Skip to content
Merged
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
27 changes: 26 additions & 1 deletion ja/tutorials/image/qwen/qwen-image-layered.mdx
Original file line number Diff line number Diff line change
Expand Up @@ -2,13 +2,14 @@
title: "Qwen-Image-Layered ComfyUI ワークフロー例"
description: "Qwen-Image-Layered は、画像を複数の RGBA レイヤーに分解できるモデルであり、レイヤー分解を通じて本質的な編集可能性を実現します。"
sidebarTitle: "Qwen-Image-Layered"
translationSourceHash: bf2f2000
translationSourceHash: dba6b09a
translationFrom: tutorials/image/qwen/qwen-image-layered.mdx
translationBlockHashes:
"_intro": 19900234
"Qwen-Image-Layered workflow": ba937275
"Model links": 98d12555
"FP8 version": 6bffdd17
"Layers and output": 2419fd13
"Workflow settings": b0f81aa2
---

Expand Down Expand Up @@ -59,11 +60,11 @@
```
📂 ComfyUI/
├── 📂 models/
│ ├── 📂 text_encoders/

Check warning on line 63 in ja/tutorials/image/qwen/qwen-image-layered.mdx

View check run for this annotation

Mintlify / Mintlify Validation (dripart) - vale-spellcheck

ja/tutorials/image/qwen/qwen-image-layered.mdx#L63

Did you really mean 'text_encoders'?
│ │ └── qwen_2.5_vl_7b_fp8_scaled.safetensors
│ ├── 📂 diffusion_models/

Check warning on line 65 in ja/tutorials/image/qwen/qwen-image-layered.mdx

View check run for this annotation

Mintlify / Mintlify Validation (dripart) - vale-spellcheck

ja/tutorials/image/qwen/qwen-image-layered.mdx#L65

Did you really mean 'diffusion_models'?
│ │ └── qwen_image_layered_bf16.safetensors
│ └── 📂 vae/

Check warning on line 67 in ja/tutorials/image/qwen/qwen-image-layered.mdx

View check run for this annotation

Mintlify / Mintlify Validation (dripart) - vale-spellcheck

ja/tutorials/image/qwen/qwen-image-layered.mdx#L67

Did you really mean 'vae'?
│ └── qwen_image_layered_vae.safetensors
```

Expand All @@ -75,6 +76,30 @@

その後、[サブグラフ](/ja/interface/features/subgraph)内の **Load Diffusion model** ノードを更新し、このファイルを使用するように設定してください。

## レイヤーと出力

レイヤーの数は、[サブグラフ](/ja/interface/features/subgraph)内の **Empty Qwen Image Layered Latent** ノードにある `layers` ウィジェットで設定します。

Check warning on line 81 in ja/tutorials/image/qwen/qwen-image-layered.mdx

View check run for this annotation

Mintlify / Mintlify Validation (dripart) - vale-spellcheck

ja/tutorials/image/qwen/qwen-image-layered.mdx#L81

Did you really mean 'Qwen'?

このモデルはレイヤーだけでなく完全な画像も生成するため、1 回の生成は常に `layers + 1` 枚の画像にデコードされます:

| `layers` | デコードされる画像数 | 内容 |
| --- | --- | --- |
| `0` | 1 | 完全な画像のみ |
| `2`(テンプレートの既定値) | 3 | 完全な画像、続いて 2 枚のレイヤー |
| `5` | 6 | 完全な画像、続いて 5 枚のレイヤー |

**最初の画像は完全な画像であり、レイヤーではありません。** 画像からレイヤーへのワークフローでは入力画像を再現したものになるため、レイヤーだけが必要な場合は破棄してください。`layers` には `0` を指定でき、その場合はこの画像だけが得られます。

**すべてのレイヤーを合成し直すと完全な画像が再現されます。** これは確認に使えます。レイヤーを重ねても最初の画像が再現されない場合、分解は意図したとおりに機能していません。

### レイヤーが個別の画像になる仕組み

**Empty Qwen Image Layered Latent** ノードは `[batch_size, 16, layers + 1, height // 8, width // 8]` という形状の 5D Latent を確保します。レイヤーは 3 番目の軸に並び、これは映像モデルがフレームを置くのと同じ時間軸です。**LatentCutToBatch** ノードの `dim` を `t` に設定するとその軸がバッチ次元へ移されるため、**VAE Decode** の後は各レイヤーがバッチ内の個別の画像になります。

Check warning on line 97 in ja/tutorials/image/qwen/qwen-image-layered.mdx

View check run for this annotation

Mintlify / Mintlify Validation (dripart) - vale-spellcheck

ja/tutorials/image/qwen/qwen-image-layered.mdx#L97

Did you really mean 'Qwen'?

したがって、レイヤーの重なり順はバッチ内のインデックスそのものであり、インデックス 0 の完全な画像から数えます。z-index フィールドも、その順序を保持するレイヤーごとのメタデータも存在しないため、バッチを並べ替えたりフィルタリングしたりすることは、そのままレイヤーの並べ替えになります。

Qwen-Image-Layered の VAE は 4 チャンネルにデコードするため、デコードされたレイヤーはアルファチャンネルを持ちます。

## ワークフローの設定

### サンプラー設定
Expand Down
27 changes: 26 additions & 1 deletion ko/tutorials/image/qwen/qwen-image-layered.mdx
Original file line number Diff line number Diff line change
Expand Up @@ -2,13 +2,14 @@
title: "Qwen-Image-Layered ComfyUI 워크플로우 예시"
description: "Qwen-Image-Layered는 이미지를 여러 개의 RGBA 레이어로 분해할 수 있는 모델로, 레이어 분해를 통해 본질적인 편집 가능성을 제공합니다."
sidebarTitle: "Qwen-Image-Layered"
translationSourceHash: bf2f2000
translationSourceHash: dba6b09a
translationFrom: tutorials/image/qwen/qwen-image-layered.mdx
translationBlockHashes:
"_intro": 19900234
"Qwen-Image-Layered workflow": ba937275
"Model links": 98d12555
"FP8 version": 6bffdd17
"Layers and output": 2419fd13
"Workflow settings": b0f81aa2
---

Expand Down Expand Up @@ -59,11 +60,11 @@
```
📂 ComfyUI/
├── 📂 models/
│ ├── 📂 text_encoders/

Check warning on line 63 in ko/tutorials/image/qwen/qwen-image-layered.mdx

View check run for this annotation

Mintlify / Mintlify Validation (dripart) - vale-spellcheck

ko/tutorials/image/qwen/qwen-image-layered.mdx#L63

Did you really mean 'text_encoders'?
│ │ └── qwen_2.5_vl_7b_fp8_scaled.safetensors
│ ├── 📂 diffusion_models/

Check warning on line 65 in ko/tutorials/image/qwen/qwen-image-layered.mdx

View check run for this annotation

Mintlify / Mintlify Validation (dripart) - vale-spellcheck

ko/tutorials/image/qwen/qwen-image-layered.mdx#L65

Did you really mean 'diffusion_models'?
│ │ └── qwen_image_layered_bf16.safetensors
│ └── 📂 vae/

Check warning on line 67 in ko/tutorials/image/qwen/qwen-image-layered.mdx

View check run for this annotation

Mintlify / Mintlify Validation (dripart) - vale-spellcheck

ko/tutorials/image/qwen/qwen-image-layered.mdx#L67

Did you really mean 'vae'?
│ └── qwen_image_layered_vae.safetensors
```

Expand All @@ -75,6 +76,30 @@

그런 다음 [서브그래프](/ko/interface/features/subgraph) 내의 **Load Diffusion model** 노드를 업데이트하여 이를 사용하세요.

## 레이어와 출력

레이어 수는 [서브그래프](/ko/interface/features/subgraph) 내의 **Empty Qwen Image Layered Latent** 노드에 있는 `layers` 위젯으로 설정합니다.

Check warning on line 81 in ko/tutorials/image/qwen/qwen-image-layered.mdx

View check run for this annotation

Mintlify / Mintlify Validation (dripart) - vale-spellcheck

ko/tutorials/image/qwen/qwen-image-layered.mdx#L81

Did you really mean 'Qwen'?

이 모델은 레이어와 함께 전체 이미지도 다시 생성하므로, 한 번의 생성은 항상 `layers + 1`개의 이미지로 디코딩됩니다.

| `layers` | 디코딩되는 이미지 수 | 내용 |
| --- | --- | --- |
| `0` | 1 | 전체 이미지만 |
| `2` (템플릿 기본값) | 3 | 전체 이미지, 그다음 레이어 2개 |
| `5` | 6 | 전체 이미지, 그다음 레이어 5개 |

**첫 번째 이미지는 전체 이미지이며 레이어가 아닙니다.** 이미지를 레이어로 분해하는 워크플로우에서는 입력 이미지를 재현한 것이므로, 레이어만 필요하다면 이 이미지는 버리세요. `layers`에는 `0`을 지정할 수 있으며, 이 경우 해당 이미지 하나만 얻게 됩니다.

**모든 레이어를 다시 합성하면 전체 이미지가 재현됩니다.** 이를 검증에 사용하세요. 레이어를 쌓아도 첫 번째 이미지가 재현되지 않는다면 분해가 의도대로 이루어지지 않은 것입니다.

### 레이어가 개별 이미지가 되는 방식

**Empty Qwen Image Layered Latent** 노드는 `[batch_size, 16, layers + 1, height // 8, width // 8]` 형태의 5D Latent를 할당합니다. 레이어는 세 번째 축에 놓이며, 이는 비디오 모델이 프레임을 두는 것과 같은 시간 축입니다. **LatentCutToBatch** 노드의 `dim`을 `t`로 설정하면 그 축이 배치 차원으로 옮겨지므로, **VAE Decode** 이후 각 레이어는 배치 안의 개별 이미지가 됩니다.

Check warning on line 97 in ko/tutorials/image/qwen/qwen-image-layered.mdx

View check run for this annotation

Mintlify / Mintlify Validation (dripart) - vale-spellcheck

ko/tutorials/image/qwen/qwen-image-layered.mdx#L97

Did you really mean 'Qwen'?

따라서 레이어의 쌓임 순서는 배치 안에서의 인덱스 그 자체이며, 인덱스 0의 전체 이미지부터 셉니다. z-index 필드도, 그 순서를 담는 레이어별 메타데이터도 없으므로 배치를 재정렬하거나 걸러내는 것은 곧 레이어를 재정렬하는 것입니다.

Qwen-Image-Layered VAE는 4채널로 디코딩하므로 디코딩된 레이어는 알파 채널을 가집니다.

## 워크플로우 설정

### 샘플러 설정
Expand Down
24 changes: 24 additions & 0 deletions tutorials/image/qwen/qwen-image-layered.mdx
Original file line number Diff line number Diff line change
@@ -1,15 +1,15 @@
---
title: "Qwen-Image-Layered ComfyUI Workflow Example"
description: "Qwen-Image-Layered is a model capable of decomposing an image into multiple RGBA layers, enabling inherent editability through layer decomposition."

Check warning on line 3 in tutorials/image/qwen/qwen-image-layered.mdx

View check run for this annotation

Mintlify / Mintlify Validation (dripart) - vale-spellcheck

tutorials/image/qwen/qwen-image-layered.mdx#L3

Did you really mean 'editability'?
sidebarTitle: "Qwen-Image-Layered"
---

import UpdateReminder from '/snippets/tutorials/update-reminder.mdx'

**Qwen-Image-Layered** is a model developed by Alibaba's Qwen team that can decompose an image into multiple RGBA layers. This layered representation unlocks inherent editability: each layer can be independently manipulated without affecting other content.

Check warning on line 9 in tutorials/image/qwen/qwen-image-layered.mdx

View check run for this annotation

Mintlify / Mintlify Validation (dripart) - vale-spellcheck

tutorials/image/qwen/qwen-image-layered.mdx#L9

Did you really mean 'Qwen'?

Check warning on line 9 in tutorials/image/qwen/qwen-image-layered.mdx

View check run for this annotation

Mintlify / Mintlify Validation (dripart) - vale-spellcheck

tutorials/image/qwen/qwen-image-layered.mdx#L9

Did you really mean 'Alibaba's'?

Check warning on line 9 in tutorials/image/qwen/qwen-image-layered.mdx

View check run for this annotation

Mintlify / Mintlify Validation (dripart) - vale-spellcheck

tutorials/image/qwen/qwen-image-layered.mdx#L9

Did you really mean 'editability'?

**Key Features**:
- **Inherent Editability**: Each layer can be independently manipulated without affecting other content

Check warning on line 12 in tutorials/image/qwen/qwen-image-layered.mdx

View check run for this annotation

Mintlify / Mintlify Validation (dripart) - vale-spellcheck

tutorials/image/qwen/qwen-image-layered.mdx#L12

Did you really mean 'Editability'?
- **High-Fidelity Elementary Operations**: Supports resizing, repositioning, and recoloring with physical isolation of semantic components
- **Variable-Layer Decomposition**: Not limited to a fixed number of layers - decompose into 3, 4, 8, or more layers as needed
- **Recursive Decomposition**: Any layer can be further decomposed, enabling infinite decomposition depth
Expand Down Expand Up @@ -50,11 +50,11 @@
```
📂 ComfyUI/
├── 📂 models/
│ ├── 📂 text_encoders/

Check warning on line 53 in tutorials/image/qwen/qwen-image-layered.mdx

View check run for this annotation

Mintlify / Mintlify Validation (dripart) - vale-spellcheck

tutorials/image/qwen/qwen-image-layered.mdx#L53

Did you really mean 'text_encoders'?
│ │ └── qwen_2.5_vl_7b_fp8_scaled.safetensors
│ ├── 📂 diffusion_models/

Check warning on line 55 in tutorials/image/qwen/qwen-image-layered.mdx

View check run for this annotation

Mintlify / Mintlify Validation (dripart) - vale-spellcheck

tutorials/image/qwen/qwen-image-layered.mdx#L55

Did you really mean 'diffusion_models'?
│ │ └── qwen_image_layered_bf16.safetensors
│ └── 📂 vae/

Check warning on line 57 in tutorials/image/qwen/qwen-image-layered.mdx

View check run for this annotation

Mintlify / Mintlify Validation (dripart) - vale-spellcheck

tutorials/image/qwen/qwen-image-layered.mdx#L57

Did you really mean 'vae'?
│ └── qwen_image_layered_vae.safetensors
```

Expand All @@ -66,6 +66,30 @@

Then update the **Load Diffusion model** node inside the [Subgraph](/interface/features/subgraph) to use it.

## Layers and output

The number of layers is set by the `layers` widget on the **Empty Qwen Image Layered Latent** node inside the [Subgraph](/interface/features/subgraph).

Check warning on line 71 in tutorials/image/qwen/qwen-image-layered.mdx

View check run for this annotation

Mintlify / Mintlify Validation (dripart) - vale-spellcheck

tutorials/image/qwen/qwen-image-layered.mdx#L71

Did you really mean 'Qwen'?

This model regenerates the full image as well as the layers, so a generation always decodes to `layers + 1` images:

| `layers` | Images decoded | Contents |
| --- | --- | --- |
| `0` | 1 | The full image only |
| `2` (template default) | 3 | The full image, then 2 layers |
| `5` | 6 | The full image, then 5 layers |

**The first image is the full image, not a layer.** In the image to layers workflow it reproduces the input image, so discard it when you only want the layers. `layers` accepts `0`, which gives you that image on its own.

**Compositing all of the layers back together recreates the full image.** Use it as a check: if stacking the layers does not reproduce the first image, the decomposition did not do what you wanted.

### How the layers become separate images

The **Empty Qwen Image Layered Latent** node allocates a 5D latent shaped `[batch_size, 16, layers + 1, height // 8, width // 8]`. The layers sit on the third axis, the same temporal axis that video models use for frames. The **LatentCutToBatch** node with `dim` set to `t` moves that axis into the batch dimension, so after **VAE Decode** each layer is a separate image in the batch.

Check warning on line 87 in tutorials/image/qwen/qwen-image-layered.mdx

View check run for this annotation

Mintlify / Mintlify Validation (dripart) - vale-spellcheck

tutorials/image/qwen/qwen-image-layered.mdx#L87

Did you really mean 'Qwen'?

A layer's position in the stack is therefore its index in the batch, counting from the full image at index 0. There is no z-index field and no per-layer metadata carrying that order, so reordering or filtering the batch reorders the layers.

The Qwen-Image-Layered VAE decodes to 4 channels, so the decoded layers carry an alpha channel.

## Workflow settings

### Sampler settings
Expand Down
27 changes: 26 additions & 1 deletion zh/tutorials/image/qwen/qwen-image-layered.mdx
Original file line number Diff line number Diff line change
Expand Up @@ -2,13 +2,14 @@
title: "Qwen-Image-Layered ComfyUI 工作流示例"
description: "Qwen-Image-Layered 是一个能够将图像分解为多个 RGBA 图层的模型,通过图层分解实现固有的可编辑性。"
sidebarTitle: "Qwen-Image-Layered"
translationSourceHash: bf2f2000
translationSourceHash: dba6b09a
translationFrom: tutorials/image/qwen/qwen-image-layered.mdx
translationBlockHashes:
"_intro": 19900234
"Qwen-Image-Layered workflow": ba937275
"Model links": 98d12555
"FP8 version": 6bffdd17
"Layers and output": 2419fd13
"Workflow settings": b0f81aa2
---

Expand Down Expand Up @@ -59,11 +60,11 @@
```
📂 ComfyUI/
├── 📂 models/
│ ├── 📂 text_encoders/

Check warning on line 63 in zh/tutorials/image/qwen/qwen-image-layered.mdx

View check run for this annotation

Mintlify / Mintlify Validation (dripart) - vale-spellcheck

zh/tutorials/image/qwen/qwen-image-layered.mdx#L63

Did you really mean 'text_encoders'?
│ │ └── qwen_2.5_vl_7b_fp8_scaled.safetensors
│ ├── 📂 diffusion_models/

Check warning on line 65 in zh/tutorials/image/qwen/qwen-image-layered.mdx

View check run for this annotation

Mintlify / Mintlify Validation (dripart) - vale-spellcheck

zh/tutorials/image/qwen/qwen-image-layered.mdx#L65

Did you really mean 'diffusion_models'?
│ │ └── qwen_image_layered_bf16.safetensors
│ └── 📂 vae/

Check warning on line 67 in zh/tutorials/image/qwen/qwen-image-layered.mdx

View check run for this annotation

Mintlify / Mintlify Validation (dripart) - vale-spellcheck

zh/tutorials/image/qwen/qwen-image-layered.mdx#L67

Did you really mean 'vae'?
│ └── qwen_image_layered_vae.safetensors
```

Expand All @@ -75,6 +76,30 @@

然后更新[子图](/zh/interface/features/subgraph)中的 **Load Diffusion model** 节点来使用它。

## 图层和输出

图层数量由[子图](/zh/interface/features/subgraph)内 **Empty Qwen Image Layered Latent** 节点上的 `layers` 组件设置。

Check warning on line 81 in zh/tutorials/image/qwen/qwen-image-layered.mdx

View check run for this annotation

Mintlify / Mintlify Validation (dripart) - vale-spellcheck

zh/tutorials/image/qwen/qwen-image-layered.mdx#L81

Did you really mean 'Qwen'?

该模型会在生成图层的同时重新生成完整图像,因此一次生成总是解码出 `layers + 1` 张图像:

| `layers` | 解码出的图像数 | 内容 |
| --- | --- | --- |
| `0` | 1 | 仅完整图像 |
| `2`(模板默认值) | 3 | 完整图像,然后是 2 个图层 |
| `5` | 6 | 完整图像,然后是 5 个图层 |

**第一张图像是完整图像,而不是图层。** 在图像转图层的工作流中,它重现的是输入图像,因此当你只需要图层时应将其丢弃。`layers` 可以设为 `0`,此时只会得到这一张图像。

**将所有图层合成回去可以重建完整图像。** 可以用它来检查:如果堆叠图层无法重现第一张图像,说明分解没有达到预期效果。

### 图层如何变成单独的图像

**Empty Qwen Image Layered Latent** 节点会分配一个形状为 `[batch_size, 16, layers + 1, height // 8, width // 8]` 的 5D Latent。图层位于第三个轴上,也就是视频模型用于存放帧的那个时间轴。将 **LatentCutToBatch** 节点的 `dim` 设置为 `t`,会把该轴移动到批次维度上,因此在 **VAE Decode** 之后,每个图层都是批次中一张单独的图像。

Check warning on line 97 in zh/tutorials/image/qwen/qwen-image-layered.mdx

View check run for this annotation

Mintlify / Mintlify Validation (dripart) - vale-spellcheck

zh/tutorials/image/qwen/qwen-image-layered.mdx#L97

Did you really mean 'Qwen'?

因此,图层在堆栈中的位置就是它在批次中的索引,从索引 0 处的完整图像开始计数。这里没有 z-index 字段,也没有承载该顺序的逐图层元数据,因此重新排序或过滤批次就等于重新排序图层。

Qwen-Image-Layered VAE 解码为 4 个通道,因此解码出的图层带有 Alpha 通道。

## 工作流设置

### 采样器设置
Expand Down
Loading