GPT Image 2.5 Sunburst — tasvirlar yaratish uchun OpenAI modeli. Ishlab chiqaruvchi boshlang‘ich materiallarni tahrirlash aniqligiga alohida e’tibor beradi. Model matnli topshiriqlarni va buning uchun ko‘zda tutilgan amallarda vizual boshlang‘ich materiallarni qo‘llab-quvvatlaydi.
Joriy Ailoot kartasida matndan tasvir yaratish rejimi taqdim etilgan. Kelajakdagi natijaning sahnasi, kompozitsiyasi, uslubi va tafsilotlarini belgilash mumkin. OpenAI tavsiflagan namunalar bilan ishlash, tahrirlash va niqob bo‘yicha hududni o‘zgartirish usullari kiruvchi tasvirlarni alohida qo‘llab-quvvatlashni talab qiladi; matnli yaratish mavjudligi buni tasdiqlamaydi.
low, medium, high, xhigh, max va auto mavjud. Sifat tanlovi tasvir shakllantirish rejimini boshqaradi. U kompozitsiya o‘lchamlari va olingan faylning siqish darajasidan farq qiladi.
O‘lcham kvadrat, gorizontal, vertikal, avtomatik tanlangan yoki qo‘lda belgilangan bo‘lishi mumkin. Foydalanuvchi o‘lchamni belgilaganda har bir tomon 16 pikselga karrali va 3840 pikseldan oshmaydi. Maydon 655 360 va 8 294 400 piksel orasida, uzun tomonning qisqa tomonga nisbati esa ko‘pi bilan 3:1 bo‘lishi kerak. Barcha shartlar bir vaqtda qo‘llanadi.
Ishlab chiqaruvchi 2560x1440’dan yuqori aniqliklarni tajribaviy deb belgilaydi. Katta kadr mos kompozitsiya maydonini tanlashga imkon beradi, lekin yozuvlar va obyektlar joylashuvini tekshirishni bekor qilmaydi.
Standart holatda PNG ishlatiladi; JPEG va WebP ham ko‘zda tutilgan. JPEG va WebP’da siqishni boshqarish mumkin. Shaffof fon uchun PNG yoki WebP kerak, chunki JPEG alfa-kanalni saqlamaydi. Shaffoflik bilan birga shaffof bo‘lmagan fon va avtomatik tanlov ko‘zda tutilgan.
O‘lcham, sifat, format va fon natijaning turli tomonlariga javob beradi. Tasvir uslubi sahna mazmuni bilan birga matnli tavsif orqali belgilanadi. Aniq sozlamalarning qo‘llab-quvvatlanishini ishlab chiqaruvchining umumiy imkoniyatlaridan alohida hisobga olish lozim.
OpenAI ma’lumotiga ko‘ra, murakkab topshiriqni qayta ishlash ikki daqiqagacha vaqt olishi mumkin. Bu aniq ilovada natijani olishning to‘liq vaqti kafolati emas, ishlab chiqaruvchidagi yaratish tavsifidir.
Alohida qo‘llab-quvvatlanadigan tahrirlash amalida niqob tanlangan hudud o‘zgarishini yo‘naltiradi. U natijaning chegaraga qat’iy mosligini kafolatlamaydi, shuning uchun tasvirning muayyan qismini aniq tuzatish va’dasi haddan tashqari kuchli bo‘lardi. Bunday rejimni qo‘llash uchun boshlang‘ich materialni yuborishning tegishli usuli kerak.
Yaratishda model matn va tafsilotlarni joylashtirishda ham xato qilishi yoki alohida tasvirlar orasida personaj ko‘rinishini o‘zgartirishi mumkin. Yozuvlar, kompozitsiya va takrorlanuvchanlik nazorati tayyor faylni tekshirishga tegishli. Hatto batafsil topshiriq ham bu xususiyatlarni kafolatlangan qilmaydi.
", "aboutText": "### Yaratish va tasvir bilan ishlash\n\nGPT Image 2.5 Sunburst — tasvirlar yaratish uchun OpenAI modeli. Ishlab chiqaruvchi boshlang‘ich materiallarni tahrirlash aniqligiga alohida e’tibor beradi. Model matnli topshiriqlarni va buning uchun ko‘zda tutilgan amallarda vizual boshlang‘ich materiallarni qo‘llab-quvvatlaydi.\n\nJoriy Ailoot kartasida matndan tasvir yaratish rejimi taqdim etilgan. Kelajakdagi natijaning sahnasi, kompozitsiyasi, uslubi va tafsilotlarini belgilash mumkin. OpenAI tavsiflagan namunalar bilan ishlash, tahrirlash va niqob bo‘yicha hududni o‘zgartirish usullari kiruvchi tasvirlarni alohida qo‘llab-quvvatlashni talab qiladi; matnli yaratish mavjudligi buni tasdiqlamaydi.\n\n### Sifat va kadr shakli\n\n`low`, `medium`, `high`, `xhigh`, `max` va `auto` mavjud. Sifat tanlovi tasvir shakllantirish rejimini boshqaradi. U kompozitsiya o‘lchamlari va olingan faylning siqish darajasidan farq qiladi.\n\nO‘lcham kvadrat, gorizontal, vertikal, avtomatik tanlangan yoki qo‘lda belgilangan bo‘lishi mumkin. Foydalanuvchi o‘lchamni belgilaganda har bir tomon 16 pikselga karrali va 3840 pikseldan oshmaydi. Maydon 655 360 va 8 294 400 piksel orasida, uzun tomonning qisqa tomonga nisbati esa ko‘pi bilan 3:1 bo‘lishi kerak. Barcha shartlar bir vaqtda qo‘llanadi.\n\nIshlab chiqaruvchi `2560x1440`’dan yuqori aniqliklarni tajribaviy deb belgilaydi. Katta kadr mos kompozitsiya maydonini tanlashga imkon beradi, lekin yozuvlar va obyektlar joylashuvini tekshirishni bekor qilmaydi.\n\n### Natija formatlari va fon\n\nStandart holatda PNG ishlatiladi; JPEG va WebP ham ko‘zda tutilgan. JPEG va WebP’da siqishni boshqarish mumkin. Shaffof fon uchun PNG yoki WebP kerak, chunki JPEG alfa-kanalni saqlamaydi. Shaffoflik bilan birga shaffof bo‘lmagan fon va avtomatik tanlov ko‘zda tutilgan.\n\nO‘lcham, sifat, format va fon natijaning turli tomonlariga javob beradi. Tasvir uslubi sahna mazmuni bilan birga matnli tavsif orqali belgilanadi. Aniq sozlamalarning qo‘llab-quvvatlanishini ishlab chiqaruvchining umumiy imkoniyatlaridan alohida hisobga olish lozim.\n\n### Tuzatish aniqligi va tasvir nazorati\n\nOpenAI ma’lumotiga ko‘ra, murakkab topshiriqni qayta ishlash ikki daqiqagacha vaqt olishi mumkin. Bu aniq ilovada natijani olishning to‘liq vaqti kafolati emas, ishlab chiqaruvchidagi yaratish tavsifidir.\n\nAlohida qo‘llab-quvvatlanadigan tahrirlash amalida niqob tanlangan hudud o‘zgarishini yo‘naltiradi. U natijaning chegaraga qat’iy mosligini kafolatlamaydi, shuning uchun tasvirning muayyan qismini aniq tuzatish va’dasi haddan tashqari kuchli bo‘lardi. Bunday rejimni qo‘llash uchun boshlang‘ich materialni yuborishning tegishli usuli kerak.\n\nYaratishda model matn va tafsilotlarni joylashtirishda ham xato qilishi yoki alohida tasvirlar orasida personaj ko‘rinishini o‘zgartirishi mumkin. Yozuvlar, kompozitsiya va takrorlanuvchanlik nazorati tayyor faylni tekshirishga tegishli. Hatto batafsil topshiriq ham bu xususiyatlarni kafolatlangan qilmaydi.", "editorialOverlay": { "copy_fields": null, "copy_sha256": null, "copy_source": null, "html_sha256": "e2529de0f41db121283ffa6756e44c4f714465e417477365691bf9f59ba09084", "module_sha256": "ee9dc1c50b1e6a8fb7fa062030fcb4646b9aaaeb08be513b723a5a92a7290f06", "raw_model_unchanged": true, "schema": "ailoot-native-model-editorial-v1" }, "locale": "uz", "methods": [ { "html": "gpt-image-2.5-sunburstGPT Image 2.5 Sunburst matnli topshiriq asosida tasvirlar yaratadi. Foydalanuvchi belgilaydigan o‘lchamlar, kengaytirilgan sifat darajalari va shaffof fonni qo‘llab-quvvatlaydi; ishlab chiqaruvchi tahrirlash aniqligini ham ta’kidlaydi.
Bu tavsif model imkoniyatlarini yoritadi. Ailoot da tanlangan usul uchun mavjud kirish, chiqish va parametrlar quyida keltirilgan.
GPT Image 2.5 Sunburst — tasvirlar yaratish uchun OpenAI modeli. Ishlab chiqaruvchi boshlang‘ich materiallarni tahrirlash aniqligiga alohida e’tibor beradi. Model matnli topshiriqlarni va buning uchun ko‘zda tutilgan amallarda vizual boshlang‘ich materiallarni qo‘llab-quvvatlaydi.
Joriy Ailoot kartasida matndan tasvir yaratish rejimi taqdim etilgan. Kelajakdagi natijaning sahnasi, kompozitsiyasi, uslubi va tafsilotlarini belgilash mumkin. OpenAI tavsiflagan namunalar bilan ishlash, tahrirlash va niqob bo‘yicha hududni o‘zgartirish usullari kiruvchi tasvirlarni alohida qo‘llab-quvvatlashni talab qiladi; matnli yaratish mavjudligi buni tasdiqlamaydi.
low, medium, high, xhigh, max va auto mavjud. Sifat tanlovi tasvir shakllantirish rejimini boshqaradi. U kompozitsiya o‘lchamlari va olingan faylning siqish darajasidan farq qiladi.
O‘lcham kvadrat, gorizontal, vertikal, avtomatik tanlangan yoki qo‘lda belgilangan bo‘lishi mumkin. Foydalanuvchi o‘lchamni belgilaganda har bir tomon 16 pikselga karrali va 3840 pikseldan oshmaydi. Maydon 655 360 va 8 294 400 piksel orasida, uzun tomonning qisqa tomonga nisbati esa ko‘pi bilan 3:1 bo‘lishi kerak. Barcha shartlar bir vaqtda qo‘llanadi.
Ishlab chiqaruvchi 2560x1440’dan yuqori aniqliklarni tajribaviy deb belgilaydi. Katta kadr mos kompozitsiya maydonini tanlashga imkon beradi, lekin yozuvlar va obyektlar joylashuvini tekshirishni bekor qilmaydi.
Standart holatda PNG ishlatiladi; JPEG va WebP ham ko‘zda tutilgan. JPEG va WebP’da siqishni boshqarish mumkin. Shaffof fon uchun PNG yoki WebP kerak, chunki JPEG alfa-kanalni saqlamaydi. Shaffoflik bilan birga shaffof bo‘lmagan fon va avtomatik tanlov ko‘zda tutilgan.
O‘lcham, sifat, format va fon natijaning turli tomonlariga javob beradi. Tasvir uslubi sahna mazmuni bilan birga matnli tavsif orqali belgilanadi. Aniq sozlamalarning qo‘llab-quvvatlanishini ishlab chiqaruvchining umumiy imkoniyatlaridan alohida hisobga olish lozim.
OpenAI ma’lumotiga ko‘ra, murakkab topshiriqni qayta ishlash ikki daqiqagacha vaqt olishi mumkin. Bu aniq ilovada natijani olishning to‘liq vaqti kafolati emas, ishlab chiqaruvchidagi yaratish tavsifidir.
Alohida qo‘llab-quvvatlanadigan tahrirlash amalida niqob tanlangan hudud o‘zgarishini yo‘naltiradi. U natijaning chegaraga qat’iy mosligini kafolatlamaydi, shuning uchun tasvirning muayyan qismini aniq tuzatish va’dasi haddan tashqari kuchli bo‘lardi. Bunday rejimni qo‘llash uchun boshlang‘ich materialni yuborishning tegishli usuli kerak.
Yaratishda model matn va tafsilotlarni joylashtirishda ham xato qilishi yoki alohida tasvirlar orasida personaj ko‘rinishini o‘zgartirishi mumkin. Yozuvlar, kompozitsiya va takrorlanuvchanlik nazorati tayyor faylni tekshirishga tegishli. Hatto batafsil topshiriq ham bu xususiyatlarni kafolatlangan qilmaydi.
POST /v1/images/generationstextimage| Maydon | Tur | Talab | Qiymatlar va cheklovlar | Standart |
|---|---|---|---|---|
Maydonmodel | Turstring | TalabMajburiy | Qiymatlar va cheklovlar gpt-image-2.5-sunburst | Standart— |
Maydonprompt | Turstring | TalabMajburiy | Qiymatlar va cheklovlar Eng kam uzunlik: 1 | Standart— |
Maydonn | Turinteger | TalabIxtiyoriy | Qiymatlar va cheklovlar Eng kam: 1 | Standart1 |
Maydonresponse_format | Turstring | TalabIxtiyoriy | Qiymatlar va cheklovlar url, b64_json | Standart— |
Maydonstream | Turboolean | TalabIxtiyoriy | Qiymatlar va cheklovlar | Standartfalse |
Maydonsize | Turstring | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydonquality | Turstring | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydonbackground | Turstring | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydonoutput_format | Turstring | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydonoutput_compression | Turinteger | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydonmoderation | Turstring | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydoninput_fidelity | Turstring | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydonstyle | Turstring | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydonpartial_images | Turinteger | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Matndan rasm · Majburiy: prompt
| Parametr | Parametr talablari |
|---|---|
Parametrmaterial_types | Parametr talablaritext |
Parametrrequired | Parametr talablarimodel, prompt |
Parametroptional_controls | Parametr talablarinull |
Parametrcontent_type | Parametr talablariapplication/json |
Hayot sikli: synchronous_result_then_owned_library
GET /v1/media/tasks/{task_id} · Amalda qaytarilgan task_id yoki media kutubxonasidagi yozuv
GET /v1/media/assets/{asset_id}/content
GET /v1/media/assets
GET /v1/media/assets/{asset_id}
Metod tuzilishlari va IDlari aniq; yetkazib beruvchining imkoniyati so‘rovni qabul qilishga ruxsatdan alohida.
POST /v1/images/generationsAiloot so‘rovdan oldin taxminiy summani band qiladi. Natijadan keyin o‘lchangan sarf asosidagi yakuniy to‘lovni yechadi. Oqimli javob bo‘yicha yakuniy hisob-kitob yakuniy sarf yozuviga asoslanadi. Summani band qilish va to‘lovni hisoblash tartibi →
set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\nexport AILOOT_API_KEY\nexport AILOOT_API_KEY\n: "${AILOOT_PROMPT_FILE:?Set your actual UTF-8 image brief}"\nexport AILOOT_PROMPT_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model": "gpt-image-2.5-sunburst", "prompt": ""}')\nf=Path(os.environ["AILOOT_PROMPT_FILE"])\nif not f.is_file():raise SystemExit("Choose your actual UTF-8 brief")\np['prompt']=f.read_text(encoding="utf-8")\nif not p['prompt'].strip():raise SystemExit("Brief must contain text")\nPath("request.json").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/images/generations \\\n -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport base64, json, os, subprocess\nfrom pathlib import Path\nfrom urllib.parse import urlsplit, urljoin\n\ndef save_images(items):\n if not items: raise SystemExit("No completed images; retain the full response")\n for index, item in enumerate(items):\n encoded=item.get("b64_json")\n uri=item.get("url", "")\n if not encoded and uri.startswith("data:image/"):\n header, separator, encoded=uri.partition(",")\n if not separator or ";base64" not in header: raise SystemExit("Unsupported image data URI")\n if encoded:\n raw=base64.b64decode(encoded,validate=True)\n elif uri:\n uri=urljoin("https://api.ailoot.ai",uri)\n parsed=urlsplit(uri)\n if parsed.scheme!="https" or not parsed.netloc or parsed.username or parsed.password:\n raise SystemExit("Invalid returned image URL")\n owned=parsed.netloc=="api.ailoot.ai" and parsed.path.startswith("/v1/media/assets/") and parsed.path.endswith("/content")\n args=["curl","--fail-with-body","--silent","--show-error",uri]\n if owned: args += ["-H","Authorization: Bearer "+os.environ["AILOOT_API_KEY"]]\n temporary=Path(f"image-{index}.bin")\n subprocess.run(args+["-o",str(temporary)],check=True)\n raw=temporary.read_bytes()\n temporary.unlink()\n else: raise SystemExit("Image has neither bytes nor URL")\n if not raw: raise SystemExit("Empty image result")\n ext="png" if raw.startswith(b"\\x89PNG") else "jpg" if raw.startswith(b"\\xff\\xd8") else "webp" if raw[:4]==b"RIFF" and raw[8:12]==b"WEBP" else "svg" if raw.lstrip().startswith((b"<svg",b"<?xml")) else "bin"\n Path(f"image-{index}.{ext}").write_bytes(raw)\n print("Every returned image saved; complete response metadata retained")\nsave_images(json.loads(Path("result.json").read_text())["data"])\nPY_RESULT\nfrom openai import OpenAI\nimport base64, json, os, subprocess\nfrom pathlib import Path\nfrom urllib.parse import urlsplit, urljoin\n\ndef save_images(items):\n if not items: raise SystemExit("No completed images; retain the full response")\n for index, item in enumerate(items):\n encoded=item.get("b64_json")\n uri=item.get("url", "")\n if not encoded and uri.startswith("data:image/"):\n header, separator, encoded=uri.partition(",")\n if not separator or ";base64" not in header: raise SystemExit("Unsupported image data URI")\n if encoded:\n raw=base64.b64decode(encoded,validate=True)\n elif uri:\n uri=urljoin("https://api.ailoot.ai",uri)\n parsed=urlsplit(uri)\n if parsed.scheme!="https" or not parsed.netloc or parsed.username or parsed.password:\n raise SystemExit("Invalid returned image URL")\n owned=parsed.netloc=="api.ailoot.ai" and parsed.path.startswith("/v1/media/assets/") and parsed.path.endswith("/content")\n args=["curl","--fail-with-body","--silent","--show-error",uri]\n if owned: args += ["-H","Authorization: Bearer "+os.environ["AILOOT_API_KEY"]]\n temporary=Path(f"image-{index}.bin")\n subprocess.run(args+["-o",str(temporary)],check=True)\n raw=temporary.read_bytes()\n temporary.unlink()\n else: raise SystemExit("Image has neither bytes nor URL")\n if not raw: raise SystemExit("Empty image result")\n ext="png" if raw.startswith(b"\\x89PNG") else "jpg" if raw.startswith(b"\\xff\\xd8") else "webp" if raw[:4]==b"RIFF" and raw[8:12]==b"WEBP" else "svg" if raw.lstrip().startswith((b"<svg",b"<?xml")) else "bin"\n Path(f"image-{index}.{ext}").write_bytes(raw)\n print("Every returned image saved; complete response metadata retained")\n\nf=Path(os.environ["AILOOT_PROMPT_FILE"])\nif not f.is_file():raise SystemExit("Set your actual UTF-8 image brief file")\nrequest={'model': 'gpt-image-2.5-sunburst', 'prompt': ''}\nrequest["prompt"]=f.read_text(encoding="utf-8")\nclient=OpenAI(base_url="https://api.ailoot.ai/v1",api_key=os.environ["AILOOT_API_KEY"],max_retries=0)\nresult=client.images.generate(**request)\nPath("sdk-result.txt").write_text(str(result),encoding="utf-8")\nsave_images([{"b64_json":getattr(item,"b64_json",None),"url":getattr(item,"url",None)} for item in result.data])\nimport OpenAI from "openai";\nimport { readFileSync, writeFileSync } from "node:fs";\nconst key=process.env.AILOOT_API_KEY;\nif(!key) throw new Error("Set your actual Ailoot API key");\nconst client=new OpenAI({baseURL:"https://api.ailoot.ai/v1",apiKey:key,maxRetries:0});\nconst request={"model": "gpt-image-2.5-sunburst", "prompt": ""};\nif(!process.env.AILOOT_PROMPT_FILE)throw new Error("Set your actual UTF-8 image brief file");\nrequest.prompt=readFileSync(process.env.AILOOT_PROMPT_FILE,"utf8");\nconst result=await client.images.generate(request);\nwriteFileSync("sdk-result.json",JSON.stringify(result,null,2));\nif(!result.data?.length) throw new Error("No completed images");\nfor(let index=0;index<result.data.length;index++) {\n const item=result.data[index];let encoded=item.b64_json,uri=item.url||"",raw;\n if(!encoded && uri.startsWith("data:image/")) {\n const comma=uri.indexOf(",");if(comma<0 || !uri.slice(0,comma).includes(";base64")) throw new Error("Unsupported image data URI");\n encoded=uri.slice(comma+1);\n }\n if(encoded) {\n if(encoded.length%4!==0 || !/^[A-Za-z0-9+/]*={0,2}$/.test(encoded)) throw new Error("Invalid Base64");\n raw=Buffer.from(encoded,"base64");\n } else if(uri) {\n const u=new URL(uri,"https://api.ailoot.ai");\n if(u.protocol!=="https:" || u.username || u.password) throw new Error("Invalid returned URL");\n const owned=u.origin==="https://api.ailoot.ai" && u.pathname.startsWith("/v1/media/assets/") && u.pathname.endsWith("/content");\n const response=await fetch(u,{headers:owned?{Authorization:"Bearer "+key}:{},redirect:"manual"});\n if(!response.ok) throw new Error("Image content download failed: "+response.status);\n raw=Buffer.from(await response.arrayBuffer());\n } else throw new Error("Image has neither bytes nor URL");\n if(!raw.length) throw new Error("Empty image result");\n const ext=raw.subarray(0,4).equals(Buffer.from([137,80,78,71]))?"png":raw[0]===255&&raw[1]===216?"jpg":raw.toString("ascii",0,4)==="RIFF"&&raw.toString("ascii",8,12)==="WEBP"?"webp":raw.toString("utf8").trimStart().startsWith("<svg")||raw.toString("utf8").trimStart().startsWith("<?xml")?"svg":"bin";\n writeFileSync(`image-${index}.${ext}`,raw);\n}\nconsole.log("Every returned image saved; sdk-result.json retains complete metadata");\nHar bir qaytarilgan rasmni yuklab oling yoki uning Base64 kontentini saqlang
GET /v1/media/tasks/{task_id}GET /v1/media/assets/{asset_id}/contentGET /v1/media/assetsGET /v1/media/assets/{asset_id}Har bir tayyor rasmni saqlang; har bir qaytarilgan URL dan kontentni oling yoki uning Base64 kontentini dekodlang.
Har bir ma’lumot elementini saqlang. Har bir b64_json ni dekodlang yoki qaytarilgan har bir imzolangan URL dan faylni yuklab oling. Fayl nomi kengaytmasini haqiqiy MIME turi/baytlar asosida tanlang.
Rasm yaratish yoki tahrirlash natijasini tekshirish kerak bo‘lsa, dastlabki operation_id/X-Client-Request-ID va qaytarilgan natija haqidagi ma’lumotlarni saqlang. Amalda qaytarilgan task_id yoki asset_id qiymatlari yordamida media kutubxonasidan o‘zingizga tegishli mavjud natijalarni tiklang. Rasm yaratish/tahrirlash so‘rovini qayta yubormang va operation_id dan holatni davriy tekshirish uchun URL tuzmang.
| Maydon | Tur |
|---|---|
Maydoncreated | Turinteger |
Maydondata[].url | Turstring |
Maydondata[].b64_json | Turbase64 string |
Maydonusage | Turobject |
| Javob | Shart | Keyingi qadam |
|---|---|---|
Javob400 · invalid_request_error | ShartMajburiy maydonlar, material ifodasi yoki parametr qiymati noto‘g‘ri | Keyingi qadamYangi yaratish so‘rovidan oldin ko‘rsatilgan maydonlarni tuzating. |
Javobserver_error | ShartQaytarilgan javob operatsiya yoki natijani tekshirish kerakligini bildiradi | Keyingi qadamDastlab qaytarilgan operatsiya/vazifa ID sini, so‘rov sarlavhalarini va javobni saqlang; aynan shu operatsiya uchun qo‘llab-quvvatlanadigan o‘qish so‘rovlarini davom ettiring. Yaratish so‘rovini qayta yubormang. |
Ailoot gpt-image-2.5-sunburst, gpt-image, gpt-image-2.5, gpt-image-2.5-latest, gpt-image-latest
Yuqorida ko‘rsatilgan usul yo‘llaridan foydalaning.
gpt-image-2.5-sunburst, gpt-image, gpt-image-2.5, gpt-image-2.5-latest, gpt-image-latest
gpt-imageGPT Image 2.5 Sunburst matnli topshiriq asosida tasvirlar yaratadi. Foydalanuvchi belgilaydigan o‘lchamlar, kengaytirilgan sifat darajalari va shaffof fonni qo‘llab-quvvatlaydi; ishlab chiqaruvchi tahrirlash aniqligini ham ta’kidlaydi.
Bu tavsif model imkoniyatlarini yoritadi. Ailoot da tanlangan usul uchun mavjud kirish, chiqish va parametrlar quyida keltirilgan.
GPT Image 2.5 Sunburst — tasvirlar yaratish uchun OpenAI modeli. Ishlab chiqaruvchi boshlang‘ich materiallarni tahrirlash aniqligiga alohida e’tibor beradi. Model matnli topshiriqlarni va buning uchun ko‘zda tutilgan amallarda vizual boshlang‘ich materiallarni qo‘llab-quvvatlaydi.
Joriy Ailoot kartasida matndan tasvir yaratish rejimi taqdim etilgan. Kelajakdagi natijaning sahnasi, kompozitsiyasi, uslubi va tafsilotlarini belgilash mumkin. OpenAI tavsiflagan namunalar bilan ishlash, tahrirlash va niqob bo‘yicha hududni o‘zgartirish usullari kiruvchi tasvirlarni alohida qo‘llab-quvvatlashni talab qiladi; matnli yaratish mavjudligi buni tasdiqlamaydi.
low, medium, high, xhigh, max va auto mavjud. Sifat tanlovi tasvir shakllantirish rejimini boshqaradi. U kompozitsiya o‘lchamlari va olingan faylning siqish darajasidan farq qiladi.
O‘lcham kvadrat, gorizontal, vertikal, avtomatik tanlangan yoki qo‘lda belgilangan bo‘lishi mumkin. Foydalanuvchi o‘lchamni belgilaganda har bir tomon 16 pikselga karrali va 3840 pikseldan oshmaydi. Maydon 655 360 va 8 294 400 piksel orasida, uzun tomonning qisqa tomonga nisbati esa ko‘pi bilan 3:1 bo‘lishi kerak. Barcha shartlar bir vaqtda qo‘llanadi.
Ishlab chiqaruvchi 2560x1440’dan yuqori aniqliklarni tajribaviy deb belgilaydi. Katta kadr mos kompozitsiya maydonini tanlashga imkon beradi, lekin yozuvlar va obyektlar joylashuvini tekshirishni bekor qilmaydi.
Standart holatda PNG ishlatiladi; JPEG va WebP ham ko‘zda tutilgan. JPEG va WebP’da siqishni boshqarish mumkin. Shaffof fon uchun PNG yoki WebP kerak, chunki JPEG alfa-kanalni saqlamaydi. Shaffoflik bilan birga shaffof bo‘lmagan fon va avtomatik tanlov ko‘zda tutilgan.
O‘lcham, sifat, format va fon natijaning turli tomonlariga javob beradi. Tasvir uslubi sahna mazmuni bilan birga matnli tavsif orqali belgilanadi. Aniq sozlamalarning qo‘llab-quvvatlanishini ishlab chiqaruvchining umumiy imkoniyatlaridan alohida hisobga olish lozim.
OpenAI ma’lumotiga ko‘ra, murakkab topshiriqni qayta ishlash ikki daqiqagacha vaqt olishi mumkin. Bu aniq ilovada natijani olishning to‘liq vaqti kafolati emas, ishlab chiqaruvchidagi yaratish tavsifidir.
Alohida qo‘llab-quvvatlanadigan tahrirlash amalida niqob tanlangan hudud o‘zgarishini yo‘naltiradi. U natijaning chegaraga qat’iy mosligini kafolatlamaydi, shuning uchun tasvirning muayyan qismini aniq tuzatish va’dasi haddan tashqari kuchli bo‘lardi. Bunday rejimni qo‘llash uchun boshlang‘ich materialni yuborishning tegishli usuli kerak.
Yaratishda model matn va tafsilotlarni joylashtirishda ham xato qilishi yoki alohida tasvirlar orasida personaj ko‘rinishini o‘zgartirishi mumkin. Yozuvlar, kompozitsiya va takrorlanuvchanlik nazorati tayyor faylni tekshirishga tegishli. Hatto batafsil topshiriq ham bu xususiyatlarni kafolatlangan qilmaydi.
POST /v1/images/generationstextimage| Maydon | Tur | Talab | Qiymatlar va cheklovlar | Standart |
|---|---|---|---|---|
Maydonmodel | Turstring | TalabMajburiy | Qiymatlar va cheklovlar gpt-image | Standart— |
Maydonprompt | Turstring | TalabMajburiy | Qiymatlar va cheklovlar Eng kam uzunlik: 1 | Standart— |
Maydonn | Turinteger | TalabIxtiyoriy | Qiymatlar va cheklovlar Eng kam: 1 | Standart1 |
Maydonresponse_format | Turstring | TalabIxtiyoriy | Qiymatlar va cheklovlar url, b64_json | Standart— |
Maydonstream | Turboolean | TalabIxtiyoriy | Qiymatlar va cheklovlar | Standartfalse |
Maydonsize | Turstring | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydonquality | Turstring | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydonbackground | Turstring | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydonoutput_format | Turstring | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydonoutput_compression | Turinteger | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydonmoderation | Turstring | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydoninput_fidelity | Turstring | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydonstyle | Turstring | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydonpartial_images | Turinteger | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Matndan rasm · Majburiy: prompt
| Parametr | Parametr talablari |
|---|---|
Parametrmaterial_types | Parametr talablaritext |
Parametrrequired | Parametr talablarimodel, prompt |
Parametroptional_controls | Parametr talablarinull |
Parametrcontent_type | Parametr talablariapplication/json |
Hayot sikli: synchronous_result_then_owned_library
GET /v1/media/tasks/{task_id} · Amalda qaytarilgan task_id yoki media kutubxonasidagi yozuv
GET /v1/media/assets/{asset_id}/content
GET /v1/media/assets
GET /v1/media/assets/{asset_id}
Metod tuzilishlari va IDlari aniq; yetkazib beruvchining imkoniyati so‘rovni qabul qilishga ruxsatdan alohida.
POST /v1/images/generationsAiloot so‘rovdan oldin taxminiy summani band qiladi. Natijadan keyin o‘lchangan sarf asosidagi yakuniy to‘lovni yechadi. Oqimli javob bo‘yicha yakuniy hisob-kitob yakuniy sarf yozuviga asoslanadi. Summani band qilish va to‘lovni hisoblash tartibi →
set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\nexport AILOOT_API_KEY\nexport AILOOT_API_KEY\n: "${AILOOT_PROMPT_FILE:?Set your actual UTF-8 image brief}"\nexport AILOOT_PROMPT_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model": "gpt-image", "prompt": ""}')\nf=Path(os.environ["AILOOT_PROMPT_FILE"])\nif not f.is_file():raise SystemExit("Choose your actual UTF-8 brief")\np['prompt']=f.read_text(encoding="utf-8")\nif not p['prompt'].strip():raise SystemExit("Brief must contain text")\nPath("request.json").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/images/generations \\\n -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport base64, json, os, subprocess\nfrom pathlib import Path\nfrom urllib.parse import urlsplit, urljoin\n\ndef save_images(items):\n if not items: raise SystemExit("No completed images; retain the full response")\n for index, item in enumerate(items):\n encoded=item.get("b64_json")\n uri=item.get("url", "")\n if not encoded and uri.startswith("data:image/"):\n header, separator, encoded=uri.partition(",")\n if not separator or ";base64" not in header: raise SystemExit("Unsupported image data URI")\n if encoded:\n raw=base64.b64decode(encoded,validate=True)\n elif uri:\n uri=urljoin("https://api.ailoot.ai",uri)\n parsed=urlsplit(uri)\n if parsed.scheme!="https" or not parsed.netloc or parsed.username or parsed.password:\n raise SystemExit("Invalid returned image URL")\n owned=parsed.netloc=="api.ailoot.ai" and parsed.path.startswith("/v1/media/assets/") and parsed.path.endswith("/content")\n args=["curl","--fail-with-body","--silent","--show-error",uri]\n if owned: args += ["-H","Authorization: Bearer "+os.environ["AILOOT_API_KEY"]]\n temporary=Path(f"image-{index}.bin")\n subprocess.run(args+["-o",str(temporary)],check=True)\n raw=temporary.read_bytes()\n temporary.unlink()\n else: raise SystemExit("Image has neither bytes nor URL")\n if not raw: raise SystemExit("Empty image result")\n ext="png" if raw.startswith(b"\\x89PNG") else "jpg" if raw.startswith(b"\\xff\\xd8") else "webp" if raw[:4]==b"RIFF" and raw[8:12]==b"WEBP" else "svg" if raw.lstrip().startswith((b"<svg",b"<?xml")) else "bin"\n Path(f"image-{index}.{ext}").write_bytes(raw)\n print("Every returned image saved; complete response metadata retained")\nsave_images(json.loads(Path("result.json").read_text())["data"])\nPY_RESULT\nfrom openai import OpenAI\nimport base64, json, os, subprocess\nfrom pathlib import Path\nfrom urllib.parse import urlsplit, urljoin\n\ndef save_images(items):\n if not items: raise SystemExit("No completed images; retain the full response")\n for index, item in enumerate(items):\n encoded=item.get("b64_json")\n uri=item.get("url", "")\n if not encoded and uri.startswith("data:image/"):\n header, separator, encoded=uri.partition(",")\n if not separator or ";base64" not in header: raise SystemExit("Unsupported image data URI")\n if encoded:\n raw=base64.b64decode(encoded,validate=True)\n elif uri:\n uri=urljoin("https://api.ailoot.ai",uri)\n parsed=urlsplit(uri)\n if parsed.scheme!="https" or not parsed.netloc or parsed.username or parsed.password:\n raise SystemExit("Invalid returned image URL")\n owned=parsed.netloc=="api.ailoot.ai" and parsed.path.startswith("/v1/media/assets/") and parsed.path.endswith("/content")\n args=["curl","--fail-with-body","--silent","--show-error",uri]\n if owned: args += ["-H","Authorization: Bearer "+os.environ["AILOOT_API_KEY"]]\n temporary=Path(f"image-{index}.bin")\n subprocess.run(args+["-o",str(temporary)],check=True)\n raw=temporary.read_bytes()\n temporary.unlink()\n else: raise SystemExit("Image has neither bytes nor URL")\n if not raw: raise SystemExit("Empty image result")\n ext="png" if raw.startswith(b"\\x89PNG") else "jpg" if raw.startswith(b"\\xff\\xd8") else "webp" if raw[:4]==b"RIFF" and raw[8:12]==b"WEBP" else "svg" if raw.lstrip().startswith((b"<svg",b"<?xml")) else "bin"\n Path(f"image-{index}.{ext}").write_bytes(raw)\n print("Every returned image saved; complete response metadata retained")\n\nf=Path(os.environ["AILOOT_PROMPT_FILE"])\nif not f.is_file():raise SystemExit("Set your actual UTF-8 image brief file")\nrequest={'model': 'gpt-image', 'prompt': ''}\nrequest["prompt"]=f.read_text(encoding="utf-8")\nclient=OpenAI(base_url="https://api.ailoot.ai/v1",api_key=os.environ["AILOOT_API_KEY"],max_retries=0)\nresult=client.images.generate(**request)\nPath("sdk-result.txt").write_text(str(result),encoding="utf-8")\nsave_images([{"b64_json":getattr(item,"b64_json",None),"url":getattr(item,"url",None)} for item in result.data])\nimport OpenAI from "openai";\nimport { readFileSync, writeFileSync } from "node:fs";\nconst key=process.env.AILOOT_API_KEY;\nif(!key) throw new Error("Set your actual Ailoot API key");\nconst client=new OpenAI({baseURL:"https://api.ailoot.ai/v1",apiKey:key,maxRetries:0});\nconst request={"model": "gpt-image", "prompt": ""};\nif(!process.env.AILOOT_PROMPT_FILE)throw new Error("Set your actual UTF-8 image brief file");\nrequest.prompt=readFileSync(process.env.AILOOT_PROMPT_FILE,"utf8");\nconst result=await client.images.generate(request);\nwriteFileSync("sdk-result.json",JSON.stringify(result,null,2));\nif(!result.data?.length) throw new Error("No completed images");\nfor(let index=0;index<result.data.length;index++) {\n const item=result.data[index];let encoded=item.b64_json,uri=item.url||"",raw;\n if(!encoded && uri.startsWith("data:image/")) {\n const comma=uri.indexOf(",");if(comma<0 || !uri.slice(0,comma).includes(";base64")) throw new Error("Unsupported image data URI");\n encoded=uri.slice(comma+1);\n }\n if(encoded) {\n if(encoded.length%4!==0 || !/^[A-Za-z0-9+/]*={0,2}$/.test(encoded)) throw new Error("Invalid Base64");\n raw=Buffer.from(encoded,"base64");\n } else if(uri) {\n const u=new URL(uri,"https://api.ailoot.ai");\n if(u.protocol!=="https:" || u.username || u.password) throw new Error("Invalid returned URL");\n const owned=u.origin==="https://api.ailoot.ai" && u.pathname.startsWith("/v1/media/assets/") && u.pathname.endsWith("/content");\n const response=await fetch(u,{headers:owned?{Authorization:"Bearer "+key}:{},redirect:"manual"});\n if(!response.ok) throw new Error("Image content download failed: "+response.status);\n raw=Buffer.from(await response.arrayBuffer());\n } else throw new Error("Image has neither bytes nor URL");\n if(!raw.length) throw new Error("Empty image result");\n const ext=raw.subarray(0,4).equals(Buffer.from([137,80,78,71]))?"png":raw[0]===255&&raw[1]===216?"jpg":raw.toString("ascii",0,4)==="RIFF"&&raw.toString("ascii",8,12)==="WEBP"?"webp":raw.toString("utf8").trimStart().startsWith("<svg")||raw.toString("utf8").trimStart().startsWith("<?xml")?"svg":"bin";\n writeFileSync(`image-${index}.${ext}`,raw);\n}\nconsole.log("Every returned image saved; sdk-result.json retains complete metadata");\nHar bir qaytarilgan rasmni yuklab oling yoki uning Base64 kontentini saqlang
GET /v1/media/tasks/{task_id}GET /v1/media/assets/{asset_id}/contentGET /v1/media/assetsGET /v1/media/assets/{asset_id}Har bir tayyor rasmni saqlang; har bir qaytarilgan URL dan kontentni oling yoki uning Base64 kontentini dekodlang.
Har bir ma’lumot elementini saqlang. Har bir b64_json ni dekodlang yoki qaytarilgan har bir imzolangan URL dan faylni yuklab oling. Fayl nomi kengaytmasini haqiqiy MIME turi/baytlar asosida tanlang.
Rasm yaratish yoki tahrirlash natijasini tekshirish kerak bo‘lsa, dastlabki operation_id/X-Client-Request-ID va qaytarilgan natija haqidagi ma’lumotlarni saqlang. Amalda qaytarilgan task_id yoki asset_id qiymatlari yordamida media kutubxonasidan o‘zingizga tegishli mavjud natijalarni tiklang. Rasm yaratish/tahrirlash so‘rovini qayta yubormang va operation_id dan holatni davriy tekshirish uchun URL tuzmang.
| Maydon | Tur |
|---|---|
Maydoncreated | Turinteger |
Maydondata[].url | Turstring |
Maydondata[].b64_json | Turbase64 string |
Maydonusage | Turobject |
| Javob | Shart | Keyingi qadam |
|---|---|---|
Javob400 · invalid_request_error | ShartMajburiy maydonlar, material ifodasi yoki parametr qiymati noto‘g‘ri | Keyingi qadamYangi yaratish so‘rovidan oldin ko‘rsatilgan maydonlarni tuzating. |
Javobserver_error | ShartQaytarilgan javob operatsiya yoki natijani tekshirish kerakligini bildiradi | Keyingi qadamDastlab qaytarilgan operatsiya/vazifa ID sini, so‘rov sarlavhalarini va javobni saqlang; aynan shu operatsiya uchun qo‘llab-quvvatlanadigan o‘qish so‘rovlarini davom ettiring. Yaratish so‘rovini qayta yubormang. |
Ailoot gpt-image-2.5-sunburst, gpt-image, gpt-image-2.5, gpt-image-2.5-latest, gpt-image-latest
Yuqorida ko‘rsatilgan usul yo‘llaridan foydalaning.
gpt-image-2.5-sunburst, gpt-image, gpt-image-2.5, gpt-image-2.5-latest, gpt-image-latest
gpt-image-2.5GPT Image 2.5 Sunburst matnli topshiriq asosida tasvirlar yaratadi. Foydalanuvchi belgilaydigan o‘lchamlar, kengaytirilgan sifat darajalari va shaffof fonni qo‘llab-quvvatlaydi; ishlab chiqaruvchi tahrirlash aniqligini ham ta’kidlaydi.
Bu tavsif model imkoniyatlarini yoritadi. Ailoot da tanlangan usul uchun mavjud kirish, chiqish va parametrlar quyida keltirilgan.
GPT Image 2.5 Sunburst — tasvirlar yaratish uchun OpenAI modeli. Ishlab chiqaruvchi boshlang‘ich materiallarni tahrirlash aniqligiga alohida e’tibor beradi. Model matnli topshiriqlarni va buning uchun ko‘zda tutilgan amallarda vizual boshlang‘ich materiallarni qo‘llab-quvvatlaydi.
Joriy Ailoot kartasida matndan tasvir yaratish rejimi taqdim etilgan. Kelajakdagi natijaning sahnasi, kompozitsiyasi, uslubi va tafsilotlarini belgilash mumkin. OpenAI tavsiflagan namunalar bilan ishlash, tahrirlash va niqob bo‘yicha hududni o‘zgartirish usullari kiruvchi tasvirlarni alohida qo‘llab-quvvatlashni talab qiladi; matnli yaratish mavjudligi buni tasdiqlamaydi.
low, medium, high, xhigh, max va auto mavjud. Sifat tanlovi tasvir shakllantirish rejimini boshqaradi. U kompozitsiya o‘lchamlari va olingan faylning siqish darajasidan farq qiladi.
O‘lcham kvadrat, gorizontal, vertikal, avtomatik tanlangan yoki qo‘lda belgilangan bo‘lishi mumkin. Foydalanuvchi o‘lchamni belgilaganda har bir tomon 16 pikselga karrali va 3840 pikseldan oshmaydi. Maydon 655 360 va 8 294 400 piksel orasida, uzun tomonning qisqa tomonga nisbati esa ko‘pi bilan 3:1 bo‘lishi kerak. Barcha shartlar bir vaqtda qo‘llanadi.
Ishlab chiqaruvchi 2560x1440’dan yuqori aniqliklarni tajribaviy deb belgilaydi. Katta kadr mos kompozitsiya maydonini tanlashga imkon beradi, lekin yozuvlar va obyektlar joylashuvini tekshirishni bekor qilmaydi.
Standart holatda PNG ishlatiladi; JPEG va WebP ham ko‘zda tutilgan. JPEG va WebP’da siqishni boshqarish mumkin. Shaffof fon uchun PNG yoki WebP kerak, chunki JPEG alfa-kanalni saqlamaydi. Shaffoflik bilan birga shaffof bo‘lmagan fon va avtomatik tanlov ko‘zda tutilgan.
O‘lcham, sifat, format va fon natijaning turli tomonlariga javob beradi. Tasvir uslubi sahna mazmuni bilan birga matnli tavsif orqali belgilanadi. Aniq sozlamalarning qo‘llab-quvvatlanishini ishlab chiqaruvchining umumiy imkoniyatlaridan alohida hisobga olish lozim.
OpenAI ma’lumotiga ko‘ra, murakkab topshiriqni qayta ishlash ikki daqiqagacha vaqt olishi mumkin. Bu aniq ilovada natijani olishning to‘liq vaqti kafolati emas, ishlab chiqaruvchidagi yaratish tavsifidir.
Alohida qo‘llab-quvvatlanadigan tahrirlash amalida niqob tanlangan hudud o‘zgarishini yo‘naltiradi. U natijaning chegaraga qat’iy mosligini kafolatlamaydi, shuning uchun tasvirning muayyan qismini aniq tuzatish va’dasi haddan tashqari kuchli bo‘lardi. Bunday rejimni qo‘llash uchun boshlang‘ich materialni yuborishning tegishli usuli kerak.
Yaratishda model matn va tafsilotlarni joylashtirishda ham xato qilishi yoki alohida tasvirlar orasida personaj ko‘rinishini o‘zgartirishi mumkin. Yozuvlar, kompozitsiya va takrorlanuvchanlik nazorati tayyor faylni tekshirishga tegishli. Hatto batafsil topshiriq ham bu xususiyatlarni kafolatlangan qilmaydi.
POST /v1/images/generationstextimage| Maydon | Tur | Talab | Qiymatlar va cheklovlar | Standart |
|---|---|---|---|---|
Maydonmodel | Turstring | TalabMajburiy | Qiymatlar va cheklovlar gpt-image-2.5 | Standart— |
Maydonprompt | Turstring | TalabMajburiy | Qiymatlar va cheklovlar Eng kam uzunlik: 1 | Standart— |
Maydonn | Turinteger | TalabIxtiyoriy | Qiymatlar va cheklovlar Eng kam: 1 | Standart1 |
Maydonresponse_format | Turstring | TalabIxtiyoriy | Qiymatlar va cheklovlar url, b64_json | Standart— |
Maydonstream | Turboolean | TalabIxtiyoriy | Qiymatlar va cheklovlar | Standartfalse |
Maydonsize | Turstring | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydonquality | Turstring | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydonbackground | Turstring | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydonoutput_format | Turstring | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydonoutput_compression | Turinteger | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydonmoderation | Turstring | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydoninput_fidelity | Turstring | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydonstyle | Turstring | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydonpartial_images | Turinteger | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Matndan rasm · Majburiy: prompt
| Parametr | Parametr talablari |
|---|---|
Parametrmaterial_types | Parametr talablaritext |
Parametrrequired | Parametr talablarimodel, prompt |
Parametroptional_controls | Parametr talablarinull |
Parametrcontent_type | Parametr talablariapplication/json |
Hayot sikli: synchronous_result_then_owned_library
GET /v1/media/tasks/{task_id} · Amalda qaytarilgan task_id yoki media kutubxonasidagi yozuv
GET /v1/media/assets/{asset_id}/content
GET /v1/media/assets
GET /v1/media/assets/{asset_id}
Metod tuzilishlari va IDlari aniq; yetkazib beruvchining imkoniyati so‘rovni qabul qilishga ruxsatdan alohida.
POST /v1/images/generationsAiloot so‘rovdan oldin taxminiy summani band qiladi. Natijadan keyin o‘lchangan sarf asosidagi yakuniy to‘lovni yechadi. Oqimli javob bo‘yicha yakuniy hisob-kitob yakuniy sarf yozuviga asoslanadi. Summani band qilish va to‘lovni hisoblash tartibi →
set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\nexport AILOOT_API_KEY\nexport AILOOT_API_KEY\n: "${AILOOT_PROMPT_FILE:?Set your actual UTF-8 image brief}"\nexport AILOOT_PROMPT_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model": "gpt-image-2.5", "prompt": ""}')\nf=Path(os.environ["AILOOT_PROMPT_FILE"])\nif not f.is_file():raise SystemExit("Choose your actual UTF-8 brief")\np['prompt']=f.read_text(encoding="utf-8")\nif not p['prompt'].strip():raise SystemExit("Brief must contain text")\nPath("request.json").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/images/generations \\\n -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport base64, json, os, subprocess\nfrom pathlib import Path\nfrom urllib.parse import urlsplit, urljoin\n\ndef save_images(items):\n if not items: raise SystemExit("No completed images; retain the full response")\n for index, item in enumerate(items):\n encoded=item.get("b64_json")\n uri=item.get("url", "")\n if not encoded and uri.startswith("data:image/"):\n header, separator, encoded=uri.partition(",")\n if not separator or ";base64" not in header: raise SystemExit("Unsupported image data URI")\n if encoded:\n raw=base64.b64decode(encoded,validate=True)\n elif uri:\n uri=urljoin("https://api.ailoot.ai",uri)\n parsed=urlsplit(uri)\n if parsed.scheme!="https" or not parsed.netloc or parsed.username or parsed.password:\n raise SystemExit("Invalid returned image URL")\n owned=parsed.netloc=="api.ailoot.ai" and parsed.path.startswith("/v1/media/assets/") and parsed.path.endswith("/content")\n args=["curl","--fail-with-body","--silent","--show-error",uri]\n if owned: args += ["-H","Authorization: Bearer "+os.environ["AILOOT_API_KEY"]]\n temporary=Path(f"image-{index}.bin")\n subprocess.run(args+["-o",str(temporary)],check=True)\n raw=temporary.read_bytes()\n temporary.unlink()\n else: raise SystemExit("Image has neither bytes nor URL")\n if not raw: raise SystemExit("Empty image result")\n ext="png" if raw.startswith(b"\\x89PNG") else "jpg" if raw.startswith(b"\\xff\\xd8") else "webp" if raw[:4]==b"RIFF" and raw[8:12]==b"WEBP" else "svg" if raw.lstrip().startswith((b"<svg",b"<?xml")) else "bin"\n Path(f"image-{index}.{ext}").write_bytes(raw)\n print("Every returned image saved; complete response metadata retained")\nsave_images(json.loads(Path("result.json").read_text())["data"])\nPY_RESULT\nfrom openai import OpenAI\nimport base64, json, os, subprocess\nfrom pathlib import Path\nfrom urllib.parse import urlsplit, urljoin\n\ndef save_images(items):\n if not items: raise SystemExit("No completed images; retain the full response")\n for index, item in enumerate(items):\n encoded=item.get("b64_json")\n uri=item.get("url", "")\n if not encoded and uri.startswith("data:image/"):\n header, separator, encoded=uri.partition(",")\n if not separator or ";base64" not in header: raise SystemExit("Unsupported image data URI")\n if encoded:\n raw=base64.b64decode(encoded,validate=True)\n elif uri:\n uri=urljoin("https://api.ailoot.ai",uri)\n parsed=urlsplit(uri)\n if parsed.scheme!="https" or not parsed.netloc or parsed.username or parsed.password:\n raise SystemExit("Invalid returned image URL")\n owned=parsed.netloc=="api.ailoot.ai" and parsed.path.startswith("/v1/media/assets/") and parsed.path.endswith("/content")\n args=["curl","--fail-with-body","--silent","--show-error",uri]\n if owned: args += ["-H","Authorization: Bearer "+os.environ["AILOOT_API_KEY"]]\n temporary=Path(f"image-{index}.bin")\n subprocess.run(args+["-o",str(temporary)],check=True)\n raw=temporary.read_bytes()\n temporary.unlink()\n else: raise SystemExit("Image has neither bytes nor URL")\n if not raw: raise SystemExit("Empty image result")\n ext="png" if raw.startswith(b"\\x89PNG") else "jpg" if raw.startswith(b"\\xff\\xd8") else "webp" if raw[:4]==b"RIFF" and raw[8:12]==b"WEBP" else "svg" if raw.lstrip().startswith((b"<svg",b"<?xml")) else "bin"\n Path(f"image-{index}.{ext}").write_bytes(raw)\n print("Every returned image saved; complete response metadata retained")\n\nf=Path(os.environ["AILOOT_PROMPT_FILE"])\nif not f.is_file():raise SystemExit("Set your actual UTF-8 image brief file")\nrequest={'model': 'gpt-image-2.5', 'prompt': ''}\nrequest["prompt"]=f.read_text(encoding="utf-8")\nclient=OpenAI(base_url="https://api.ailoot.ai/v1",api_key=os.environ["AILOOT_API_KEY"],max_retries=0)\nresult=client.images.generate(**request)\nPath("sdk-result.txt").write_text(str(result),encoding="utf-8")\nsave_images([{"b64_json":getattr(item,"b64_json",None),"url":getattr(item,"url",None)} for item in result.data])\nimport OpenAI from "openai";\nimport { readFileSync, writeFileSync } from "node:fs";\nconst key=process.env.AILOOT_API_KEY;\nif(!key) throw new Error("Set your actual Ailoot API key");\nconst client=new OpenAI({baseURL:"https://api.ailoot.ai/v1",apiKey:key,maxRetries:0});\nconst request={"model": "gpt-image-2.5", "prompt": ""};\nif(!process.env.AILOOT_PROMPT_FILE)throw new Error("Set your actual UTF-8 image brief file");\nrequest.prompt=readFileSync(process.env.AILOOT_PROMPT_FILE,"utf8");\nconst result=await client.images.generate(request);\nwriteFileSync("sdk-result.json",JSON.stringify(result,null,2));\nif(!result.data?.length) throw new Error("No completed images");\nfor(let index=0;index<result.data.length;index++) {\n const item=result.data[index];let encoded=item.b64_json,uri=item.url||"",raw;\n if(!encoded && uri.startsWith("data:image/")) {\n const comma=uri.indexOf(",");if(comma<0 || !uri.slice(0,comma).includes(";base64")) throw new Error("Unsupported image data URI");\n encoded=uri.slice(comma+1);\n }\n if(encoded) {\n if(encoded.length%4!==0 || !/^[A-Za-z0-9+/]*={0,2}$/.test(encoded)) throw new Error("Invalid Base64");\n raw=Buffer.from(encoded,"base64");\n } else if(uri) {\n const u=new URL(uri,"https://api.ailoot.ai");\n if(u.protocol!=="https:" || u.username || u.password) throw new Error("Invalid returned URL");\n const owned=u.origin==="https://api.ailoot.ai" && u.pathname.startsWith("/v1/media/assets/") && u.pathname.endsWith("/content");\n const response=await fetch(u,{headers:owned?{Authorization:"Bearer "+key}:{},redirect:"manual"});\n if(!response.ok) throw new Error("Image content download failed: "+response.status);\n raw=Buffer.from(await response.arrayBuffer());\n } else throw new Error("Image has neither bytes nor URL");\n if(!raw.length) throw new Error("Empty image result");\n const ext=raw.subarray(0,4).equals(Buffer.from([137,80,78,71]))?"png":raw[0]===255&&raw[1]===216?"jpg":raw.toString("ascii",0,4)==="RIFF"&&raw.toString("ascii",8,12)==="WEBP"?"webp":raw.toString("utf8").trimStart().startsWith("<svg")||raw.toString("utf8").trimStart().startsWith("<?xml")?"svg":"bin";\n writeFileSync(`image-${index}.${ext}`,raw);\n}\nconsole.log("Every returned image saved; sdk-result.json retains complete metadata");\nHar bir qaytarilgan rasmni yuklab oling yoki uning Base64 kontentini saqlang
GET /v1/media/tasks/{task_id}GET /v1/media/assets/{asset_id}/contentGET /v1/media/assetsGET /v1/media/assets/{asset_id}Har bir tayyor rasmni saqlang; har bir qaytarilgan URL dan kontentni oling yoki uning Base64 kontentini dekodlang.
Har bir ma’lumot elementini saqlang. Har bir b64_json ni dekodlang yoki qaytarilgan har bir imzolangan URL dan faylni yuklab oling. Fayl nomi kengaytmasini haqiqiy MIME turi/baytlar asosida tanlang.
Rasm yaratish yoki tahrirlash natijasini tekshirish kerak bo‘lsa, dastlabki operation_id/X-Client-Request-ID va qaytarilgan natija haqidagi ma’lumotlarni saqlang. Amalda qaytarilgan task_id yoki asset_id qiymatlari yordamida media kutubxonasidan o‘zingizga tegishli mavjud natijalarni tiklang. Rasm yaratish/tahrirlash so‘rovini qayta yubormang va operation_id dan holatni davriy tekshirish uchun URL tuzmang.
| Maydon | Tur |
|---|---|
Maydoncreated | Turinteger |
Maydondata[].url | Turstring |
Maydondata[].b64_json | Turbase64 string |
Maydonusage | Turobject |
| Javob | Shart | Keyingi qadam |
|---|---|---|
Javob400 · invalid_request_error | ShartMajburiy maydonlar, material ifodasi yoki parametr qiymati noto‘g‘ri | Keyingi qadamYangi yaratish so‘rovidan oldin ko‘rsatilgan maydonlarni tuzating. |
Javobserver_error | ShartQaytarilgan javob operatsiya yoki natijani tekshirish kerakligini bildiradi | Keyingi qadamDastlab qaytarilgan operatsiya/vazifa ID sini, so‘rov sarlavhalarini va javobni saqlang; aynan shu operatsiya uchun qo‘llab-quvvatlanadigan o‘qish so‘rovlarini davom ettiring. Yaratish so‘rovini qayta yubormang. |
Ailoot gpt-image-2.5-sunburst, gpt-image, gpt-image-2.5, gpt-image-2.5-latest, gpt-image-latest
Yuqorida ko‘rsatilgan usul yo‘llaridan foydalaning.
gpt-image-2.5-sunburst, gpt-image, gpt-image-2.5, gpt-image-2.5-latest, gpt-image-latest
gpt-image-2.5-latestGPT Image 2.5 Sunburst matnli topshiriq asosida tasvirlar yaratadi. Foydalanuvchi belgilaydigan o‘lchamlar, kengaytirilgan sifat darajalari va shaffof fonni qo‘llab-quvvatlaydi; ishlab chiqaruvchi tahrirlash aniqligini ham ta’kidlaydi.
Bu tavsif model imkoniyatlarini yoritadi. Ailoot da tanlangan usul uchun mavjud kirish, chiqish va parametrlar quyida keltirilgan.
GPT Image 2.5 Sunburst — tasvirlar yaratish uchun OpenAI modeli. Ishlab chiqaruvchi boshlang‘ich materiallarni tahrirlash aniqligiga alohida e’tibor beradi. Model matnli topshiriqlarni va buning uchun ko‘zda tutilgan amallarda vizual boshlang‘ich materiallarni qo‘llab-quvvatlaydi.
Joriy Ailoot kartasida matndan tasvir yaratish rejimi taqdim etilgan. Kelajakdagi natijaning sahnasi, kompozitsiyasi, uslubi va tafsilotlarini belgilash mumkin. OpenAI tavsiflagan namunalar bilan ishlash, tahrirlash va niqob bo‘yicha hududni o‘zgartirish usullari kiruvchi tasvirlarni alohida qo‘llab-quvvatlashni talab qiladi; matnli yaratish mavjudligi buni tasdiqlamaydi.
low, medium, high, xhigh, max va auto mavjud. Sifat tanlovi tasvir shakllantirish rejimini boshqaradi. U kompozitsiya o‘lchamlari va olingan faylning siqish darajasidan farq qiladi.
O‘lcham kvadrat, gorizontal, vertikal, avtomatik tanlangan yoki qo‘lda belgilangan bo‘lishi mumkin. Foydalanuvchi o‘lchamni belgilaganda har bir tomon 16 pikselga karrali va 3840 pikseldan oshmaydi. Maydon 655 360 va 8 294 400 piksel orasida, uzun tomonning qisqa tomonga nisbati esa ko‘pi bilan 3:1 bo‘lishi kerak. Barcha shartlar bir vaqtda qo‘llanadi.
Ishlab chiqaruvchi 2560x1440’dan yuqori aniqliklarni tajribaviy deb belgilaydi. Katta kadr mos kompozitsiya maydonini tanlashga imkon beradi, lekin yozuvlar va obyektlar joylashuvini tekshirishni bekor qilmaydi.
Standart holatda PNG ishlatiladi; JPEG va WebP ham ko‘zda tutilgan. JPEG va WebP’da siqishni boshqarish mumkin. Shaffof fon uchun PNG yoki WebP kerak, chunki JPEG alfa-kanalni saqlamaydi. Shaffoflik bilan birga shaffof bo‘lmagan fon va avtomatik tanlov ko‘zda tutilgan.
O‘lcham, sifat, format va fon natijaning turli tomonlariga javob beradi. Tasvir uslubi sahna mazmuni bilan birga matnli tavsif orqali belgilanadi. Aniq sozlamalarning qo‘llab-quvvatlanishini ishlab chiqaruvchining umumiy imkoniyatlaridan alohida hisobga olish lozim.
OpenAI ma’lumotiga ko‘ra, murakkab topshiriqni qayta ishlash ikki daqiqagacha vaqt olishi mumkin. Bu aniq ilovada natijani olishning to‘liq vaqti kafolati emas, ishlab chiqaruvchidagi yaratish tavsifidir.
Alohida qo‘llab-quvvatlanadigan tahrirlash amalida niqob tanlangan hudud o‘zgarishini yo‘naltiradi. U natijaning chegaraga qat’iy mosligini kafolatlamaydi, shuning uchun tasvirning muayyan qismini aniq tuzatish va’dasi haddan tashqari kuchli bo‘lardi. Bunday rejimni qo‘llash uchun boshlang‘ich materialni yuborishning tegishli usuli kerak.
Yaratishda model matn va tafsilotlarni joylashtirishda ham xato qilishi yoki alohida tasvirlar orasida personaj ko‘rinishini o‘zgartirishi mumkin. Yozuvlar, kompozitsiya va takrorlanuvchanlik nazorati tayyor faylni tekshirishga tegishli. Hatto batafsil topshiriq ham bu xususiyatlarni kafolatlangan qilmaydi.
POST /v1/images/generationstextimage| Maydon | Tur | Talab | Qiymatlar va cheklovlar | Standart |
|---|---|---|---|---|
Maydonmodel | Turstring | TalabMajburiy | Qiymatlar va cheklovlar gpt-image-2.5-latest | Standart— |
Maydonprompt | Turstring | TalabMajburiy | Qiymatlar va cheklovlar Eng kam uzunlik: 1 | Standart— |
Maydonn | Turinteger | TalabIxtiyoriy | Qiymatlar va cheklovlar Eng kam: 1 | Standart1 |
Maydonresponse_format | Turstring | TalabIxtiyoriy | Qiymatlar va cheklovlar url, b64_json | Standart— |
Maydonstream | Turboolean | TalabIxtiyoriy | Qiymatlar va cheklovlar | Standartfalse |
Maydonsize | Turstring | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydonquality | Turstring | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydonbackground | Turstring | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydonoutput_format | Turstring | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydonoutput_compression | Turinteger | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydonmoderation | Turstring | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydoninput_fidelity | Turstring | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydonstyle | Turstring | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydonpartial_images | Turinteger | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Matndan rasm · Majburiy: prompt
| Parametr | Parametr talablari |
|---|---|
Parametrmaterial_types | Parametr talablaritext |
Parametrrequired | Parametr talablarimodel, prompt |
Parametroptional_controls | Parametr talablarinull |
Parametrcontent_type | Parametr talablariapplication/json |
Hayot sikli: synchronous_result_then_owned_library
GET /v1/media/tasks/{task_id} · Amalda qaytarilgan task_id yoki media kutubxonasidagi yozuv
GET /v1/media/assets/{asset_id}/content
GET /v1/media/assets
GET /v1/media/assets/{asset_id}
Metod tuzilishlari va IDlari aniq; yetkazib beruvchining imkoniyati so‘rovni qabul qilishga ruxsatdan alohida.
POST /v1/images/generationsAiloot so‘rovdan oldin taxminiy summani band qiladi. Natijadan keyin o‘lchangan sarf asosidagi yakuniy to‘lovni yechadi. Oqimli javob bo‘yicha yakuniy hisob-kitob yakuniy sarf yozuviga asoslanadi. Summani band qilish va to‘lovni hisoblash tartibi →
set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\nexport AILOOT_API_KEY\nexport AILOOT_API_KEY\n: "${AILOOT_PROMPT_FILE:?Set your actual UTF-8 image brief}"\nexport AILOOT_PROMPT_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model": "gpt-image-2.5-latest", "prompt": ""}')\nf=Path(os.environ["AILOOT_PROMPT_FILE"])\nif not f.is_file():raise SystemExit("Choose your actual UTF-8 brief")\np['prompt']=f.read_text(encoding="utf-8")\nif not p['prompt'].strip():raise SystemExit("Brief must contain text")\nPath("request.json").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/images/generations \\\n -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport base64, json, os, subprocess\nfrom pathlib import Path\nfrom urllib.parse import urlsplit, urljoin\n\ndef save_images(items):\n if not items: raise SystemExit("No completed images; retain the full response")\n for index, item in enumerate(items):\n encoded=item.get("b64_json")\n uri=item.get("url", "")\n if not encoded and uri.startswith("data:image/"):\n header, separator, encoded=uri.partition(",")\n if not separator or ";base64" not in header: raise SystemExit("Unsupported image data URI")\n if encoded:\n raw=base64.b64decode(encoded,validate=True)\n elif uri:\n uri=urljoin("https://api.ailoot.ai",uri)\n parsed=urlsplit(uri)\n if parsed.scheme!="https" or not parsed.netloc or parsed.username or parsed.password:\n raise SystemExit("Invalid returned image URL")\n owned=parsed.netloc=="api.ailoot.ai" and parsed.path.startswith("/v1/media/assets/") and parsed.path.endswith("/content")\n args=["curl","--fail-with-body","--silent","--show-error",uri]\n if owned: args += ["-H","Authorization: Bearer "+os.environ["AILOOT_API_KEY"]]\n temporary=Path(f"image-{index}.bin")\n subprocess.run(args+["-o",str(temporary)],check=True)\n raw=temporary.read_bytes()\n temporary.unlink()\n else: raise SystemExit("Image has neither bytes nor URL")\n if not raw: raise SystemExit("Empty image result")\n ext="png" if raw.startswith(b"\\x89PNG") else "jpg" if raw.startswith(b"\\xff\\xd8") else "webp" if raw[:4]==b"RIFF" and raw[8:12]==b"WEBP" else "svg" if raw.lstrip().startswith((b"<svg",b"<?xml")) else "bin"\n Path(f"image-{index}.{ext}").write_bytes(raw)\n print("Every returned image saved; complete response metadata retained")\nsave_images(json.loads(Path("result.json").read_text())["data"])\nPY_RESULT\nfrom openai import OpenAI\nimport base64, json, os, subprocess\nfrom pathlib import Path\nfrom urllib.parse import urlsplit, urljoin\n\ndef save_images(items):\n if not items: raise SystemExit("No completed images; retain the full response")\n for index, item in enumerate(items):\n encoded=item.get("b64_json")\n uri=item.get("url", "")\n if not encoded and uri.startswith("data:image/"):\n header, separator, encoded=uri.partition(",")\n if not separator or ";base64" not in header: raise SystemExit("Unsupported image data URI")\n if encoded:\n raw=base64.b64decode(encoded,validate=True)\n elif uri:\n uri=urljoin("https://api.ailoot.ai",uri)\n parsed=urlsplit(uri)\n if parsed.scheme!="https" or not parsed.netloc or parsed.username or parsed.password:\n raise SystemExit("Invalid returned image URL")\n owned=parsed.netloc=="api.ailoot.ai" and parsed.path.startswith("/v1/media/assets/") and parsed.path.endswith("/content")\n args=["curl","--fail-with-body","--silent","--show-error",uri]\n if owned: args += ["-H","Authorization: Bearer "+os.environ["AILOOT_API_KEY"]]\n temporary=Path(f"image-{index}.bin")\n subprocess.run(args+["-o",str(temporary)],check=True)\n raw=temporary.read_bytes()\n temporary.unlink()\n else: raise SystemExit("Image has neither bytes nor URL")\n if not raw: raise SystemExit("Empty image result")\n ext="png" if raw.startswith(b"\\x89PNG") else "jpg" if raw.startswith(b"\\xff\\xd8") else "webp" if raw[:4]==b"RIFF" and raw[8:12]==b"WEBP" else "svg" if raw.lstrip().startswith((b"<svg",b"<?xml")) else "bin"\n Path(f"image-{index}.{ext}").write_bytes(raw)\n print("Every returned image saved; complete response metadata retained")\n\nf=Path(os.environ["AILOOT_PROMPT_FILE"])\nif not f.is_file():raise SystemExit("Set your actual UTF-8 image brief file")\nrequest={'model': 'gpt-image-2.5-latest', 'prompt': ''}\nrequest["prompt"]=f.read_text(encoding="utf-8")\nclient=OpenAI(base_url="https://api.ailoot.ai/v1",api_key=os.environ["AILOOT_API_KEY"],max_retries=0)\nresult=client.images.generate(**request)\nPath("sdk-result.txt").write_text(str(result),encoding="utf-8")\nsave_images([{"b64_json":getattr(item,"b64_json",None),"url":getattr(item,"url",None)} for item in result.data])\nimport OpenAI from "openai";\nimport { readFileSync, writeFileSync } from "node:fs";\nconst key=process.env.AILOOT_API_KEY;\nif(!key) throw new Error("Set your actual Ailoot API key");\nconst client=new OpenAI({baseURL:"https://api.ailoot.ai/v1",apiKey:key,maxRetries:0});\nconst request={"model": "gpt-image-2.5-latest", "prompt": ""};\nif(!process.env.AILOOT_PROMPT_FILE)throw new Error("Set your actual UTF-8 image brief file");\nrequest.prompt=readFileSync(process.env.AILOOT_PROMPT_FILE,"utf8");\nconst result=await client.images.generate(request);\nwriteFileSync("sdk-result.json",JSON.stringify(result,null,2));\nif(!result.data?.length) throw new Error("No completed images");\nfor(let index=0;index<result.data.length;index++) {\n const item=result.data[index];let encoded=item.b64_json,uri=item.url||"",raw;\n if(!encoded && uri.startsWith("data:image/")) {\n const comma=uri.indexOf(",");if(comma<0 || !uri.slice(0,comma).includes(";base64")) throw new Error("Unsupported image data URI");\n encoded=uri.slice(comma+1);\n }\n if(encoded) {\n if(encoded.length%4!==0 || !/^[A-Za-z0-9+/]*={0,2}$/.test(encoded)) throw new Error("Invalid Base64");\n raw=Buffer.from(encoded,"base64");\n } else if(uri) {\n const u=new URL(uri,"https://api.ailoot.ai");\n if(u.protocol!=="https:" || u.username || u.password) throw new Error("Invalid returned URL");\n const owned=u.origin==="https://api.ailoot.ai" && u.pathname.startsWith("/v1/media/assets/") && u.pathname.endsWith("/content");\n const response=await fetch(u,{headers:owned?{Authorization:"Bearer "+key}:{},redirect:"manual"});\n if(!response.ok) throw new Error("Image content download failed: "+response.status);\n raw=Buffer.from(await response.arrayBuffer());\n } else throw new Error("Image has neither bytes nor URL");\n if(!raw.length) throw new Error("Empty image result");\n const ext=raw.subarray(0,4).equals(Buffer.from([137,80,78,71]))?"png":raw[0]===255&&raw[1]===216?"jpg":raw.toString("ascii",0,4)==="RIFF"&&raw.toString("ascii",8,12)==="WEBP"?"webp":raw.toString("utf8").trimStart().startsWith("<svg")||raw.toString("utf8").trimStart().startsWith("<?xml")?"svg":"bin";\n writeFileSync(`image-${index}.${ext}`,raw);\n}\nconsole.log("Every returned image saved; sdk-result.json retains complete metadata");\nHar bir qaytarilgan rasmni yuklab oling yoki uning Base64 kontentini saqlang
GET /v1/media/tasks/{task_id}GET /v1/media/assets/{asset_id}/contentGET /v1/media/assetsGET /v1/media/assets/{asset_id}Har bir tayyor rasmni saqlang; har bir qaytarilgan URL dan kontentni oling yoki uning Base64 kontentini dekodlang.
Har bir ma’lumot elementini saqlang. Har bir b64_json ni dekodlang yoki qaytarilgan har bir imzolangan URL dan faylni yuklab oling. Fayl nomi kengaytmasini haqiqiy MIME turi/baytlar asosida tanlang.
Rasm yaratish yoki tahrirlash natijasini tekshirish kerak bo‘lsa, dastlabki operation_id/X-Client-Request-ID va qaytarilgan natija haqidagi ma’lumotlarni saqlang. Amalda qaytarilgan task_id yoki asset_id qiymatlari yordamida media kutubxonasidan o‘zingizga tegishli mavjud natijalarni tiklang. Rasm yaratish/tahrirlash so‘rovini qayta yubormang va operation_id dan holatni davriy tekshirish uchun URL tuzmang.
| Maydon | Tur |
|---|---|
Maydoncreated | Turinteger |
Maydondata[].url | Turstring |
Maydondata[].b64_json | Turbase64 string |
Maydonusage | Turobject |
| Javob | Shart | Keyingi qadam |
|---|---|---|
Javob400 · invalid_request_error | ShartMajburiy maydonlar, material ifodasi yoki parametr qiymati noto‘g‘ri | Keyingi qadamYangi yaratish so‘rovidan oldin ko‘rsatilgan maydonlarni tuzating. |
Javobserver_error | ShartQaytarilgan javob operatsiya yoki natijani tekshirish kerakligini bildiradi | Keyingi qadamDastlab qaytarilgan operatsiya/vazifa ID sini, so‘rov sarlavhalarini va javobni saqlang; aynan shu operatsiya uchun qo‘llab-quvvatlanadigan o‘qish so‘rovlarini davom ettiring. Yaratish so‘rovini qayta yubormang. |
Ailoot gpt-image-2.5-sunburst, gpt-image, gpt-image-2.5, gpt-image-2.5-latest, gpt-image-latest
Yuqorida ko‘rsatilgan usul yo‘llaridan foydalaning.
gpt-image-2.5-sunburst, gpt-image, gpt-image-2.5, gpt-image-2.5-latest, gpt-image-latest
gpt-image-latestGPT Image 2.5 Sunburst matnli topshiriq asosida tasvirlar yaratadi. Foydalanuvchi belgilaydigan o‘lchamlar, kengaytirilgan sifat darajalari va shaffof fonni qo‘llab-quvvatlaydi; ishlab chiqaruvchi tahrirlash aniqligini ham ta’kidlaydi.
Bu tavsif model imkoniyatlarini yoritadi. Ailoot da tanlangan usul uchun mavjud kirish, chiqish va parametrlar quyida keltirilgan.
GPT Image 2.5 Sunburst — tasvirlar yaratish uchun OpenAI modeli. Ishlab chiqaruvchi boshlang‘ich materiallarni tahrirlash aniqligiga alohida e’tibor beradi. Model matnli topshiriqlarni va buning uchun ko‘zda tutilgan amallarda vizual boshlang‘ich materiallarni qo‘llab-quvvatlaydi.
Joriy Ailoot kartasida matndan tasvir yaratish rejimi taqdim etilgan. Kelajakdagi natijaning sahnasi, kompozitsiyasi, uslubi va tafsilotlarini belgilash mumkin. OpenAI tavsiflagan namunalar bilan ishlash, tahrirlash va niqob bo‘yicha hududni o‘zgartirish usullari kiruvchi tasvirlarni alohida qo‘llab-quvvatlashni talab qiladi; matnli yaratish mavjudligi buni tasdiqlamaydi.
low, medium, high, xhigh, max va auto mavjud. Sifat tanlovi tasvir shakllantirish rejimini boshqaradi. U kompozitsiya o‘lchamlari va olingan faylning siqish darajasidan farq qiladi.
O‘lcham kvadrat, gorizontal, vertikal, avtomatik tanlangan yoki qo‘lda belgilangan bo‘lishi mumkin. Foydalanuvchi o‘lchamni belgilaganda har bir tomon 16 pikselga karrali va 3840 pikseldan oshmaydi. Maydon 655 360 va 8 294 400 piksel orasida, uzun tomonning qisqa tomonga nisbati esa ko‘pi bilan 3:1 bo‘lishi kerak. Barcha shartlar bir vaqtda qo‘llanadi.
Ishlab chiqaruvchi 2560x1440’dan yuqori aniqliklarni tajribaviy deb belgilaydi. Katta kadr mos kompozitsiya maydonini tanlashga imkon beradi, lekin yozuvlar va obyektlar joylashuvini tekshirishni bekor qilmaydi.
Standart holatda PNG ishlatiladi; JPEG va WebP ham ko‘zda tutilgan. JPEG va WebP’da siqishni boshqarish mumkin. Shaffof fon uchun PNG yoki WebP kerak, chunki JPEG alfa-kanalni saqlamaydi. Shaffoflik bilan birga shaffof bo‘lmagan fon va avtomatik tanlov ko‘zda tutilgan.
O‘lcham, sifat, format va fon natijaning turli tomonlariga javob beradi. Tasvir uslubi sahna mazmuni bilan birga matnli tavsif orqali belgilanadi. Aniq sozlamalarning qo‘llab-quvvatlanishini ishlab chiqaruvchining umumiy imkoniyatlaridan alohida hisobga olish lozim.
OpenAI ma’lumotiga ko‘ra, murakkab topshiriqni qayta ishlash ikki daqiqagacha vaqt olishi mumkin. Bu aniq ilovada natijani olishning to‘liq vaqti kafolati emas, ishlab chiqaruvchidagi yaratish tavsifidir.
Alohida qo‘llab-quvvatlanadigan tahrirlash amalida niqob tanlangan hudud o‘zgarishini yo‘naltiradi. U natijaning chegaraga qat’iy mosligini kafolatlamaydi, shuning uchun tasvirning muayyan qismini aniq tuzatish va’dasi haddan tashqari kuchli bo‘lardi. Bunday rejimni qo‘llash uchun boshlang‘ich materialni yuborishning tegishli usuli kerak.
Yaratishda model matn va tafsilotlarni joylashtirishda ham xato qilishi yoki alohida tasvirlar orasida personaj ko‘rinishini o‘zgartirishi mumkin. Yozuvlar, kompozitsiya va takrorlanuvchanlik nazorati tayyor faylni tekshirishga tegishli. Hatto batafsil topshiriq ham bu xususiyatlarni kafolatlangan qilmaydi.
POST /v1/images/generationstextimage| Maydon | Tur | Talab | Qiymatlar va cheklovlar | Standart |
|---|---|---|---|---|
Maydonmodel | Turstring | TalabMajburiy | Qiymatlar va cheklovlar gpt-image-latest | Standart— |
Maydonprompt | Turstring | TalabMajburiy | Qiymatlar va cheklovlar Eng kam uzunlik: 1 | Standart— |
Maydonn | Turinteger | TalabIxtiyoriy | Qiymatlar va cheklovlar Eng kam: 1 | Standart1 |
Maydonresponse_format | Turstring | TalabIxtiyoriy | Qiymatlar va cheklovlar url, b64_json | Standart— |
Maydonstream | Turboolean | TalabIxtiyoriy | Qiymatlar va cheklovlar | Standartfalse |
Maydonsize | Turstring | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydonquality | Turstring | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydonbackground | Turstring | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydonoutput_format | Turstring | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydonoutput_compression | Turinteger | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydonmoderation | Turstring | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydoninput_fidelity | Turstring | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydonstyle | Turstring | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Maydonpartial_images | Turinteger | TalabIxtiyoriy | Qiymatlar va cheklovlar Modelga bogʻliq | Standart— |
Matndan rasm · Majburiy: prompt
| Parametr | Parametr talablari |
|---|---|
Parametrmaterial_types | Parametr talablaritext |
Parametrrequired | Parametr talablarimodel, prompt |
Parametroptional_controls | Parametr talablarinull |
Parametrcontent_type | Parametr talablariapplication/json |
Hayot sikli: synchronous_result_then_owned_library
GET /v1/media/tasks/{task_id} · Amalda qaytarilgan task_id yoki media kutubxonasidagi yozuv
GET /v1/media/assets/{asset_id}/content
GET /v1/media/assets
GET /v1/media/assets/{asset_id}
Metod tuzilishlari va IDlari aniq; yetkazib beruvchining imkoniyati so‘rovni qabul qilishga ruxsatdan alohida.
POST /v1/images/generationsAiloot so‘rovdan oldin taxminiy summani band qiladi. Natijadan keyin o‘lchangan sarf asosidagi yakuniy to‘lovni yechadi. Oqimli javob bo‘yicha yakuniy hisob-kitob yakuniy sarf yozuviga asoslanadi. Summani band qilish va to‘lovni hisoblash tartibi →
set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\nexport AILOOT_API_KEY\nexport AILOOT_API_KEY\n: "${AILOOT_PROMPT_FILE:?Set your actual UTF-8 image brief}"\nexport AILOOT_PROMPT_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model": "gpt-image-latest", "prompt": ""}')\nf=Path(os.environ["AILOOT_PROMPT_FILE"])\nif not f.is_file():raise SystemExit("Choose your actual UTF-8 brief")\np['prompt']=f.read_text(encoding="utf-8")\nif not p['prompt'].strip():raise SystemExit("Brief must contain text")\nPath("request.json").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/images/generations \\\n -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport base64, json, os, subprocess\nfrom pathlib import Path\nfrom urllib.parse import urlsplit, urljoin\n\ndef save_images(items):\n if not items: raise SystemExit("No completed images; retain the full response")\n for index, item in enumerate(items):\n encoded=item.get("b64_json")\n uri=item.get("url", "")\n if not encoded and uri.startswith("data:image/"):\n header, separator, encoded=uri.partition(",")\n if not separator or ";base64" not in header: raise SystemExit("Unsupported image data URI")\n if encoded:\n raw=base64.b64decode(encoded,validate=True)\n elif uri:\n uri=urljoin("https://api.ailoot.ai",uri)\n parsed=urlsplit(uri)\n if parsed.scheme!="https" or not parsed.netloc or parsed.username or parsed.password:\n raise SystemExit("Invalid returned image URL")\n owned=parsed.netloc=="api.ailoot.ai" and parsed.path.startswith("/v1/media/assets/") and parsed.path.endswith("/content")\n args=["curl","--fail-with-body","--silent","--show-error",uri]\n if owned: args += ["-H","Authorization: Bearer "+os.environ["AILOOT_API_KEY"]]\n temporary=Path(f"image-{index}.bin")\n subprocess.run(args+["-o",str(temporary)],check=True)\n raw=temporary.read_bytes()\n temporary.unlink()\n else: raise SystemExit("Image has neither bytes nor URL")\n if not raw: raise SystemExit("Empty image result")\n ext="png" if raw.startswith(b"\\x89PNG") else "jpg" if raw.startswith(b"\\xff\\xd8") else "webp" if raw[:4]==b"RIFF" and raw[8:12]==b"WEBP" else "svg" if raw.lstrip().startswith((b"<svg",b"<?xml")) else "bin"\n Path(f"image-{index}.{ext}").write_bytes(raw)\n print("Every returned image saved; complete response metadata retained")\nsave_images(json.loads(Path("result.json").read_text())["data"])\nPY_RESULT\nfrom openai import OpenAI\nimport base64, json, os, subprocess\nfrom pathlib import Path\nfrom urllib.parse import urlsplit, urljoin\n\ndef save_images(items):\n if not items: raise SystemExit("No completed images; retain the full response")\n for index, item in enumerate(items):\n encoded=item.get("b64_json")\n uri=item.get("url", "")\n if not encoded and uri.startswith("data:image/"):\n header, separator, encoded=uri.partition(",")\n if not separator or ";base64" not in header: raise SystemExit("Unsupported image data URI")\n if encoded:\n raw=base64.b64decode(encoded,validate=True)\n elif uri:\n uri=urljoin("https://api.ailoot.ai",uri)\n parsed=urlsplit(uri)\n if parsed.scheme!="https" or not parsed.netloc or parsed.username or parsed.password:\n raise SystemExit("Invalid returned image URL")\n owned=parsed.netloc=="api.ailoot.ai" and parsed.path.startswith("/v1/media/assets/") and parsed.path.endswith("/content")\n args=["curl","--fail-with-body","--silent","--show-error",uri]\n if owned: args += ["-H","Authorization: Bearer "+os.environ["AILOOT_API_KEY"]]\n temporary=Path(f"image-{index}.bin")\n subprocess.run(args+["-o",str(temporary)],check=True)\n raw=temporary.read_bytes()\n temporary.unlink()\n else: raise SystemExit("Image has neither bytes nor URL")\n if not raw: raise SystemExit("Empty image result")\n ext="png" if raw.startswith(b"\\x89PNG") else "jpg" if raw.startswith(b"\\xff\\xd8") else "webp" if raw[:4]==b"RIFF" and raw[8:12]==b"WEBP" else "svg" if raw.lstrip().startswith((b"<svg",b"<?xml")) else "bin"\n Path(f"image-{index}.{ext}").write_bytes(raw)\n print("Every returned image saved; complete response metadata retained")\n\nf=Path(os.environ["AILOOT_PROMPT_FILE"])\nif not f.is_file():raise SystemExit("Set your actual UTF-8 image brief file")\nrequest={'model': 'gpt-image-latest', 'prompt': ''}\nrequest["prompt"]=f.read_text(encoding="utf-8")\nclient=OpenAI(base_url="https://api.ailoot.ai/v1",api_key=os.environ["AILOOT_API_KEY"],max_retries=0)\nresult=client.images.generate(**request)\nPath("sdk-result.txt").write_text(str(result),encoding="utf-8")\nsave_images([{"b64_json":getattr(item,"b64_json",None),"url":getattr(item,"url",None)} for item in result.data])\nimport OpenAI from "openai";\nimport { readFileSync, writeFileSync } from "node:fs";\nconst key=process.env.AILOOT_API_KEY;\nif(!key) throw new Error("Set your actual Ailoot API key");\nconst client=new OpenAI({baseURL:"https://api.ailoot.ai/v1",apiKey:key,maxRetries:0});\nconst request={"model": "gpt-image-latest", "prompt": ""};\nif(!process.env.AILOOT_PROMPT_FILE)throw new Error("Set your actual UTF-8 image brief file");\nrequest.prompt=readFileSync(process.env.AILOOT_PROMPT_FILE,"utf8");\nconst result=await client.images.generate(request);\nwriteFileSync("sdk-result.json",JSON.stringify(result,null,2));\nif(!result.data?.length) throw new Error("No completed images");\nfor(let index=0;index<result.data.length;index++) {\n const item=result.data[index];let encoded=item.b64_json,uri=item.url||"",raw;\n if(!encoded && uri.startsWith("data:image/")) {\n const comma=uri.indexOf(",");if(comma<0 || !uri.slice(0,comma).includes(";base64")) throw new Error("Unsupported image data URI");\n encoded=uri.slice(comma+1);\n }\n if(encoded) {\n if(encoded.length%4!==0 || !/^[A-Za-z0-9+/]*={0,2}$/.test(encoded)) throw new Error("Invalid Base64");\n raw=Buffer.from(encoded,"base64");\n } else if(uri) {\n const u=new URL(uri,"https://api.ailoot.ai");\n if(u.protocol!=="https:" || u.username || u.password) throw new Error("Invalid returned URL");\n const owned=u.origin==="https://api.ailoot.ai" && u.pathname.startsWith("/v1/media/assets/") && u.pathname.endsWith("/content");\n const response=await fetch(u,{headers:owned?{Authorization:"Bearer "+key}:{},redirect:"manual"});\n if(!response.ok) throw new Error("Image content download failed: "+response.status);\n raw=Buffer.from(await response.arrayBuffer());\n } else throw new Error("Image has neither bytes nor URL");\n if(!raw.length) throw new Error("Empty image result");\n const ext=raw.subarray(0,4).equals(Buffer.from([137,80,78,71]))?"png":raw[0]===255&&raw[1]===216?"jpg":raw.toString("ascii",0,4)==="RIFF"&&raw.toString("ascii",8,12)==="WEBP"?"webp":raw.toString("utf8").trimStart().startsWith("<svg")||raw.toString("utf8").trimStart().startsWith("<?xml")?"svg":"bin";\n writeFileSync(`image-${index}.${ext}`,raw);\n}\nconsole.log("Every returned image saved; sdk-result.json retains complete metadata");\nHar bir qaytarilgan rasmni yuklab oling yoki uning Base64 kontentini saqlang
GET /v1/media/tasks/{task_id}GET /v1/media/assets/{asset_id}/contentGET /v1/media/assetsGET /v1/media/assets/{asset_id}Har bir tayyor rasmni saqlang; har bir qaytarilgan URL dan kontentni oling yoki uning Base64 kontentini dekodlang.
Har bir ma’lumot elementini saqlang. Har bir b64_json ni dekodlang yoki qaytarilgan har bir imzolangan URL dan faylni yuklab oling. Fayl nomi kengaytmasini haqiqiy MIME turi/baytlar asosida tanlang.
Rasm yaratish yoki tahrirlash natijasini tekshirish kerak bo‘lsa, dastlabki operation_id/X-Client-Request-ID va qaytarilgan natija haqidagi ma’lumotlarni saqlang. Amalda qaytarilgan task_id yoki asset_id qiymatlari yordamida media kutubxonasidan o‘zingizga tegishli mavjud natijalarni tiklang. Rasm yaratish/tahrirlash so‘rovini qayta yubormang va operation_id dan holatni davriy tekshirish uchun URL tuzmang.
| Maydon | Tur |
|---|---|
Maydoncreated | Turinteger |
Maydondata[].url | Turstring |
Maydondata[].b64_json | Turbase64 string |
Maydonusage | Turobject |
| Javob | Shart | Keyingi qadam |
|---|---|---|
Javob400 · invalid_request_error | ShartMajburiy maydonlar, material ifodasi yoki parametr qiymati noto‘g‘ri | Keyingi qadamYangi yaratish so‘rovidan oldin ko‘rsatilgan maydonlarni tuzating. |
Javobserver_error | ShartQaytarilgan javob operatsiya yoki natijani tekshirish kerakligini bildiradi | Keyingi qadamDastlab qaytarilgan operatsiya/vazifa ID sini, so‘rov sarlavhalarini va javobni saqlang; aynan shu operatsiya uchun qo‘llab-quvvatlanadigan o‘qish so‘rovlarini davom ettiring. Yaratish so‘rovini qayta yubormang. |
Ailoot gpt-image-2.5-sunburst, gpt-image, gpt-image-2.5, gpt-image-2.5-latest, gpt-image-latest
Yuqorida ko‘rsatilgan usul yo‘llaridan foydalaning.
gpt-image-2.5-sunburst, gpt-image, gpt-image-2.5, gpt-image-2.5-latest, gpt-image-latest