Skip to content

docs: add Common Questions section with GPU resolution guidance and noise seed explanation #1238

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

Open
lin-bot23 wants to merge 1 commit into
base: main
Choose a base branch
from
Open

docs: add Common Questions section with GPU resolution guidance and noise seed explanation #1238

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
23 changes: 23 additions & 0 deletions ja/troubleshooting/overview.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -476,6 +476,29 @@ pip install torch==2.3.1.post0+cxx11.abi torchvision==0.18.1.post0+cxx11.abi tor
</Step>
</Steps>

## よくある質問

### 自分の GPU にはどの解像度を使用すればよいですか？

特定の GPU に「最適な」解像度はありません。最大使用可能な解像度は、モデルの種類、VRAM、ワークフローの複雑さによって異なります。一般的な目安は以下の通りです。

- **8 GB VRAM（RTX 3070、RTX 4060 など）：** 512x512 〜 1024x1024（SD1.5/FLUX）、動画モデルではより小さいサイズ
- **12-16 GB VRAM（RTX 4070、RTX 3080、RTX 4080 など）：** 768x768 〜 1280x1280（画像）、動画は 512x512（短いクリップ）
- **24 GB VRAM（RTX 4090、RTX 3090、A5000 など）：** 1024x1024 〜 1536x1536（画像）、動画は 640x640 まで
- **48 GB+ VRAM（A6000、A100 など）：** 最高解像度、マルチワークフローバッチ処理対応

使用するモデルのデフォルトサイズから始めて、徐々に大きくしてください。メモリ不足になった場合は、解像度を下げるか、fp8量子化モデルに切り替えるか、バッチサイズを小さくしてください。

### ノイズシード（noise seed）とは何ですか？

**ノイズシード**は、サンプラーが使用するランダムノイズパターンを制御します。同じシード、モデル、チェックポイント、パラメータを使用すると、毎回まったく同じ結果が得られます。これは以下の場面で役立ちます。

- **特定の出力を再現する** — シードをワークフローと一緒に共有する
- **パラメータ変更を比較する** — シードを固定して1つの設定のみ変更し、その効果を分離する
- **バリエーションを探索する** — シードを変更して異なる出力を生成する

シードは [RandomNoise](/ja/built-in-nodes/RandomNoise) などのノード、または [KSampler](/ja/built-in-nodes/KSampler) や [SamplerCustom](/ja/built-in-nodes/SamplerCustom) の `noise_seed` パラメータで設定できます。

@coderabbitai coderabbitai Bot Jul 7, 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.

🎯 Functional Correctness | 🟠 Major | ⚡ Quick win

Fix the KSampler parameter name.

KSampler uses seed, not noise_seed; only RandomNoise and SamplerCustom use noise_seed. Otherwise the localized FAQ points readers at the wrong control.

Suggested rewrite 
-シードは [RandomNoise](/ja/built-in-nodes/RandomNoise) などのノード、または [KSampler](/ja/built-in-nodes/KSampler) や [SamplerCustom](/ja/built-in-nodes/SamplerCustom) の `noise_seed` パラメータで設定できます。
+シードは [RandomNoise](/ja/built-in-nodes/RandomNoise) などのノード、または [KSampler](/ja/built-in-nodes/KSampler) の `seed` パラメータと [SamplerCustom](/ja/built-in-nodes/SamplerCustom) の `noise_seed` パラメータで設定できます。
📝 Committable suggestion

‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.

Suggested change
シードは [RandomNoise](/ja/built-in-nodes/RandomNoise) などのノード、または [KSampler](/ja/built-in-nodes/KSampler) や [SamplerCustom](/ja/built-in-nodes/SamplerCustom) の `noise_seed` パラメータで設定できます。
シードは [RandomNoise](/ja/built-in-nodes/RandomNoise) などのノード、または [KSampler](/ja/built-in-nodes/KSampler) の `seed` パラメータと [SamplerCustom](/ja/built-in-nodes/SamplerCustom) の `noise_seed` パラメータで設定できます。
🤖 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 `@ja/troubleshooting/overview.mdx` at line 500, The localized FAQ text is using
the wrong parameter name for KSampler, which can mislead readers; update the
sentence in the troubleshooting overview so that KSampler is referenced with its
actual seed parameter name while keeping noise_seed only for RandomNoise and
SamplerCustom. Use the existing link labels and surrounding troubleshooting
wording in the current paragraph to make the correction consistent with the rest
of the documentation.


## コミュニティリソース

- **公式フォーラム:** [forum.comfy.org](https://forum.comfy.org/)
Expand Down
23 changes: 23 additions & 0 deletions ko/troubleshooting/overview.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -476,6 +476,29 @@ pip install torch==2.3.1.post0+cxx11.abi torchvision==0.18.1.post0+cxx11.abi tor
</Step>
</Steps>

## 자주 묻는 질문

### 내 GPU에 어떤 해상도를 사용해야 하나요?

특정 GPU에 "최적"의 해상도는 없습니다. 최대 사용 가능 해상도는 모델 유형, VRAM, 워크플로 복잡성에 따라 다릅니다. 일반적인 가이드라인은 다음과 같습니다.

- **8 GB VRAM (예: RTX 3070, RTX 4060):** 512x512 ~ 1024x1024 (SD1.5/FLUX), 비디오 모델은 더 작은 크기
- **12-16 GB VRAM (예: RTX 4070, RTX 3080, RTX 4080):** 768x768 ~ 1280x1280 (이미지), 비디오 512x512 (짧은 클립)
- **24 GB VRAM (예: RTX 4090, RTX 3090, A5000):** 1024x1024 ~ 1536x1536 (이미지), 비디오 최대 640x640
- **48 GB+ VRAM (예: A6000, A100):** 최고 해상도, 멀티 워크플로 배치 처리 지원

사용 중인 모델의 기본 크기에서 시작하여 점차 늘려보세요. 메모리가 부족하면 해상도를 낮추거나, fp8 양자화 모델로 전환하거나, 배치 크기를 줄이세요.

### 노이즈 시드(noise seed)란 무엇인가요?

**노이즈 시드**는 샘플러가 사용하는 무작위 노이즈 패턴을 제어합니다. 동일한 시드, 모델, 체크포인트, 파라미터를 사용하면 매번 정확히 동일한 결과가 생성됩니다. 이는 다음과 같은 경우에 유용합니다.

- **특정 출력 재현** — 시드를 워크플로와 함께 공유
- **파라미터 변경 비교** — 시드를 고정하고 하나의 설정만 변경하여 효과를 분리
- **배치 변형** — 시드를 변경하여 다양한 출력 생성

시드는 [RandomNoise](/ko/built-in-nodes/RandomNoise) 노드 또는 [KSampler](/ko/built-in-nodes/KSampler)와 [SamplerCustom](/ko/built-in-nodes/SamplerCustom)의 `noise_seed` 파라미터에서 설정할 수 있습니다.

@coderabbitai coderabbitai Bot Jul 7, 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.

🎯 Functional Correctness | 🟠 Major | ⚡ Quick win

Fix the KSampler parameter name.

KSampler uses seed, not noise_seed; only RandomNoise and SamplerCustom use noise_seed. Otherwise this sends users to the wrong knob.

Suggested rewrite 
-시드는 [RandomNoise](/ko/built-in-nodes/RandomNoise) 노드 또는 [KSampler](/ko/built-in-nodes/KSampler)와 [SamplerCustom](/ko/built-in-nodes/SamplerCustom)의 `noise_seed` 파라미터에서 설정할 수 있습니다.
+시드는 [RandomNoise](/ko/built-in-nodes/RandomNoise) 노드 또는 [KSampler](/ko/built-in-nodes/KSampler)의 `seed` 파라미터와 [SamplerCustom](/ko/built-in-nodes/SamplerCustom)의 `noise_seed` 파라미터에서 설정할 수 있습니다.
📝 Committable suggestion

‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.

Suggested change
시드는 [RandomNoise](/ko/built-in-nodes/RandomNoise) 노드 또는 [KSampler](/ko/built-in-nodes/KSampler)와 [SamplerCustom](/ko/built-in-nodes/SamplerCustom)의 `noise_seed` 파라미터에서 설정할 수 있습니다.
시드는 [RandomNoise](/ko/built-in-nodes/RandomNoise) 노드 또는 [KSampler](/ko/built-in-nodes/KSampler)의 `seed` 파라미터와 [SamplerCustom](/ko/built-in-nodes/SamplerCustom)의 `noise_seed` 파라미터에서 설정할 수 있습니다.
🤖 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 `@ko/troubleshooting/overview.mdx` at line 500, The parameter name in this
troubleshooting sentence is wrong for KSampler: it should refer to KSampler’s
seed field, not noise_seed. Update the wording in the overview text so
RandomNoise and SamplerCustom keep noise_seed, while KSampler is described with
seed, using the KSampler, RandomNoise, and SamplerCustom references already
present to keep the explanation accurate.


## 커뮤니티 리소스

- **공식 포럼:** [forum.comfy.org](https://forum.comfy.org/)
Expand Down
23 changes: 23 additions & 0 deletions troubleshooting/overview.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -464,6 +464,29 @@ When reporting any issue, include:
</Step>
</Steps>

## Common Questions

### What resolution or dimensions should I use for my GPU?

There is no single "best" resolution for a given GPU model. The maximum viable resolution depends on your specific model type, VRAM, and the workflow complexity. As a general guideline:

- **8 GB VRAM (e.g. RTX 3070, RTX 4060):** 512x512 to 1024x1024 for SD1.5/FLUX; smaller sizes for video models
- **12-16 GB VRAM (e.g. RTX 4070, RTX 3080, RTX 4080):** 768x768 to 1280x1280 for images; 512x512 video at shorter lengths
- **24 GB VRAM (e.g. RTX 4090, RTX 3090, A5000):** 1024x1024 to 1536x1536 for images; up to 640x640 video or longer clips
- **48 GB+ VRAM (e.g. A6000, A100):** Highest available resolutions, multi-workflow batching

Start with the default dimensions of the model you are using and increase gradually. If you run out of memory, reduce the resolution, switch to a fp8 quantized model, or lower your batch size.

### How does the noise seed work?

The **noise seed** controls the random noise pattern that the sampler starts from. Using the same seed, model, checkpoint, and parameters will produce the exact same result every time. This is useful for:

- **Reproducing a specific output** — share the seed along with your workflow
- **Comparing parameter changes** — keep the seed fixed and change only one setting to isolate its effect
- **Batch variation** — change the seed to explore different outputs

The seed is set in nodes like [RandomNoise](/built-in-nodes/RandomNoise) or in the `noise_seed` parameter of [KSampler](/built-in-nodes/KSampler) and [SamplerCustom](/built-in-nodes/SamplerCustom).

@coderabbitai coderabbitai Bot Jul 7, 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.

🎯 Functional Correctness | 🟠 Major | ⚡ Quick win

Fix the KSampler parameter name.

KSampler exposes seed, not noise_seed; only RandomNoise and SamplerCustom use noise_seed. Otherwise this points readers at the wrong setting.

Suggested rewrite 
-The seed is set in nodes like [RandomNoise](/built-in-nodes/RandomNoise) or in the `noise_seed` parameter of [KSampler](/built-in-nodes/KSampler) and [SamplerCustom](/built-in-nodes/SamplerCustom).
+The seed is set in nodes like [RandomNoise](/built-in-nodes/RandomNoise) or in the `seed` parameter of [KSampler](/built-in-nodes/KSampler) and the `noise_seed` parameter of [SamplerCustom](/built-in-nodes/SamplerCustom).
📝 Committable suggestion

‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.

Suggested change
The seed is set in nodes like [RandomNoise](/built-in-nodes/RandomNoise) or in the `noise_seed` parameter of [KSampler](/built-in-nodes/KSampler) and [SamplerCustom](/built-in-nodes/SamplerCustom).
The seed is set in nodes like [RandomNoise](/built-in-nodes/RandomNoise) or in the `seed` parameter of [KSampler](/built-in-nodes/KSampler) and the `noise_seed` parameter of [SamplerCustom](/built-in-nodes/SamplerCustom).
🤖 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 `@troubleshooting/overview.mdx` at line 488, The parameter reference in the
troubleshooting overview is incorrect for KSampler: it should point to
KSampler’s seed field rather than noise_seed. Update the sentence that mentions
RandomNoise, KSampler, and SamplerCustom so that only RandomNoise and
SamplerCustom are associated with noise_seed, while KSampler is referenced with
seed instead.


## Community Resources

- **Official Forum:** [forum.comfy.org](https://forum.comfy.org/)
Expand Down
23 changes: 23 additions & 0 deletions zh/troubleshooting/overview.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -476,6 +476,29 @@ pip install torch==2.3.1.post0+cxx11.abi torchvision==0.18.1.post0+cxx11.abi tor
</Step>
</Steps>

## 常见问题

### 我的 GPU 应该使用什么分辨率？

没有适用于某款 GPU 的"最佳"分辨率。最大可用分辨率取决于您的具体模型类型、VRAM 和工作流复杂度。以下是一般参考：

- **8 GB VRAM（如 RTX 3070、RTX 4060）：** 512x512 至 1024x1024（SD1.5/FLUX）；视频模型使用更小尺寸
- **12-16 GB VRAM（如 RTX 4070、RTX 3080、RTX 4080）：** 768x768 至 1280x1280（图片）；视频 512x512（短片段）
- **24 GB VRAM（如 RTX 4090、RTX 3090、A5000）：** 1024x1024 至 1536x1536（图片）；视频可达 640x640 或更长片段
- **48 GB+ VRAM（如 A6000、A100）：** 最高分辨率，支持多工作流批处理

从所用模型的默认尺寸开始，逐渐增大。如果内存不足，请降低分辨率、切换到 fp8 量化模型或减小 batch size。

### 噪声种子（noise seed）是什么？

**噪声种子**控制采样器使用的随机噪波图案。使用相同的种子、模型、检查点和参数，每次都会得到完全一致的结果。这在以下场景非常有用：

- **复现特定输出** — 将种子随工作流一起分享
- **对比参数变化** — 固定种子，只改变一个设置以隔离其效果
- **批量探索** — 改变种子以生成不同的输出

种子可以在 [RandomNoise](/zh/built-in-nodes/RandomNoise) 等节点中设置，也可以在 [KSampler](/zh/built-in-nodes/KSampler) 和 [SamplerCustom](/zh/built-in-nodes/SamplerCustom) 的 `noise_seed` 参数中设置。

@coderabbitai coderabbitai Bot Jul 7, 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.

🎯 Functional Correctness | 🟠 Major | ⚡ Quick win

Fix the KSampler parameter name.

KSampler uses seed, not noise_seed; only RandomNoise and SamplerCustom use noise_seed. Otherwise this points readers to the wrong setting.

Suggested rewrite 
-种子可以在 [RandomNoise](/zh/built-in-nodes/RandomNoise) 等节点中设置，也可以在 [KSampler](/zh/built-in-nodes/KSampler) 和 [SamplerCustom](/zh/built-in-nodes/SamplerCustom) 的 `noise_seed` 参数中设置。
+种子可以在 [RandomNoise](/zh/built-in-nodes/RandomNoise) 等节点中设置，也可以在 [KSampler](/zh/built-in-nodes/KSampler) 的 `seed` 参数和 [SamplerCustom](/zh/built-in-nodes/SamplerCustom) 的 `noise_seed` 参数中设置。
📝 Committable suggestion

‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.

Suggested change
种子可以在 [RandomNoise](/zh/built-in-nodes/RandomNoise) 等节点中设置，也可以在 [KSampler](/zh/built-in-nodes/KSampler) 和 [SamplerCustom](/zh/built-in-nodes/SamplerCustom) 的 `noise_seed` 参数中设置。
种子可以在 [RandomNoise](/zh/built-in-nodes/RandomNoise) 等节点中设置，也可以在 [KSampler](/zh/built-in-nodes/KSampler) 的 `seed` 参数和 [SamplerCustom](/zh/built-in-nodes/SamplerCustom) 的 `noise_seed` 参数中设置。
🤖 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` at line 500, The parameter reference is
wrong in the troubleshooting text: KSampler does not use noise_seed, it uses
seed. Update the sentence in overview.mdx so that RandomNoise and SamplerCustom
are described as using noise_seed, while KSampler is referenced with seed,
keeping the existing node links and wording clear for readers.


## 社区资源

- **官方论坛：** [forum.comfy.org](https://forum.comfy.org/)
Expand Down
Loading