[Docs] Korean translation update #4684
Conversation
controlnet, reproducibility 업로드 generator 그대로 사용 seamless multi-GPU 그대로 사용 create_dataset 번역 1차 stable_diffusion_jax new translation Add coreml, tome kr docs minor fix translate training/instructpix2pix fix training/instructpix2pix.mdx using-diffusers/weighting_prompts 번역 1차 add SDXL docs Translate using-diffuers/loading_overview.md translate using-diffusers/textual_inversion_inference.md Conditional image generation (#37) * stable_diffusion_jax * index_update * index_update * condition_image_generation --------- Co-authored-by: Seongsu Park <tjdtnsu@gmail.com> jihwan/stable_diffusion.mdx custom_diffusion 작업 완료 quicktour 작업 완료 distributed inference & control brightness (#40) * distributed_inference.mdx * control_brightness --------- Co-authored-by: idra79haza <idra79haza@github.com> Co-authored-by: Seongsu Park <tjdtnsu@gmail.com> using_safetensors (#41) * distributed_inference.mdx * control_brightness * using_safetensors.mdx --------- Co-authored-by: idra79haza <idra79haza@github.com> Co-authored-by: Seongsu Park <tjdtnsu@gmail.com> delete safetensor short
|
Hello. Thank you for reviewing them. |
0dcdb78 to
9a355cb
Compare
|
The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. |
stevhliu
left a comment
There was a problem hiding this comment.
Big thanks again for working on translating so many of these! I'd just like to ping @wonhyeongseo for maybe a quick review of the content for accuracy, then we're good to merge! 🚀
|
|
||
| *text-to-image의 latent diffusion 모델인 SDXL을 소개합니다. 이전 버전의 Stable Diffusion과 비교하면, SDXL은 세 배 더큰 규모의 UNet 백본을 포함합니다: 모델 파라미터의 증가는 많은 attention 블럭을 사용하고 더 큰 cross-attention context를 SDXL의 두 번째 텍스트 인코더에 사용하기 때문입니다. 다중 종횡비에 다수의 새로운 conditioning 방법을 구성했습니다. 또한 후에 수정하는 image-to-image 기술을 사용함으로써 SDXL에 의해 생성된 시각적 품질을 향상하기 위해 정제된 모델을 소개합니다. SDXL은 이전 버전의 Stable Diffusion보다 성능이 향상되었고, 이러한 black-box 최신 이미지 생성자와 경쟁력있는 결과를 달성했습니다.* | ||
|
|
||
| ## 팁 |
There was a problem hiding this comment.
| ## 팁 | |
| ## 팁 [[tips]] |
Just a small suggestion! Could we add internal English anchors like this? It'll help match our in-document ToC better. I noticed some documents have them, and some don't. Thanks! 🙂
There was a problem hiding this comment.
Currently anchors are added only to paragraphs corresponding to the original document. I might consider adding this, but I'll skip it for now.
|
|
||
| ## Swift에서 Core ML 추론하기 | ||
|
|
||
| Running inference in Swift is slightly faster than in Python because the models are already compiled in the `mlmodelc` format. This is noticeable on app startup when the model is loaded but shouldn’t be noticeable if you run several generations afterward. |
There was a problem hiding this comment.
I think there might have been a slight oversight during the translation process. Would you mind taking a look at this section? Appreciate your help! 😊
| Apple's [conversion and inference repo](https://github.com/apple/ml-stable-diffusion) and our own [swift-coreml-diffusers](https://github.com/huggingface/swift-coreml-diffusers) repos are intended as technology demonstrators to enable other developers to build upon. | ||
|
|
||
| If you feel strongly about any missing features, please feel free to open a feature request or, better yet, a contribution PR :) |
There was a problem hiding this comment.
Same here! These should be translated as well.
|
|
||
| `--checkpointing_steps` 인수를 사용한 경우 학습 과정에서 저장된 전체 체크포인트 중 하나에서 추론을 수행할 수도 있습니다. | ||
|
|
||
| 해야 할 일. |
There was a problem hiding this comment.
| 해야 할 일. | |
| TODO. |
Hey @stevhliu ! I noticed this section of the English doc might not be complete. Could you share your thoughts on the next steps? Thanks! 😊
There was a problem hiding this comment.
You can remove the TODO text :)
|
|
||
| 이제 컨텍스트 관리자로 [`~accelerate.PartialState.split_between_processes`] 유틸리티를 사용하여 프로세스 수에 따라 프롬프트를 자동으로 분배합니다. | ||
|
|
||
| Translated with www.DeepL.com/Translator (free version) |
There was a problem hiding this comment.
| Translated with www.DeepL.com/Translator (free version) |
It looks like this might have been added inadvertently. Could you kindly remove it? Thanks! 😺
|
👍 LGTM. I'll 📝 update the docs with TOCs 📖 as we progress. All-in-all, great work 🎉 @Snailpong ! |
* Docs kr update 3 controlnet, reproducibility 업로드 generator 그대로 사용 seamless multi-GPU 그대로 사용 create_dataset 번역 1차 stable_diffusion_jax new translation Add coreml, tome kr docs minor fix translate training/instructpix2pix fix training/instructpix2pix.mdx using-diffusers/weighting_prompts 번역 1차 add SDXL docs Translate using-diffuers/loading_overview.md translate using-diffusers/textual_inversion_inference.md Conditional image generation (huggingface#37) * stable_diffusion_jax * index_update * index_update * condition_image_generation --------- Co-authored-by: Seongsu Park <tjdtnsu@gmail.com> jihwan/stable_diffusion.mdx custom_diffusion 작업 완료 quicktour 작업 완료 distributed inference & control brightness (huggingface#40) * distributed_inference.mdx * control_brightness --------- Co-authored-by: idra79haza <idra79haza@github.com> Co-authored-by: Seongsu Park <tjdtnsu@gmail.com> using_safetensors (huggingface#41) * distributed_inference.mdx * control_brightness * using_safetensors.mdx --------- Co-authored-by: idra79haza <idra79haza@github.com> Co-authored-by: Seongsu Park <tjdtnsu@gmail.com> delete safetensor short * Repace mdx to md * toctree update * Add controlling_generation * toctree fix * colab link, minor fix * docs name typo fix * frontmatter fix * translation fix
What does this PR do?
Added some documentation translated into Korean. (part 3)
Before submitting
documentation guidelines, and
here are tips on formatting docstrings.
Who can review?
@patrickvonplaten
@stevhliu