Skip to content

docs: add Cloud Content Moderation section and clarify async-offload default based on analytics #1240

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.

Sign up for GitHub

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

Closed
lin-bot23 wants to merge 1 commit into from
Closed

docs: add Cloud Content Moderation section and clarify async-offload default based on analytics #1240

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 4 additions & 0 deletions development/cloud/overview.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -319,6 +319,10 @@ Here's a full end-to-end example combining all three steps:
| [WebSocket](/development/cloud/api-reference#websocket-for-real-time-progress) | Real-time progress updates |
| [Object Info](/development/cloud/api-reference#object-info) | Available nodes and their definitions |

## Content Moderation

Workflows submitted to Comfy Cloud run on Comfy-managed infrastructure. Standard content moderation policies apply. If your workflow uses Partner Nodes, your inputs (prompts, images, and other content) are sent to third-party providers for processing, and those providers enforce their own content moderation policies. Please do not submit NSFW or other prohibited content to API nodes.

## Next Steps

The quick start above covers the basics of submitting workflows and retrieving results. For more advanced use cases, refer to the [Cloud API Reference](/development/cloud/api-reference):
Expand Down
4 changes: 4 additions & 0 deletions ja/development/cloud/overview.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -331,6 +331,10 @@ print(f"Job submitted: {prompt_id}")
| [WebSocket](/ja/development/cloud/api-reference#websocket-for-real-time-progress) | リアルタイムの進捗更新 |
| [オブジェクト情報](/ja/development/cloud/api-reference#object-info) | 利用可能なノードとその定義 |

## コンテンツモデレーション

Comfy Cloud に送信されたワークフローは、Comfy が管理するインフラストラクチャ上で実行されます。標準のコンテンツモデレーションポリシーが適用されます。パートナーノードを使用する場合、入力（プロンプト、画像など）はサードパーティプロバイダーに送信されて処理され、それらのプロバイダーは独自のコンテンツモデレーションポリシーを適用します。NSFW やその他の禁止コンテンツを API ノードに送信しないでください。

## 次のステップ

上記のクイックスタートでは、ワークフローの送信と結果の取得の基礎をカバーしています。より高度なユースケースについては、[Cloud API リファレンス](/ja/development/cloud/api-reference)を参照してください：
Expand Down
5 changes: 4 additions & 1 deletion ja/troubleshooting/overview.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -77,8 +77,11 @@ python main.py --preview-method none
python main.py --use-pytorch-cross-attention
python main.py --use-flash-attention

# 非同期ウェイトオフローディング
# 非同期ウェイトオフロード（Nvidia GPU でデフォルト有効）
python main.py --async-offload

# 非同期ウェイトオフロードを無効化
python main.py --disable-async-offload
```

メモリ管理用：
Expand Down
4 changes: 4 additions & 0 deletions ko/development/cloud/overview.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -330,6 +330,10 @@ print(f"작업 제출됨: {prompt_id}")
| [WebSocket](/ko/development/cloud/api-reference#websocket-for-real-time-progress) | 실시간 진행 상태 업데이트 |
| [객체 정보](/ko/development/cloud/api-reference#object-info) | 사용 가능한 노드 및 그 정의 |

## 콘텐츠 모더레이션

Comfy Cloud에 제출된 워크플로우는 Comfy 관리 인프라에서 실행됩니다. 표준 콘텐츠 모더레이션 정책이 적용됩니다. 파트너 노드를 사용하는 경우 입력(프롬프트, 이미지 등)이 타사 공급업체로 전송되어 처리되며, 해당 공급업체는 자체 콘텐츠 모더레이션 정책을 적용합니다. NSFW 또는 기타 금지된 콘텐츠를 API 노드에 제출하지 마십시오.

## 다음 단계

위의 빠른 시작은 워크플로우 제출과 결과 가져오기에 대한 기본 사항을 다룹니다. 더 고급 사용 사례를 위해서는 [클라우드 API 참조](/ko/development/cloud/api-reference)를 참고하십시오:
Expand Down
5 changes: 4 additions & 1 deletion ko/troubleshooting/overview.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -77,8 +77,11 @@ python main.py --preview-method none
python main.py --use-pytorch-cross-attention
python main.py --use-flash-attention

# 비동기 웨이트 오프로드
# 비동기 가중치 오프로딩（Nvidia GPU에서 기본 활성화）
python main.py --async-offload

# 비동기 가중치 오프로딩 비활성화
python main.py --disable-async-offload
```

메모리 관리를 위해:
Expand Down
4 changes: 4 additions & 0 deletions zh/development/cloud/overview.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -331,6 +331,10 @@ print(f"Job submitted: {prompt_id}")
| [WebSocket](/zh/development/cloud/api-reference#实时进度-websocket) | 实时进度更新 |
| [对象信息](/zh/development/cloud/api-reference#对象信息) | 可用节点及其定义 |

## 内容审核

提交到 Comfy Cloud 的工作流在 Comfy 管理的基础设施上运行。标准内容审核政策适用。如果您的工作流使用了合作伙伴节点，您的输入（提示词、图像等内容）将发送给第三方供应商处理，这些供应商会执行其自身的内容审核政策。请勿向 API 节点提交 NSFW 或其他违禁内容。

## 后续步骤

上面的快速入门涵盖了提交工作流和获取结果的基础知识。对于更高级的用例，请参阅 [Cloud API 参考](/zh/development/cloud/api-reference)：
Expand Down
5 changes: 4 additions & 1 deletion zh/troubleshooting/overview.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -77,8 +77,11 @@ python main.py --preview-method none
python main.py --use-pytorch-cross-attention
python main.py --use-flash-attention

# 异步权重卸载
# 异步权重卸载（Nvidia GPU 上默认启用）
python main.py --async-offload

# 禁用异步权重卸载
python main.py --disable-async-offload
Comment on lines +80 to +84

@coderabbitai coderabbitai Bot Jul 8, 2026

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

📐 Maintainability & Code Quality | 🟡 Minor | ⚡ Quick win

🧩 Analysis chain

🏁 Script executed:

#!/bin/bash
# Description: Check if the English troubleshooting doc already has the async offload updates.

# Search for --disable-async-offload in the root-level troubleshooting overview
rg -n 'disable-async-offload' troubleshooting/overview.mdx

# Also check for the Nvidia default-enabled note
rg -n -i 'default.*async.*offload\|async.*offload.*default' troubleshooting/overview.mdx

Repository: Comfy-Org/docs

Length of output: 152

🏁 Script executed:

#!/bin/bash
set -euo pipefail

printf '\n## Files named overview.mdx under troubleshooting\n'
git ls-files '*troubleshooting/overview.mdx' || true

printf '\n## Search for async offload references across troubleshooting docs\n'
rg -n -i 'async[- ]offload|disable-async-offload|default.*async.*offload|async.*offload.*default|Nvidia.*default|default.*Nvidia' . --glob '*troubleshooting/overview.mdx' || true

printf '\n## Search for English troubleshooting overview at repo root or nearby\n'
fd -a 'overview.mdx' . | rg 'troubleshooting/overview\.mdx$' || true

Repository: Comfy-Org/docs

Length of output: 733

Sync the English troubleshooting page

troubleshooting/overview.mdx:69 still only has python main.py --async-offload; add the --disable-async-offload command and the Nvidia default-enabled note here too, or split this into a separate English change.

🤖 Prompt for AI Agents 
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.

In `@zh/troubleshooting/overview.mdx` around lines 80 - 84, The troubleshooting
overview content in the English page is missing the async offload disable
command and the Nvidia default-enabled note. Update the corresponding section in
the troubleshooting overview to match the Chinese version by including both the
“async offload enabled by default on Nvidia GPU” note and the
`--disable-async-offload` command, using the same section around the
troubleshooting commands so the English and Chinese docs stay in sync.

```

内存管理：
Expand Down
Loading