-
Notifications
You must be signed in to change notification settings - Fork 10
unconditional_image_generation_1stDraft #14
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Conversation
@@ -0,0 +1,70 @@ | |||
<!--Copy 2023 허깅페이스 팀. 모든 권리 보유. |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
copyright는 안해도 됩니다
라이선스에 따른 권한 및 제한을 규율하는 특정 언어를 참조하십시오. | ||
--> | ||
|
||
# 언컨디셔널 이미지 생성 |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
unconditional(위키 참조)
|
||
# 언컨디셔널 이미지 생성 | ||
|
||
[[오픈 인 콜랩]] |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
코랩에서 열기
|
||
언컨디셔널 이미지 생성은 비교적 간단한 작업입니다. 모델은 텍스트나 이미지와 같은 추가 컨텍스트 없이 학습된 훈련 데이터와 유사한 이미지만 생성합니다. | ||
|
||
[디퓨전 파이프라인`]은 추론을 위해 미리 훈련된 디퓨전 시스템을 사용하는 가장 쉬운 방법입니다. |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
디퓨전 -> diffusion
[디퓨전 파이프라인`]은 추론을 위해 미리 훈련된 디퓨전 시스템을 사용하는 가장 쉬운 방법입니다. | ||
|
||
먼저 [`디퓨전 파이프라인`]의 인스턴스를 생성하고 다운로드할 파이프라인 체크포인트를 지정합니다. | ||
허브의 🧨디퓨저 [체크포인트](https://huggingface.co/models?library=diffusers&sort=downloads) 중 하나를 사용할 수 있습니다(사용할 체크포인트는 나비 이미지를 생성합니다). |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
디퓨저 -> Diffusers
|
||
<팁> | ||
|
||
💡 나만의 언컨디셔널 이미지 생성 모델을 훈련하고 싶으신가요? 트레이닝 [가이드](training/unconditional_training)를 참고하여 나만의 이미지를 생성하는 방법을 알아보세요. |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
트레이닝 -> 학습
|
||
이 가이드에서는 [DDPM](https://arxiv.org/abs/2006.11239)을 사용한 언컨디셔널 이미지 생성에 [`DiffusionPipeline`]을 사용합니다: | ||
|
||
'''파이썬 |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
파이썬 -> python
|
||
출력은 기본적으로 [`PIL.Image`](https://pillow.readthedocs.io/en/stable/reference/Image.html?highlight=image#the-image-class) 객체로 래핑됩니다. | ||
|
||
호출하여 이미지를 저장할 수 있습니다: |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
다음을 호출하여..
>>> image = generator().images[0] | ||
``` | ||
|
||
출력은 기본적으로 [`PIL.Image`](https://pillow.readthedocs.io/en/stable/reference/Image.html?highlight=image#the-image-class) 객체로 래핑됩니다. |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
래핑 -> 감싸다
></iframe> | ||
|
||
|
||
Translated with www.DeepL.com/Translator (free version) |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
줄 지워주세요
conditional-언컨디셔널 직역