studioglobal
인기 있는 발견
보고서게시됨9 소스

GPT Image 2와 GPT Image 1.5, 이미지 속 글자 가독성 판정

GPT Image 2는 텍스트가 많은 이미지 작업의 기본 선택지로 더 설득력 있다. OpenAI 관련 자료가 읽기 쉬운, 현지화된, 제작용 이미지 흐름을 강조하기 때문이다 [32][77]. GPT Image 1.5도 이미 조밀하고 작은 글자 렌더링 개선을 내세운 모델이었다.

15K0
Side-by-side editorial illustration comparing readable text rendering in GPT Image 2 and GPT Image 1.5
GPT Image 2 vs GPT Image 1.5: Which Renders Readable Text BetterAI-generated editorial illustration for a comparison of GPT Image 2 and GPT Image 1.5 text rendering.
AI 프롬프트

Create a landscape editorial hero image for this Studio Global article: GPT Image 2 vs GPT Image 1.5: Which Renders Readable Text Better?. Article summary: GPT Image 2 is the better practical default for readable text in images, especially dense or multilingual assets; the caveat is that public sources reviewed here do not include a transparent head to head benchmark aga.... Topic tags: ai, openai, chatgpt, image generation, text to image. Reference image context from search candidates: Reference image 1: visual subject "ChatGPT Image 2.0 vs GPT Image 1.5: Which AI Image Generator Should You Use? Compare ChatGPT Image 2.0 and GPT Image 1.5 across text rendering, speed, 4K quality, world understandi" source context "ChatGPT Image 2.0 vs GPT Image 1.5: Full Feature Comparison" Reference image 2: visual subject "# GPT Image Family. Compare GPT Image 2, GPT Image 1.5, and GPT Image 1 in one

openai.com

AI 이미지에서 글자는 장식이 아니라 기능입니다. 포스터 제목, 발표 슬라이드의 표, 앱 화면의 버튼, 제품 라벨, 인포그래픽 주석, 현지화 광고 문구가 틀리면 이미지는 그럴듯해 보여도 바로 쓰기 어렵습니다.

현재 확인 가능한 자료만 놓고 보면, 글자가 많이 들어가는 이미지 생성은 GPT Image 2를 먼저 시도하는 편이 합리적입니다. 다만 이 결론은 정확히 읽어야 합니다. 공개된 자료 안에서 ‘GPT Image 2가 GPT Image 1.5보다 몇 퍼센트 더 낫다’고 말할 수 있는 투명한 동일 조건 벤치마크는 확인되지 않았습니다.

짧은 판정

텍스트 가독성이 중요하다면 GPT Image 2를 먼저 쓰는 쪽에 무게가 실립니다. OpenAI의 개발자 프롬프팅 가이드에는 gpt-image-2를 사용해 읽기 쉬운 슬라이드 텍스트, 명확한 정보 위계, 정돈된 간격, 전문적인 발표자료 스타일을 요구하는 예시가 등장합니다 [23].

또 OpenAI Developer Community의 gpt-image-2 발표는 이 모델을 정확하고, 읽기 쉽고, 브랜드에 맞고, 현지화 가능하며, 최종 사용 매체에 맞게 포맷팅되고, 대대적인 후처리 없이 쓸 수 있는 제작 워크플로용으로 설명합니다. 같은 발표는 다국어 텍스트 렌더링 개선도 강조합니다 [32].

TechCrunch는 OpenAI 보도자료의 설명을 인용해 ChatGPT Images 2.0이 작은 글자, 아이콘, UI 요소, 조밀한 구성, 미묘한 스타일 제약처럼 이미지 모델이 자주 실패하는 세부 요소를 최대 2K 해상도에서 처리할 수 있다고 보도했습니다 [77].

단, 이것은 공개된 동일 프롬프트 실험에서 GPT Image 2가 GPT Image 1.5보다 특정 수치만큼 우수하다는 뜻은 아닙니다. 검토한 자료에는 철자 정확도, 글리프 정확도, 정렬, 언어별 성능, 출력 크기, 실패율을 모두 포함해 두 모델을 직접 채점한 공개 벤치마크가 없습니다. 이 공백은 중요합니다. GPT Image 1.5도 출시 당시 조밀하고 작은 텍스트 렌더링 개선을 내세웠기 때문입니다 [69].

자료로 확인되는 것과 확인되지 않는 것

주장판정
gpt-image-2가 읽기 쉬운 슬라이드 생성 예시에서 사용된다.확인됨 [23]
gpt-image-2가 정확하고 읽기 쉬우며 현지화 가능한 제작용 이미지 흐름에 맞춰 소개된다.확인됨 [32]
ChatGPT Images 2.0이 작은 글자, UI 요소, 조밀한 구성을 최대 2K에서 처리한다는 OpenAI 보도자료 설명이 보도됐다.보도 내용으로 확인됨 [77]
GPT Image 1.5도 조밀하고 작은 텍스트 렌더링을 개선했다고 발표됐다.확인됨 [69]
GPT Image 2와 GPT Image 1.5를 직접 비교한 투명한 공개 가독성 점수표가 있다.검토한 자료에서는 확인되지 않음

왜 GPT Image 2를 먼저 권할 수 있나

핵심은 ‘예쁜 이미지’가 아니라 ‘바로 쓸 수 있는 이미지’입니다. gpt-image-2 관련 자료는 읽기 쉽고, 현지화되고, 브랜드에 맞고, 실제 배포면에 맞는 산출물을 강조합니다 [32]. 이는 이미지 속 글자가 가장 자주 문제가 되는 영역과 정확히 겹칩니다. 예를 들어 발표 슬라이드, 앱 목업, 제품 패키지, 광고 배너, 상세 설명용 인포그래픽, 여러 언어가 섞인 시각 자료가 그렇습니다.

OpenAI의 ChatGPT Images 2.0 공개 페이지도 굵은 타이포그래피, 편집 문구, 데스크톱 UI처럼 텍스트가 중요한 장면의 예시를 전면에 배치합니다 [31]. 여기에 TechCrunch가 전한 OpenAI 보도자료 설명까지 더하면, GPT Image 2 / ChatGPT Images 2.0은 작은 글자와 UI 요소, 조밀한 레이아웃 같은 실무형 텍스트 과제에 더 초점을 둔 모델로 보는 것이 자연스럽습니다 [77].

따라서 최종 산출물이 포스터, 슬라이드, 앱 화면, 상품 라벨, 인포그래픽처럼 ‘읽혀야 하는 이미지’라면 GPT Image 2를 먼저 테스트하는 편이 낫습니다.

그렇다고 GPT Image 1.5가 무의미한 것은 아니다

GPT Image 1.5를 ‘글자 렌더링 이전 세대’처럼 취급하면 안 됩니다. 출시 발표에서 GPT Image 1.5는 더 정밀한 이미지 편집, 더 나은 프롬프트 준수, 그리고 특히 조밀하고 작은 글자에 대한 텍스트 렌더링 개선을 내세웠습니다 [69].

간단한 작업에서는 여전히 충분할 수 있습니다. 큰 제목 한 줄, 짧은 라벨, 사람이 쉽게 검수할 수 있는 시안, 내부용 목업이라면 GPT Image 1.5도 실무 흐름에 맞을 가능성이 있습니다.

다만 OpenAI의 API 이미지 생성 가이드는 gpt-image-1.5를 포함한 GPT Image 모델의 한계로 텍스트 렌더링을 여전히 언급합니다. DALL·E 계열보다 크게 개선됐더라도 정확한 글자 배치와 선명도에서는 어려움을 겪을 수 있다는 설명입니다 [47]. 즉 어떤 모델이든 ‘오탈자 없는 최종 원고 출력기’처럼 믿어서는 안 됩니다.

‘99% 타이포그래피 정확도’는 조심해서 봐야 한다

일부 서드파티 글이나 소셜 게시물은 GPT Image 2의 타이포그래피 또는 글리프 정확도가 99% 수준이라는 강한 주장을 내놓습니다 [4][7][78]. 방향성 신호로는 참고할 수 있지만, 검토한 자료만으로는 이를 확정된 벤치마크 사실로 보기 어렵습니다.

이런 수치가 의미 있으려면 최소한 다음이 공개돼야 합니다.

  • 어떤 프롬프트 세트를 썼는지
  • 어떤 언어와 문자 체계를 포함했는지
  • 몇 장을 생성했는지
  • 해상도와 품질 설정은 무엇이었는지
  • 실패한 생성물을 어떻게 계산했는지
  • 철자, 글리프, 자간, 줄바꿈, 정렬을 어떤 기준으로 채점했는지
  • 최종 게시 크기에서 사람이 실제로 읽을 수 있었는지

이 정보가 없으면 큰 포스터 제목에서는 좋아 보여도 긴 문단, 약관 수준의 작은 글씨, 차트 라벨, UI 버튼, 다국어 레이아웃에서는 실패할 수 있습니다.

이름 정리: GPT Image 2와 ChatGPT Images 2.0

자료에는 두 이름이 함께 나옵니다. 개발자 대상 자료에서는 gpt-image-2라는 모델 ID가 쓰입니다. OpenAI 프롬프팅 가이드 예시와 Developer Community 발표가 여기에 해당합니다 [23][32].

반면 일반 공개 페이지와 언론 보도에서는 ChatGPT Images 2.0이라는 이름이 사용됩니다 [31][77]. 제공된 자료 안에는 두 이름의 모든 주장을 1대1로 공식 매핑하는 단일 문장이 없습니다. 그래서 겹치는 근거를 말할 때는 GPT Image 2 / ChatGPT Images 2.0처럼 함께 표기하는 것이 가장 안전합니다.

어떤 모델을 써야 할까

GPT Image 2를 먼저 고를 상황은 비교적 분명합니다.

  • 텍스트 영역이 여러 군데 있는 이미지
  • 작은 라벨이나 주석이 들어가는 인포그래픽
  • 제품 패키지, 성분표, 스티커형 라벨
  • 앱 화면, 대시보드, 웹 UI 목업
  • 발표 슬라이드나 교육용 설명 자료
  • 여러 언어로 현지화해야 하는 광고나 안내 이미지

이 추천은 gpt-image-2가 읽기 쉬운 제작 워크플로에 맞춰 소개되고, Images 2.0이 작은 글자·UI 요소·조밀한 구성을 처리한다는 OpenAI 설명이 보도된 데 근거합니다 [32][77].

GPT Image 1.5도 고려할 만한 상황은 텍스트가 짧고 크며, 사람이 바로 검수할 수 있고, 현재 작업 흐름에서 이미 충분한 품질이 나오는 경우입니다. GPT Image 1.5 역시 조밀하고 작은 글자 렌더링 개선을 내세운 모델입니다 [69].

직접 비교할 때의 간단한 테스트법

텍스트 정확도가 비용이나 브랜드 신뢰와 직결된다면, 모델을 바꾸기 전에 같은 프롬프트로 직접 비교하는 것이 좋습니다.

  1. 정확 복사 테스트: 같은 제목, 부제, 짧은 라벨을 두 모델에 넣고 철자와 누락을 확인합니다.
  2. 작은 글자 테스트: 각주, 차트 라벨, UI 버튼, 제품 라벨의 작은 문구를 실제 게시 크기로 확인합니다.
  3. 조밀한 레이아웃 테스트: 인포그래픽, 메뉴판, 대시보드, 슬라이드처럼 텍스트 구역이 많은 이미지를 만듭니다.
  4. 수정 보존 테스트: 문구 하나만 바꿨을 때 나머지 이미지가 흔들리지 않는지 봅니다.
  5. 다국어 테스트: 팀이 실제로 배포하는 언어와 문자 체계를 넣습니다. 한국어처럼 라틴문자가 아닌 문자를 쓰는 작업이라면 별도 표본이 필요합니다.
  6. 사람 검수 점수화: 철자, 빠진 글자, 바뀐 단어, 가독성, 정렬, 후처리 없이 배포 가능한지를 항목별로 채점합니다.

가장 좋은 모델은 쇼케이스 이미지 한 장이 멋진 모델이 아닙니다. 여러분의 프롬프트, 목표 크기, 검수 절차에서 가장 꾸준히 정확하고 읽기 쉬운 글자를 내는 모델입니다.

결론

현재 자료 기준으로는 GPT Image 2가 이미지 속 텍스트가 중요한 실무 작업에서 더 나은 출발점으로 보입니다. 특히 작은 글자, 조밀한 레이아웃, UI 요소, 현지화·다국어 문구가 들어가는 이미지에서 그렇습니다.

그러나 결론은 과장하면 안 됩니다. OpenAI 관련 자료는 GPT Image 2 / ChatGPT Images 2.0을 읽기 쉬운 제작용 이미지와 세밀한 텍스트 처리 쪽으로 포지셔닝합니다 [32][77]. 동시에 GPT Image 1.5도 조밀하고 작은 글자 렌더링 개선을 내세웠고, 검토한 자료에는 두 모델을 직접 비교한 투명한 공개 가독성 벤치마크가 없습니다 [69].

Studio Global AI

Search, cite, and publish your own answer

Use this topic as a starting point for a fresh source-backed answer, then compare citations before you share it.

Studio Global AI로 검색 및 팩트체크

주요 시사점

  • GPT Image 2는 텍스트가 많은 이미지 작업의 기본 선택지로 더 설득력 있다. OpenAI 관련 자료가 읽기 쉬운, 현지화된, 제작용 이미지 흐름을 강조하기 때문이다 [32][77].
  • GPT Image 1.5도 이미 조밀하고 작은 글자 렌더링 개선을 내세운 모델이었다. 따라서 ‘구형은 못 쓰고 신형은 완벽하다’는 식의 결론은 부정확하다 [69].
  • ‘타이포그래피 99% 정확도’ 같은 주장은 시험 설계가 공개되지 않았다면 검증된 벤치마크로 보기 어렵다 [4][7][78].

사람들은 또한 묻습니다.

"GPT Image 2와 GPT Image 1.5, 이미지 속 글자 가독성 판정"에 대한 짧은 대답은 무엇입니까?

GPT Image 2는 텍스트가 많은 이미지 작업의 기본 선택지로 더 설득력 있다. OpenAI 관련 자료가 읽기 쉬운, 현지화된, 제작용 이미지 흐름을 강조하기 때문이다 [32][77].

먼저 검증할 핵심 포인트는 무엇인가요?

GPT Image 2는 텍스트가 많은 이미지 작업의 기본 선택지로 더 설득력 있다. OpenAI 관련 자료가 읽기 쉬운, 현지화된, 제작용 이미지 흐름을 강조하기 때문이다 [32][77]. GPT Image 1.5도 이미 조밀하고 작은 글자 렌더링 개선을 내세운 모델이었다. 따라서 ‘구형은 못 쓰고 신형은 완벽하다’는 식의 결론은 부정확하다 [69].

실무에서는 다음으로 무엇을 해야 합니까?

‘타이포그래피 99% 정확도’ 같은 주장은 시험 설계가 공개되지 않았다면 검증된 벤치마크로 보기 어렵다 [4][7][78].

다음에는 어떤 관련 주제를 탐구해야 할까요?

다른 각도와 추가 인용을 보려면 "Claude Opus 4.7·GPT-5.5·DeepSeek V4·Kimi K2.6 벤치마크 비교: 2026년 판정"으로 계속하세요.

관련 페이지 열기

이것을 무엇과 비교해야 합니까?

"DeepSeek V4 엔지니어링 해설: 100만 토큰, MoE, API 이전 체크포인트"에 대해 이 답변을 대조 확인하세요.

관련 페이지 열기

연구를 계속하세요

연구 대화

당신

연구문제

Search and fact-check: Is GPT Image 2 better than GPT Image 1.5 at rendering readable text inside images?

Studio Global AI40 소스

인용 답변

Verdict

Insufficient evidence. Based on the provided sources, I can’t verify that GPT Image 2 is definitively better than GPT Image 1.5 at rendering readable text inside images.[1][3][5][6][7][59]

What the evidence does show

  • The OpenAI sources in the provided evidence are API references and image-generation guides, but the snippets shown do not include any benchmark, evaluation, or explicit comparison between GPT Image 2 and GPT Image 1.5 on text rendering quality.[1][3][5][6][7]

  • The only direct comparison in the provided evidence is a Reddit post claiming that GPT Image 2 produces “super legible” text and is a “huge upgrade” over GPT Image 1.5.[59]

Why that is not enough to fact-check the claim

  • A single Reddit anecdote is not strong enough to establish a general performance claim without controlled examples, official test results, or independent evaluations.[59]

  • Since the provided official documentation snippets do not address readable text performance at all, they do not confirm the Reddit claim.[1][3][5][6][7]

Conclusion

If you ask strictly for a fact-check from the evidence provided, the answer is: not proven. There is one anecdotal signal in favor of GPT Image 2, but no solid comparative evidence here to confirm it.[1][3][5][6][7][59]

당신

연구문제

Research and fact-check: Is GPT Image 2 better than GPT Image 1.5 at rendering readable text inside images?

Studio Global AI22 소스

인용 답변

Based on the provided evidence alone, there is not enough reliable support to conclude that GPT Image 2 is definitively better than GPT Image 1.5 at rendering readable text inside images. Insufficient evidence. The only direct claim in the evidence favoring GPT Image 2 on text legibility is a Reddit anecdote, which is too weak on its own to establish a fact-checked conclusion [22].

Key findings

  • The strongest direct comparison in the provided evidence is a Reddit post stating that GPT Image 2 output is “so much better” and that “all the text is super legible,” but this is an unverified user report rather than a controlled benchmark or official evaluation [22].

  • The provided GPT Image 1.5 materials describe improvements such as faster generation, stronger instruction following, and more precise editing that preserves important details like faces, logos, and lighting, but the snippets do not provide a direct text-readability benchmark against GPT Image 2 [5][6][7].

  • One provided academic source includes “Text” as a category in a broader image-editing evaluation table, which shows that text rendering/editing is a recognized benchmark dimension, but the evidence shown does not establish a head-to-head GPT Image 2 vs. GPT Image 1.5 result [1].

  • A comparison page between “ChatGPT Images” and “GPT Image 2” is listed in the evidence, but the snippet provided does not show a methodology, a text-legibility metric, or a clear result relevant to GPT Image 2 versus GPT Image 1.5 specifically [2].

  • The provided GPT Image 2 guide entry does not expose any usable claim in the snippet about readable text performance, so it does not materially strengthen the case either way from the evidence shown [3].

Evidence notes

  • The available evidence is uneven in quality:
    • [1] is the most academic-looking source, but it does not clearly answer the exact product-vs-product question from the visible evidence [1].
    • [22] is the only direct claim about text readability, but it is anecdotal [22].
    • [5], [6], and [7] describe GPT Image 1.5 positively, but not with a direct comparable text-rendering test against GPT Image 2 [5][6][7].

Limitations / uncertainty

  • There is no official OpenAI benchmark, release note, or controlled side-by-side evaluation in the provided evidence that directly measures readable text rendering for GPT Image 2 versus GPT Image 1.5.

  • Several sources are product guides or comparison pages rather than primary technical evaluations, and the snippets shown do not contain enough detail to verify methodology or isolate text performance [2][3][5][6][7].

  • Because the only explicit “GPT Image 2 is better at text” evidence here is anecdotal, the safest fact-checked answer is that the claim is not established by the provided record [22].

Summary

With only the evidence provided, you cannot reliably say that GPT Image 2 is better than GPT Image 1.5 at rendering readable text inside images. There is a weak signal pointing that way from one Reddit comparison [22], but there is no strong, direct, verifiable benchmark in the evidence to confirm it [1][2][3][5][6][7].

당신

연구문제

Deep research & fact-check: Is GPT Image 2 better than GPT Image 1.5 at rendering readable text inside images?

Studio Global AI40 소스

인용 답변

Based on the evidence provided, there is not enough reliable support to say that GPT Image 2 is better than GPT Image 1.5 at rendering readable text inside images. The strongest official evidence only says that GPT Image models, including gpt-image-1.5 and gpt-image-1, have text rendering that is significantly improved over DALL·E models, but it does not provide a direct 1.5-versus-2 comparison or a benchmark for readable text performance between those two versions [4]. A single X post claims “99% typography accuracy” for “ChatGPT Images 2.0,” but that is not an official benchmark document and is not enough on its own to establish the comparison [64].

Key findings

  • The supplied official OpenAI documentation confirms that GPT Image models have improved text rendering relative to earlier DALL·E models, not relative to each other [4].
  • The evidence set includes official references to gpt-image-1 and mentions gpt-image-1.5, but it does not include an official model page or benchmark for a model explicitly identified as gpt-image-2 [2][4][6].
  • The only item suggesting a major typography improvement for “ChatGPT Images 2.0” is a social-media post, which is weaker evidence than official documentation or published evaluations [64].
  • Therefore, the answer is: Insufficient evidence to confirm that GPT Image 2 is better than GPT Image 1.5 at rendering readable text inside images.

Confirmed facts

  • OpenAI’s image-generation guide lists GPT Image models including gpt-image-1.5, gpt-image-1, and gpt-image-1-mini [4].
  • That same guide states that text rendering is “significantly improved” over DALL·E models, while still describing text rendering as a limitation category for GPT Image models [4].
  • OpenAI has an official model page for gpt-image-1 with pricing and generation settings, which confirms that gpt-image-1 is a current documented model in the API docs [2].
  • The supplied OpenAI models index also references “Image 1,” reinforcing that official documentation in this evidence set is centered on the Image 1 family rather than an officially documented “Image 2” page [6].
  • A post on X claims “99% typography accuracy” for “ChatGPT Images 2.0,” but the provided evidence does not show an OpenAI technical document, evaluation methodology, or side-by-side comparison supporting that number [64].

What remains inference

  • It is possible that “GPT Image 2” refers to “ChatGPT Images 2.0,” but the evidence provided does not formally map those names to the same API model family [64].
  • It is possible that GPT Image 2 is better at typography than GPT Image 1.5, but the evidence does not provide controlled tests, official benchmarks, or even a direct vendor claim in the docs comparing the two [4][64].
  • It is also possible that “99% typography accuracy” refers to a narrow internal test rather than general real-world text rendering across prompts, fonts, languages, or layouts, because no methodology is provided in the supplied evidence [64].

What the evidence suggests

  • The official documentation supports a modest claim: recent GPT Image models are better at text rendering than older DALL·E models [4].
  • The evidence does not support the stronger claim the user asked about: that GPT Image 2 is better than GPT Image 1.5 specifically at rendering readable text [4].
  • If forced to weigh the evidence, the social post points toward a likely improvement narrative for a newer image system, but that remains suggestive rather than verified because it lacks official documentation and reproducible testing in the supplied record [64].

Conflicting evidence or uncertainty

  • There is no direct contradiction in the evidence, but there is a major evidence gap.
  • Official OpenAI documentation in the record discusses gpt-image-1 and mentions gpt-image-1.5, yet the supplied evidence does not include an official GPT Image 2 model page or a text-rendering benchmark comparing 1.5 and 2 [2][4][6].
  • The X post is the only source mentioning a high typography-accuracy figure for “ChatGPT Images 2.0,” and social-media claims are materially weaker than primary technical documentation, especially when no test details are shown [64].
  • Because of that gap, any conclusion stronger than “unverified but plausible” would overstate what the evidence can support.

Open questions

  • Is “GPT Image 2” an official API model name, or is it a product/marketing label such as “ChatGPT Images 2.0”? [64]
  • Did OpenAI publish any benchmark or eval methodology for text readability, spelling accuracy, or typography across image models? The supplied evidence does not show one [4][64].
  • Are there controlled side-by-side tests comparing gpt-image-1.5 and the newer system on identical prompts with readable text requirements? The supplied evidence does not include any [4].

Sources worth trusting most

  • The strongest source here is the official OpenAI image-generation guide, because it directly discusses GPT Image model limitations and capabilities, including text rendering, even though it does not answer the 1.5-versus-2 question directly [4].
  • The official OpenAI model page for gpt-image-1 is also strong for confirming model existence and official documentation status, but it does not provide typography comparisons [2].
  • The OpenAI models index is useful for confirming naming/documentation context, though it is less specific than the model or guide pages [6].
  • The X post is the weakest source for the core claim because it is not official technical documentation and provides no visible methodology in the supplied evidence [64].

Recommended next step

  • Treat the claim as unproven unless you can obtain one of these:
    • an official OpenAI page for GPT Image 2 with text-rendering claims,
    • a published benchmark comparing GPT Image 2 and GPT Image 1.5 on readable text,
    • or controlled side-by-side test results using the same prompts and settings.
  • If you want, I can next help you design a fair prompt-based evaluation rubric for “readable text in images” so you can compare the models yourself.

Summary

No, this cannot be confirmed from the provided evidence. Official documentation supports only that GPT Image models improved text rendering versus DALL·E, not that GPT Image 2 outperforms GPT Image 1.5 specifically [4]. The only evidence pointing toward a major typography leap for “ChatGPT Images 2.0” is a single social-media post, which is not strong enough to establish the claim on its own [64].

출처