive editorial chaos, focus on the character."
  }'

# 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"

Questa richiesta: 0,035 $ 35 crediti API Esegui in questa pagina

Ottieni la chiave API
Recraft Da testo a immagine #design#brand-colors#illustration

Modello di immagini orientato al design, con tavolozze del brand e controllo del colore di sfondo.

Esempi

Output · ~27 s
Full-body fashion shot with the character framed in a close-up, cropped from mid-thigh or waist up so the figure domi...

PromptFull-body fashion shot with the character framed in a close-up, cropped from mid-thigh or waist up so the figure dominates the composition, neutral pose, muted outfit, solid grey background (flat, no gradient). Minimal scribbles with one large graphic element (e.g. oversized abstract shape or drawn eye) placed behind and partially overlapping the figure. Bold oversized typography integrated tightly around the subject: 'MAKE IT BREAK / MAKE IT WORK' (large serif, slightly distorted, crossing the upper body), 'no perfect version exists' (small subtle line). Add stickers: minimal icons, checkmarks, soft scribbles, small tape details. Clean but expressive editorial chaos, focus on the character.

0,035 $ · 35 crediti API

Prompt di @recraftai su X

Crea una richiesta

I controlli vengono generati dallo schema del modello. Il codice e il prezzo si aggiornano mentre li modifichi.

•obbligatorio 700 / 10000
image_size predefinito square_hd
Avanzate colors · background_color
predefinito []

Array contenente i colori preferiti.

Colore preferito per lo sfondo delle immagini generate.

POST /run/recraft/v4.1/text-to-image?wait=20 preventivo → 0,035 $
# 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/recraft/v4.1/text-to-image?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "Full-body fashion shot with the character framed in a close-up, cropped from mid-thigh or waist up so the figure dominates the composition, neutral pose, muted outfit, solid grey background (flat, no gradient). Minimal scribbles with one large graphic element (e.g. oversized abstract shape or drawn eye) placed behind and partially overlapping the figure. Bold oversized typography integrated tightly around the subject: '\''MAKE IT BREAK / MAKE IT WORK'\'' (large serif, slightly distorted, crossing the upper body), '\''no perfect version exists'\'' (small subtle line). Add stickers: minimal icons, checkmarks, soft scribbles, small tape details. Clean but expressive editorial chaos, focus on the character."
  }'

# 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"

Esegui questa richiesta

La tua chiave rimane in questo browser: viene inviata solo al Doitong API e salvata in localStorage solo se selezioni Ricorda. Ottieni una chiave API

Informazioni su Recraft V4.1 Text to Image

Recraft V4.1 è progettato per il design: visual di marketing, illustrazioni e scene di prodotto con una composizione pulita. Passa un elenco di colori RGB preferiti per mantenere la tavolozza del brand oppure fissa il colore di sfondo per set coerenti. Un'immagine per richiesta, con dimensione preimpostata o personalizzata.

Parametri

NomeTipo PredefinitoConsentiti Descrizione
promptobbligatorio
Tipostring
≤ 10.000 caratteri
image_sizefacoltativo
Tipoobject
Predefinitosquare_hd
square_hdsquareportrait_4_3portrait_16_9landscape_4_3landscape_16_9
colorsfacoltativo
Tipoobject[]
Predefinito[]
Array contenente i colori preferiti.
colors[].rfacoltativo
Tipointeger
Predefinito0
0 – 255
Valore della componente rossa.
colors[].gfacoltativo
Tipointeger
Predefinito0
0 – 255
Valore della componente verde.
colors[].bfacoltativo
Tipointeger
Predefinito0
0 – 255
Valore della componente blu.
background_colorfacoltativo
Tipoobject
Colore preferito per lo sfondo delle immagini generate.
background_color.rfacoltativo
Tipointeger
Predefinito0
0 – 255
Valore della componente rossa.
background_color.gfacoltativo
Tipointeger
Predefinito0
0 – 255
Valore della componente verde.
background_color.bfacoltativo
Tipointeger
Predefinito0
0 – 255
Valore della componente blu.
obbligatorio

Output

GET /requests/req_8k2m4q7x1z9c3v5b6n0p2r4t
{
  "id": "req_8k2m4q7x1z9c3v5b6n0p2r4t",
  "object": "request",
  "model": "recraft/v4.1/text-to-image",
  "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": 35,
    "usd": "0.035",
    "charged": 35,
    "refunded": 0
  },
  "input": {
    "prompt": "Tilt-shift miniature view of a fishing village harbor at golden hour, colorful boats, toy-like scale",
    "image_size": "landscape_16_9"
  },
  "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
      }
    ]
  },
  "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"
  }
}
I tuoi file, la tua sceltaOgni outputs[].url è una copia nella nostra archiviazione: conservata per sempre (a pagamento per GB-mese) oppure 7 giorni gratuitamente, in base all'impostazione dell'account o a ?storage=.
Stessa struttura per ogni modellotype, url, content_type, width, height e duration, per immagini, video e audio. output è l'oggetto risultato del modello.
Campi dell'output
images
array of object {url, content_type, file_name, file_size}

Altri modelli: Da testo a immagine

Per gli agenti AI: questa pagina in Markdown è disponibile all'indirizzo https://doitong.com/it/developers/models/recraft/v4.1/text-to-image.md. Tutti i modelli e le guide: https://doitong.com/developers/llms.txt