Skip to content
Open
Show file tree
Hide file tree
Changes from all commits
Commits
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
2 changes: 2 additions & 0 deletions development/comfyui-server/startup-flags.mdx
Original file line number Diff line number Diff line change
Expand Up @@ -177,6 +177,8 @@ python main.py --disable-auto-launch
VRAM mode flags (`--gpu-only`, `--highvram`, `--lowvram`, `--novram`, `--cpu`) are mutually exclusive.
</Note>

**Default behavior on Nvidia GPUs:** `--async-offload` (weight offloading) and dynamic VRAM are both enabled by default. Models are automatically moved between VRAM and CPU RAM as needed. You do not need to pass any flags to enable this.

| Flag | Default | Description |
|------|---------|-------------|
| `--gpu-only` | — | Store and run everything on the GPU (text encoders, CLIP, etc.). |
Expand Down
4 changes: 4 additions & 0 deletions get_started/cloud.mdx
Original file line number Diff line number Diff line change
Expand Up @@ -134,6 +134,10 @@ If you have any thoughts, suggestions, or run into any issues, simply click the
View frequently asked questions and answers about Comfy Cloud, including pricing, features, limitations, and more
</Card>

### Does Comfy Cloud have content moderation?

Yes. Comfy Cloud enforces content policies. Generating explicit or prohibited content may result in account suspension. For questions about what is or is not allowed, see the Comfy Cloud Terms of Service at [comfy.org](https://comfy.org).

Comment on lines +137 to +140

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
set -euo pipefail

echo "== file excerpt =="
nl -ba get_started/cloud.mdx | sed -n '126,148p'

echo
echo "== comfy.org references =="
rg -n "comfy\.org|Terms of Service|content policies" get_started . -g '!**/node_modules/**' || true

Repository: Comfy-Org/docs

Length of output: 211


🏁 Script executed:

#!/bin/bash
set -euo pipefail

echo "== file excerpt =="
awk 'NR>=126 && NR<=148 {printf "%d:%s\n", NR, $0}' get_started/cloud.mdx

echo
echo "== comfy.org references =="
rg -n "comfy\.org|Terms of Service|content policies|policy page|tos" get_started . -g '!**/node_modules/**' || true

Repository: Comfy-Org/docs

Length of output: 50371


Point the Terms of Service link to the policy page. The current link lands on the homepage. Use the Terms of Service URL instead: https://www.comfy.org/terms-of-service?utm_source=docs.

🤖 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 `@get_started/cloud.mdx` around lines 137 - 140, Update the Terms of Service
link in the content about Comfy Cloud moderation so it points to the actual
policy page instead of the homepage. In the relevant markdown section with the
Comfy Cloud Terms of Service reference, replace the current comfy.org link with
the Terms of Service URL and keep the surrounding wording unchanged.

## Next steps

<CardGroup cols={2}>
Expand Down
2 changes: 2 additions & 0 deletions ja/development/comfyui-server/startup-flags.mdx
Original file line number Diff line number Diff line change
Expand Up @@ -196,6 +196,8 @@ python main.py --disable-auto-launch
VRAM モードのフラグ(`--gpu-only`、`--highvram`、`--lowvram`、`--novram`、`--cpu`)は排他的です。
</Note>

**Nvidia GPU のデフォルト動作:** `--async-offload`(ウェイトオフロード)と動的 VRAM はどちらもデフォルトで有効です。モデルは必要に応じて VRAM と CPU RAM の間で自動的に移動されます。これを有効にするためにフラグを渡す必要はありません。

| フラグ | デフォルト | 説明 |
|--------|-----------|------|
| `--gpu-only` | — | すべて(テキストエンコーダー、CLIP など)を GPU に保存して実行。 |
Expand Down
2 changes: 2 additions & 0 deletions ko/development/comfyui-server/startup-flags.mdx
Original file line number Diff line number Diff line change
Expand Up @@ -194,6 +194,8 @@ python main.py --disable-auto-launch
VRAM 모드 플래그(`--gpu-only`, `--highvram`, `--lowvram`, `--novram`, `--cpu`)는 상호 배타적입니다.
</Note>

**Nvidia GPU 기본 동작:** `--async-offload`(가중치 오프로딩)와 동적 VRAM이 모두 기본적으로 활성화되어 있습니다. 모델은 필요에 따라 VRAM과 CPU RAM 간에 자동으로 이동됩니다. 이 동작을 활성화하기 위해 플래그를 전달할 필요가 없습니다.

| 플래그 | 기본값 | 설명 |
|------|---------|-------------|
| `--gpu-only` | — | 모든 것을 GPU에 저장하고 실행합니다(텍스트 인코더, CLIP 등). |
Expand Down
2 changes: 2 additions & 0 deletions zh/development/comfyui-server/startup-flags.mdx
Original file line number Diff line number Diff line change
Expand Up @@ -196,6 +196,8 @@ python main.py --disable-auto-launch
VRAM 模式参数(`--gpu-only`、`--highvram`、`--lowvram`、`--novram`、`--cpu`)互斥。
</Note>

**Nvidia GPU 默认行为:** `--async-offload`(权重卸载)和动态 VRAM 都默认启用。模型会根据需要自动在 VRAM 和 CPU RAM 之间移动。无需传递任何标志即可启用此行为。

| 参数 | 默认值 | 说明 |
|------|--------|------|
| `--gpu-only` | — | 将所有内容(文本编码器、CLIP 等)存储并运行在 GPU 上。 |
Expand Down
4 changes: 4 additions & 0 deletions zh/get_started/cloud.mdx
Original file line number Diff line number Diff line change
Expand Up @@ -142,6 +142,10 @@ ComfyUI Cloud 是 ComfyUI 的云端版本,具有与本地版本相同的功能
查看有关 Comfy Cloud 的常见问题和解答,包括定价、功能、限制等详细信息
</Card>

### 云端有内容审核吗

有。Comfy Cloud 会执行内容政策。生成违规或禁止内容可能导致账号被封禁。有关允许与不允许内容的疑问,请参阅 Comfy Cloud 服务条款(访问 [comfy.org](https://comfy.org))。

## 下一步

<CardGroup cols={2}>
Expand Down
Loading