diff --git a/.github/scripts/cms/staging/cloud/en/changelog/index.mdx b/.github/scripts/cms/staging/cloud/en/changelog/index.mdx
index 9c53c5bc1f..6262a1a3c6 100644
--- a/.github/scripts/cms/staging/cloud/en/changelog/index.mdx
+++ b/.github/scripts/cms/staging/cloud/en/changelog/index.mdx
@@ -4,6 +4,22 @@ cmsStaging: true
 ---
 
 
+<Update label="v0.40.0" description="October 13, 2026">
+
+**New Open-Source Model Support**
+* [**Qwen-Image 2.1 Turbo**](https://cloud.comfy.org/?template=image_qwen_image_2_1_turbo_t2i): Added the 8-step Turbo model
+
+**Partner Node Updates**
+* [**Fish Audio Drama 3**](https://cloud.comfy.org/?template=api_fishaudio_drama3_dialogue): Added Drama 3 voice direction model
+* [**HeyGen Video 1.0**](https://cloud.comfy.org/?template=api_heygen_video_1_r2v): Added 2K resolution
+* [**Quiver Arrow 1 retirement**](https://cloud.comfy.org/?template=api_quiver_arrow2_text_to_svg): Arrow 1-series models stop working on October 16; use Arrow 2
+* [**Luma Ray 2 retirement**](https://cloud.comfy.org/?template=api_luma_ray3_3_i2v): Ray 2 nodes stop working on October 24; use Ray 3.2
+
+**New Node Updates**
+* [**NVIDIA RTX Video Enhance**](https://blog.comfy.org/p/nvidia-vfx-nodes-for-video-upscaling): Upscale, frame generation, and SDR-to-HDR in one pass
+
+</Update>
+
 <Update label="v0.39.1" description="October 7, 2026">
 
 **Partner Node Updates**
diff --git a/.github/scripts/cms/staging/cloud/es/changelog/index.mdx b/.github/scripts/cms/staging/cloud/es/changelog/index.mdx
index 906b077e17..3c3f05f23b 100644
--- a/.github/scripts/cms/staging/cloud/es/changelog/index.mdx
+++ b/.github/scripts/cms/staging/cloud/es/changelog/index.mdx
@@ -4,6 +4,22 @@ cmsStaging: true
 ---
 
 
+<Update label="v0.40.0" description="13 de octubre de 2026">
+
+**Soporte para nuevos modelos de código abierto**
+* [**Qwen-Image 2.1 Turbo**](https://cloud.comfy.org/?template=image_qwen_image_2_1_turbo_t2i): Se añadió el modelo Turbo de 8 pasos
+
+**Actualizaciones de nodos de socios**
+* [**Fish Audio Drama 3**](https://cloud.comfy.org/?template=api_fishaudio_drama3_dialogue): Se añadió el modelo de dirección de voz Drama 3
+* [**HeyGen Video 1.0**](https://cloud.comfy.org/?template=api_heygen_video_1_r2v): Se añadió resolución 2K
+* [**Retiro de Quiver Arrow 1**](https://cloud.comfy.org/?template=api_quiver_arrow2_text_to_svg): Los modelos de la serie Arrow 1 dejan de funcionar el 16 de octubre; use Arrow 2
+* [**Retiro de Luma Ray 2**](https://cloud.comfy.org/?template=api_luma_ray3_3_i2v): Los nodos Ray 2 dejan de funcionar el 24 de octubre; use Ray 3.2
+
+**Actualizaciones de nuevos nodos**
+* [**NVIDIA RTX Video Enhance**](https://blog.comfy.org/p/nvidia-vfx-nodes-for-video-upscaling): Escalado, generación de fotogramas y conversión de SDR a HDR en una sola pasada
+
+</Update>
+
 <Update label="v0.39.1" description="7 de octubre de 2026">
 
 **Actualizaciones de nodos de socios**
diff --git a/.github/scripts/cms/staging/cloud/fr/changelog/index.mdx b/.github/scripts/cms/staging/cloud/fr/changelog/index.mdx
index 650341d761..5dc04c4d3f 100644
--- a/.github/scripts/cms/staging/cloud/fr/changelog/index.mdx
+++ b/.github/scripts/cms/staging/cloud/fr/changelog/index.mdx
@@ -4,6 +4,22 @@ cmsStaging: true
 ---
 
 
+<Update label="v0.40.0" description="13 octobre 2026">
+
+**Prise en charge de nouveaux modèles open source**
+* [**Qwen-Image 2.1 Turbo**](https://cloud.comfy.org/?template=image_qwen_image_2_1_turbo_t2i) : Ajout du modèle Turbo en 8 étapes
+
+**Mises à jour des nœuds partenaires**
+* [**Fish Audio Drama 3**](https://cloud.comfy.org/?template=api_fishaudio_drama3_dialogue) : Ajout du modèle de direction vocale Drama 3
+* [**HeyGen Video 1.0**](https://cloud.comfy.org/?template=api_heygen_video_1_r2v) : Ajout de la résolution 2K
+* [**Retrait de Quiver Arrow 1**](https://cloud.comfy.org/?template=api_quiver_arrow2_text_to_svg) : Les modèles de la série Arrow 1 cessent de fonctionner le 16 octobre ; utilisez Arrow 2
+* [**Retrait de Luma Ray 2**](https://cloud.comfy.org/?template=api_luma_ray3_3_i2v) : Les nœuds Ray 2 cessent de fonctionner le 24 octobre ; utilisez Ray 3.2
+
+**Mises à jour des nouveaux nœuds**
+* [**NVIDIA RTX Video Enhance**](https://blog.comfy.org/p/nvidia-vfx-nodes-for-video-upscaling) : Mise à l’échelle, génération d’images et conversion SDR vers HDR en une seule passe
+
+</Update>
+
 <Update label="v0.39.1" description="7 octobre 2026">
 
 **Mises à jour des nœuds partenaires**
diff --git a/.github/scripts/cms/staging/cloud/ja/changelog/index.mdx b/.github/scripts/cms/staging/cloud/ja/changelog/index.mdx
index 6b698faba1..e47cbf8d0f 100644
--- a/.github/scripts/cms/staging/cloud/ja/changelog/index.mdx
+++ b/.github/scripts/cms/staging/cloud/ja/changelog/index.mdx
@@ -4,6 +4,22 @@ cmsStaging: true
 ---
 
 
+<Update label="v0.40.0" description="2026年10月13日">
+
+**新しいオープンソースモデルのサポート**
+* [**Qwen-Image 2.1 Turbo**](https://cloud.comfy.org/?template=image_qwen_image_2_1_turbo_t2i): 8ステップのTurboモデルを追加
+
+**パートナーノードの更新**
+* [**Fish Audio Drama 3**](https://cloud.comfy.org/?template=api_fishaudio_drama3_dialogue): Drama 3音声演出モデルを追加
+* [**HeyGen Video 1.0**](https://cloud.comfy.org/?template=api_heygen_video_1_r2v): 2K解像度を追加
+* [**Quiver Arrow 1 提供終了**](https://cloud.comfy.org/?template=api_quiver_arrow2_text_to_svg): Arrow 1シリーズのモデルは10月16日に動作しなくなります。Arrow 2を使用してください
+* [**Luma Ray 2 提供終了**](https://cloud.comfy.org/?template=api_luma_ray3_3_i2v): Ray 2ノードは10月24日に動作しなくなります。Ray 3.2を使用してください
+
+**新しいノードの更新**
+* [**NVIDIA RTX Video Enhance**](https://blog.comfy.org/p/nvidia-vfx-nodes-for-video-upscaling): アップスケール、フレーム生成、SDRからHDRへの変換を1パスで実行
+
+</Update>
+
 <Update label="v0.39.1" description="2026年10月7日">
 
 **パートナーノードの更新**
diff --git a/.github/scripts/cms/staging/cloud/ko/changelog/index.mdx b/.github/scripts/cms/staging/cloud/ko/changelog/index.mdx
index a1220bc67f..45ed64e3c9 100644
--- a/.github/scripts/cms/staging/cloud/ko/changelog/index.mdx
+++ b/.github/scripts/cms/staging/cloud/ko/changelog/index.mdx
@@ -4,6 +4,22 @@ cmsStaging: true
 ---
 
 
+<Update label="v0.40.0" description="2026년 10월 13일">
+
+**새로운 오픈 소스 모델 지원**
+* [**Qwen-Image 2.1 Turbo**](https://cloud.comfy.org/?template=image_qwen_image_2_1_turbo_t2i): 8단계 Turbo 모델을 추가했습니다
+
+**파트너 노드 업데이트**
+* [**Fish Audio Drama 3**](https://cloud.comfy.org/?template=api_fishaudio_drama3_dialogue): Drama 3 음성 연출 모델을 추가했습니다
+* [**HeyGen Video 1.0**](https://cloud.comfy.org/?template=api_heygen_video_1_r2v): 2K 해상도를 추가했습니다
+* [**Quiver Arrow 1 지원 종료**](https://cloud.comfy.org/?template=api_quiver_arrow2_text_to_svg): Arrow 1 시리즈 모델은 10월 16일부터 작동이 중지됩니다; Arrow 2를 사용하세요
+* [**Luma Ray 2 지원 종료**](https://cloud.comfy.org/?template=api_luma_ray3_3_i2v): Ray 2 노드는 10월 24일부터 작동이 중지됩니다; Ray 3.2를 사용하세요
+
+**새로운 노드 업데이트**
+* [**NVIDIA RTX Video Enhance**](https://blog.comfy.org/p/nvidia-vfx-nodes-for-video-upscaling): 업스케일, 프레임 생성 및 SDR-to-HDR을 한 번에 처리
+
+</Update>
+
 <Update label="v0.39.1" description="2026년 10월 7일">
 
 **파트너 노드 업데이트**
diff --git a/.github/scripts/cms/staging/cloud/ru/changelog/index.mdx b/.github/scripts/cms/staging/cloud/ru/changelog/index.mdx
index df4e9d0cc7..8cca925996 100644
--- a/.github/scripts/cms/staging/cloud/ru/changelog/index.mdx
+++ b/.github/scripts/cms/staging/cloud/ru/changelog/index.mdx
@@ -4,6 +4,22 @@ cmsStaging: true
 ---
 
 
+<Update label="v0.40.0" description="13 октября 2026">
+
+**Поддержка новых открытых моделей**
+* [**Qwen-Image 2.1 Turbo**](https://cloud.comfy.org/?template=image_qwen_image_2_1_turbo_t2i): Добавлена 8-шаговая модель Turbo
+
+**Обновления партнёрских нод**
+* [**Fish Audio Drama 3**](https://cloud.comfy.org/?template=api_fishaudio_drama3_dialogue): Добавлена модель голосовой режиссуры Drama 3
+* [**HeyGen Video 1.0**](https://cloud.comfy.org/?template=api_heygen_video_1_r2v): Добавлено разрешение 2K
+* [**Прекращение поддержки Quiver Arrow 1**](https://cloud.comfy.org/?template=api_quiver_arrow2_text_to_svg): Модели серии Arrow 1 перестанут работать 16 октября; используйте Arrow 2
+* [**Прекращение поддержки Luma Ray 2**](https://cloud.comfy.org/?template=api_luma_ray3_3_i2v): Ноды Ray 2 перестанут работать 24 октября; используйте Ray 3.2
+
+**Обновления новых нод**
+* [**NVIDIA RTX Video Enhance**](https://blog.comfy.org/p/nvidia-vfx-nodes-for-video-upscaling): Апскейл, генерация кадров и преобразование SDR в HDR за один проход
+
+</Update>
+
 <Update label="v0.39.1" description="7 октября 2026 г.">
 
 **Обновления партнёрских узлов**
diff --git a/.github/scripts/cms/staging/cloud/zh/changelog/index.mdx b/.github/scripts/cms/staging/cloud/zh/changelog/index.mdx
index cc23d3c197..dc6f2649f2 100644
--- a/.github/scripts/cms/staging/cloud/zh/changelog/index.mdx
+++ b/.github/scripts/cms/staging/cloud/zh/changelog/index.mdx
@@ -4,6 +4,22 @@ cmsStaging: true
 ---
 
 
+<Update label="v0.40.0" description="2026年10月13日">
+
+**新的开源模型支持**
+* [**Qwen-Image 2.1 Turbo**](https://cloud.comfy.org/?template=image_qwen_image_2_1_turbo_t2i)：新增 8 步 Turbo 模型
+
+**合作伙伴节点更新**
+* [**Fish Audio Drama 3**](https://cloud.comfy.org/?template=api_fishaudio_drama3_dialogue)：新增 Drama 3 语音指导模型
+* [**HeyGen Video 1.0**](https://cloud.comfy.org/?template=api_heygen_video_1_r2v)：新增 2K 分辨率
+* [**Quiver Arrow 1 退役**](https://cloud.comfy.org/?template=api_quiver_arrow2_text_to_svg)：Arrow 1 系列模型将于 10 月 16 日停止工作；请使用 Arrow 2
+* [**Luma Ray 2 退役**](https://cloud.comfy.org/?template=api_luma_ray3_3_i2v)：Ray 2 节点将于 10 月 24 日停止工作；请使用 Ray 3.2
+
+**新节点更新**
+* [**NVIDIA RTX Video Enhance**](https://blog.comfy.org/p/nvidia-vfx-nodes-for-video-upscaling)：一次处理即可完成放大、帧生成和 SDR 转 HDR
+
+</Update>
+
 <Update label="v0.39.1" description="2026年10月7日">
 
 **合作伙伴节点更新**
diff --git a/.github/scripts/cms/staging/en/changelog/index.mdx b/.github/scripts/cms/staging/en/changelog/index.mdx
index dc45a52b22..f2efd1ff84 100644
--- a/.github/scripts/cms/staging/en/changelog/index.mdx
+++ b/.github/scripts/cms/staging/en/changelog/index.mdx
@@ -4,6 +4,20 @@ cmsStaging: true
 ---
 
 
+<Update label="v0.40.0" description="October 13, 2026">
+
+**New Open-Source Model Support**
+* [**Qwen-Image 2.1 Turbo**](https://github.com/Comfy-Org/workflow_templates/pull/1328): 8-step accelerated checkpoint for text-to-image and image edit workflows
+
+**Partner Node Updates**
+* [**Fish Audio Drama 3**](https://github.com/Comfy-Org/ComfyUI/pull/16999): Voice direction model on Text to Speech, with up to 5 voices
+* [**Higgsfield Genjutsu Motion Transfer**](https://github.com/Comfy-Org/ComfyUI/pull/16913): Rebuilds a video's cast, location, and style while keeping motion
+* [**HeyGen Video 1.0**](https://github.com/Comfy-Org/ComfyUI/pull/16876): 2K resolution support added to the HeyGen Video nodes
+* [**Quiver Arrow 1 retirement**](https://github.com/Comfy-Org/ComfyUI/pull/16775): Arrow 1-series models stop working on October 16; switch to the V2 nodes
+* [**Luma Ray 2 retirement**](https://github.com/Comfy-Org/ComfyUI/pull/16741): Ray 2 nodes and templates stop working on October 24; use Ray 3.2
+
+</Update>
+
 <Update label="v0.39.1" description="October 7, 2026">
 
 **Partner Node Updates**
diff --git a/.github/scripts/cms/staging/es/changelog/index.mdx b/.github/scripts/cms/staging/es/changelog/index.mdx
index b12296895b..5f4f67c60b 100644
--- a/.github/scripts/cms/staging/es/changelog/index.mdx
+++ b/.github/scripts/cms/staging/es/changelog/index.mdx
@@ -4,6 +4,20 @@ cmsStaging: true
 ---
 
 
+<Update label="v0.40.0" description="13 de octubre de 2026">
+
+**Nuevo soporte para modelos de código abierto**
+* [**Qwen-Image 2.1 Turbo**](https://github.com/Comfy-Org/workflow_templates/pull/1328): checkpoint acelerado de 8 pasos para flujos de trabajo de texto a imagen y edición de imágenes
+
+**Actualizaciones de nodos de socios**
+* [**Fish Audio Drama 3**](https://github.com/Comfy-Org/ComfyUI/pull/16999): modelo de dirección de voz en Texto a voz, con hasta 5 voces
+* [**Higgsfield Genjutsu Motion Transfer**](https://github.com/Comfy-Org/ComfyUI/pull/16913): reconstruye el reparto, la ubicación y el estilo de un vídeo mientras conserva el movimiento
+* [**HeyGen Video 1.0**](https://github.com/Comfy-Org/ComfyUI/pull/16876): se ha añadido soporte de resolución 2K a los nodos de HeyGen Video
+* [**Retirada de Quiver Arrow 1**](https://github.com/Comfy-Org/ComfyUI/pull/16775): los modelos de la serie Arrow 1 dejarán de funcionar el 16 de octubre; cambia a los nodos V2
+* [**Retirada de Luma Ray 2**](https://github.com/Comfy-Org/ComfyUI/pull/16741): los nodos y las plantillas de Ray 2 dejarán de funcionar el 24 de octubre; usa Ray 3.2
+
+</Update>
+
 <Update label="v0.39.1" description="7 de octubre de 2026">
 
 **Actualizaciones de nodos de socios**
diff --git a/.github/scripts/cms/staging/fr/changelog/index.mdx b/.github/scripts/cms/staging/fr/changelog/index.mdx
index e8317ef88a..6a4824a519 100644
--- a/.github/scripts/cms/staging/fr/changelog/index.mdx
+++ b/.github/scripts/cms/staging/fr/changelog/index.mdx
@@ -4,6 +4,20 @@ cmsStaging: true
 ---
 
 
+<Update label="v0.40.0" description="13 octobre 2026">
+
+**Nouveau support de modèles open source**
+* [**Qwen-Image 2.1 Turbo**](https://github.com/Comfy-Org/workflow_templates/pull/1328): checkpoint accéléré en 8 étapes pour les workflows de génération d’images à partir de texte et d’édition d’images
+
+**Mises à jour des nœuds partenaires**
+* [**Fish Audio Drama 3**](https://github.com/Comfy-Org/ComfyUI/pull/16999): modèle de direction vocale sur Text to Speech, avec jusqu’à 5 voix
+* [**Higgsfield Genjutsu Motion Transfer**](https://github.com/Comfy-Org/ComfyUI/pull/16913): reconstruit le casting, le lieu et le style d’une vidéo tout en conservant le mouvement
+* [**HeyGen Video 1.0**](https://github.com/Comfy-Org/ComfyUI/pull/16876): prise en charge de la résolution 2K ajoutée aux nœuds HeyGen Video
+* [**Retrait de Quiver Arrow 1**](https://github.com/Comfy-Org/ComfyUI/pull/16775): les modèles de la série Arrow 1 cessent de fonctionner le 16 octobre ; passez aux nœuds V2
+* [**Retrait de Luma Ray 2**](https://github.com/Comfy-Org/ComfyUI/pull/16741): les nœuds et modèles Ray 2 cessent de fonctionner le 24 octobre ; utilisez Ray 3.2
+
+</Update>
+
 <Update label="v0.39.1" description="7 octobre 2026">
 
 **Mises à jour des nœuds partenaires**
diff --git a/.github/scripts/cms/staging/ja/changelog/index.mdx b/.github/scripts/cms/staging/ja/changelog/index.mdx
index d72a52cd08..ff45b3485e 100644
--- a/.github/scripts/cms/staging/ja/changelog/index.mdx
+++ b/.github/scripts/cms/staging/ja/changelog/index.mdx
@@ -4,6 +4,20 @@ cmsStaging: true
 ---
 
 
+<Update label="v0.40.0" description="2026年10月13日">
+
+**新しいオープンソースモデルのサポート**
+* [**Qwen-Image 2.1 Turbo**](https://github.com/Comfy-Org/workflow_templates/pull/1328): テキストから画像へおよび画像編集ワークフロー向けの8ステップ高速化チェックポイント
+
+**パートナーノードの更新**
+* [**Fish Audio Drama 3**](https://github.com/Comfy-Org/ComfyUI/pull/16999): テキスト読み上げの音声演出モデルで、最大5音声に対応
+* [**Higgsfield Genjutsu Motion Transfer**](https://github.com/Comfy-Org/ComfyUI/pull/16913): 動きを維持しながらビデオのキャスト、ロケーション、スタイルを再構築します
+* [**HeyGen Video 1.0**](https://github.com/Comfy-Org/ComfyUI/pull/16876): HeyGen Videoノードに2K解像度サポートを追加
+* [**Quiver Arrow 1の提供終了**](https://github.com/Comfy-Org/ComfyUI/pull/16775): Arrow 1シリーズのモデルは10月16日に動作しなくなります。V2ノードに切り替えてください
+* [**Luma Ray 2の提供終了**](https://github.com/Comfy-Org/ComfyUI/pull/16741): Ray 2ノードとテンプレートは10月24日に動作しなくなります。Ray 3.2を使用してください
+
+</Update>
+
 <Update label="v0.39.1" description="2026年10月7日">
 
 **パートナーノードの更新**
diff --git a/.github/scripts/cms/staging/ko/changelog/index.mdx b/.github/scripts/cms/staging/ko/changelog/index.mdx
index b4bf2f07e8..405a56b39c 100644
--- a/.github/scripts/cms/staging/ko/changelog/index.mdx
+++ b/.github/scripts/cms/staging/ko/changelog/index.mdx
@@ -4,6 +4,20 @@ cmsStaging: true
 ---
 
 
+<Update label="v0.40.0" description="2026년 10월 13일">
+
+**신규 오픈소스 모델 지원**
+* [**Qwen-Image 2.1 Turbo**](https://github.com/Comfy-Org/workflow_templates/pull/1328): 텍스트 기반 이미지 생성 및 이미지 편집 워크플로용 8단계 가속 체크포인트
+
+**파트너 노드 업데이트**
+* [**Fish Audio Drama 3**](https://github.com/Comfy-Org/ComfyUI/pull/16999): 텍스트 음성 변환용 음성 연출 모델, 최대 5개 음성 지원
+* [**Higgsfield Genjutsu Motion Transfer**](https://github.com/Comfy-Org/ComfyUI/pull/16913): 모션은 유지한 채 비디오의 출연진, 장소, 스타일을 재구성합니다
+* [**HeyGen Video 1.0**](https://github.com/Comfy-Org/ComfyUI/pull/16876): HeyGen Video 노드에 2K 해상도 지원 추가
+* [**Quiver Arrow 1 지원 종료**](https://github.com/Comfy-Org/ComfyUI/pull/16775): Arrow 1 시리즈 모델은 10월 16일부터 작동이 중지됩니다. V2 노드로 전환하세요
+* [**Luma Ray 2 지원 종료**](https://github.com/Comfy-Org/ComfyUI/pull/16741): Ray 2 노드와 템플릿은 10월 24일부터 작동이 중지됩니다. Ray 3.2를 사용하세요
+
+</Update>
+
 <Update label="v0.39.1" description="2026년 10월 7일">
 
 **파트너 노드 업데이트**
diff --git a/.github/scripts/cms/staging/ru/changelog/index.mdx b/.github/scripts/cms/staging/ru/changelog/index.mdx
index 0589638f7c..7e69839ac6 100644
--- a/.github/scripts/cms/staging/ru/changelog/index.mdx
+++ b/.github/scripts/cms/staging/ru/changelog/index.mdx
@@ -4,6 +4,20 @@ cmsStaging: true
 ---
 
 
+<Update label="v0.40.0" description="13 октября 2026">
+
+**Поддержка новых моделей с открытым исходным кодом**
+* [**Qwen-Image 2.1 Turbo**](https://github.com/Comfy-Org/workflow_templates/pull/1328): 8-шаговый ускоренный чекпоинт для рабочих процессов «текст-в-изображение» и редактирования изображений
+
+**Обновления партнёрских нод**
+* [**Fish Audio Drama 3**](https://github.com/Comfy-Org/ComfyUI/pull/16999): Модель управления голосом для Text to Speech с поддержкой до 5 голосов
+* [**Higgsfield Genjutsu Motion Transfer**](https://github.com/Comfy-Org/ComfyUI/pull/16913): Пересобирает актёрский состав, локацию и стиль видео, сохраняя движение
+* [**HeyGen Video 1.0**](https://github.com/Comfy-Org/ComfyUI/pull/16876): В ноды HeyGen Video добавлена поддержка разрешения 2K
+* [**Прекращение поддержки Quiver Arrow 1**](https://github.com/Comfy-Org/ComfyUI/pull/16775): Модели серии Arrow 1 перестанут работать 16 октября; переключитесь на ноды V2
+* [**Прекращение поддержки Luma Ray 2**](https://github.com/Comfy-Org/ComfyUI/pull/16741): Ноды и шаблоны Ray 2 перестанут работать 24 октября; используйте Ray 3.2
+
+</Update>
+
 <Update label="v0.39.1" description="7 октября 2026 г.">
 
 **Обновления партнёрских узлов**
diff --git a/.github/scripts/cms/staging/zh/changelog/index.mdx b/.github/scripts/cms/staging/zh/changelog/index.mdx
index dc1462b4d2..7a1517e01d 100644
--- a/.github/scripts/cms/staging/zh/changelog/index.mdx
+++ b/.github/scripts/cms/staging/zh/changelog/index.mdx
@@ -4,6 +4,20 @@ cmsStaging: true
 ---
 
 
+<Update label="v0.40.0" description="2026年10月13日">
+
+**新增开源模型支持**
+* [**Qwen-Image 2.1 Turbo**](https://github.com/Comfy-Org/workflow_templates/pull/1328)：用于文生图和图像编辑工作流的 8 步加速检查点
+
+**合作伙伴节点更新**
+* [**Fish Audio Drama 3**](https://github.com/Comfy-Org/ComfyUI/pull/16999)：面向文本转语音的语音指导模型，最多支持 5 种音色
+* [**Higgsfield Genjutsu Motion Transfer**](https://github.com/Comfy-Org/ComfyUI/pull/16913)：在保留动作的同时，重建视频的演员阵容、场景和风格
+* [**HeyGen Video 1.0**](https://github.com/Comfy-Org/ComfyUI/pull/16876)：HeyGen Video 节点新增 2K 分辨率支持
+* [**Quiver Arrow 1 退役**](https://github.com/Comfy-Org/ComfyUI/pull/16775)：Arrow 1 系列模型将于 10 月 16 日停止工作；请切换到 V2 节点
+* [**Luma Ray 2 退役**](https://github.com/Comfy-Org/ComfyUI/pull/16741)：Ray 2 节点和模板将于 10 月 24 日停止工作；请使用 Ray 3.2
+
+</Update>
+
 <Update label="v0.39.1" description="2026年10月7日">
 
 **合作伙伴节点更新**
diff --git a/changelog/index.mdx b/changelog/index.mdx
index 8a3d429d94..6c966e770e 100644
--- a/changelog/index.mdx
+++ b/changelog/index.mdx
@@ -4,6 +4,69 @@ description: "ComfyUI changelog: the latest features, improvements, and bug fixe
 icon: "clock-rotate-left"
 ---
 
+<Update label="v0.40.0" description="October 13, 2026">
+
+**New Open-Source Model Support**
+* [**Qwen-Image 2.1 Turbo**](https://github.com/Comfy-Org/workflow_templates/pull/1328): The 8-step accelerated Qwen-Image 2.1 checkpoint, with new text-to-image and image edit templates
+
+**New Node Updates**
+* [**LoRA stack loaders**](https://github.com/Comfy-Org/ComfyUI/pull/16309): Apply several LoRAs in order from one node, each with its own file, strength, and on/off switch, to either the diffusion model or the text encoder
+* [**Camera Angle**](https://github.com/Comfy-Org/ComfyUI/pull/16251): Pick a horizontal angle, vertical angle, and zoom to output a `camera_info` and a plain-English shot description for prompts
+* [**Create Camera Info**](https://github.com/Comfy-Org/ComfyUI/pull/14964): Build a `camera_info` in orbit, look-at, or quaternion mode for Render Splat and the other 3D camera nodes
+* [**Latent Operation Blend**](https://github.com/Comfy-Org/ComfyUI/pull/16923): A new blend operation, plus start and end percent on `LatentApplyOperationCFG`
+* [**LoRA attention config**](https://github.com/Comfy-Org/ComfyUI/pull/16880): LoRAs can replace a model's per-layer attention config, so turbo LoRAs can switch layers to sol or kitchen attention
+
+**Partner Node Updates**
+* [**Fish Audio Drama 3**](https://github.com/Comfy-Org/ComfyUI/pull/16999): Fish Audio's voice direction model on the Text to Speech node, with plain-language directions, word tags, and up to 5 voices
+* [**Higgsfield Genjutsu Motion Transfer**](https://github.com/Comfy-Org/ComfyUI/pull/16913): Rebuild the cast, location, and style of a video from reference images while keeping its motion and audio
+* [**HeyGen Video 1.0**](https://github.com/Comfy-Org/ComfyUI/pull/16876): Added 2K resolution to the HeyGen Video 1.0 nodes
+
+**Performance & Stability**
+* [**Qwen-Image 2.1 low VRAM**](https://github.com/Comfy-Org/ComfyUI/pull/16870): comfy-aimdo 0.5.6 and fewer compiler rogues when the KV cache is offloaded to CPU
+* [**Qwen 3.5 LLM**](https://github.com/Comfy-Org/ComfyUI/pull/16820): Faster in low VRAM conditions
+* [**Qwen 3.5 MTP**](https://github.com/Comfy-Org/ComfyUI/pull/16922): MTP decoding now also runs on prompts that contain images
+* [**comfy_attention**](https://github.com/Comfy-Org/ComfyUI/pull/16806): Extended to the remaining models, and [model files can now use kitchen sol attention](https://github.com/Comfy-Org/ComfyUI/pull/16831)
+* [**AMD gfx1151**](https://github.com/Comfy-Org/ComfyUI/pull/16726): Faster attention when keys and values do not fit in L2 cache
+* [**Saved EXR**](https://github.com/Comfy-Org/ComfyUI/pull/16948): EXR files are now saved with compression
+* [**GLB textures**](https://github.com/Comfy-Org/ComfyUI/pull/16867): Faster saving with PNG compression level 4
+* [**3D outputs**](https://github.com/Comfy-Org/ComfyUI/pull/16200): Every 3D node now reports its models as a standard `3d` output item
+* [**cryptography removed**](https://github.com/Comfy-Org/ComfyUI/pull/16988): Dropped the cryptography package dependency
+
+**Bug Fixes**
+* [**Bypass LoRAs**](https://github.com/Comfy-Org/ComfyUI/pull/16862): Fixed bypass LoRAs on fused Linear paths
+* [**Qwen 3.5 MTP offload**](https://github.com/Comfy-Org/ComfyUI/pull/16877): Fixed MTP embedding offload
+* [**MiniMax-H3 single images**](https://github.com/Comfy-Org/ComfyUI/pull/16881): Single images are now decoded as the first latent of a clip
+* [**Half float video**](https://github.com/Comfy-Org/ComfyUI/pull/16949): Fixed loading half float files with PyAV
+* [**Dynamic inputs**](https://github.com/Comfy-Org/ComfyUI/pull/16377): Validation and lazy execution now work with dynamic inputs
+* [**Asset dates**](https://github.com/Comfy-Org/ComfyUI/pull/16810): Scanned assets are dated by their file modification time
+
+**Asset Library**
+* [**Enable flag**](https://github.com/Comfy-Org/ComfyUI/pull/16929): The asset system stays off unless ComfyUI starts with `--enable-assets`, and the output folder is scanned again when it is on
+* [**Windows portable**](https://github.com/Comfy-Org/ComfyUI/pull/16928): The asset system is on by default in the Windows standalone build
+* [**Asset export API**](https://github.com/Comfy-Org/ComfyUI/pull/16578): The asset export API now works locally
+* [**Video metadata**](https://github.com/Comfy-Org/ComfyUI/pull/15180): Video metadata is extracted on ingest and scan
+* [**EXR previews**](https://github.com/Comfy-Org/ComfyUI/pull/16898): Previews for EXR assets, written by `SaveImageAdvanced` for outputs
+
+**Developer Experience**
+* [**Prompt metadata**](https://github.com/Comfy-Org/ComfyUI/pull/16763): Attach metadata to a prompt's websocket messages and [preview image frames](https://github.com/Comfy-Org/ComfyUI/pull/16809)
+* [**Custom node governance**](https://github.com/Comfy-Org/ComfyUI/pull/16167): Governed builds can restrict ComfyUI to approved custom node packs; normal installs are unchanged
+* [**Content Security Policy**](https://github.com/Comfy-Org/ComfyUI/pull/15565): The CSP now allows `blob:` and `data:` sources
+
+**Installation**
+* [**ARM64 NVIDIA portable**](https://github.com/Comfy-Org/ComfyUI/pull/16985): A new Windows portable build for ARM64 devices with NVIDIA GPUs
+
+**Workflow Templates**
+* [**Templates v0.11.82**](https://github.com/Comfy-Org/ComfyUI/pull/17001): Updated the bundled workflow templates, with these new templates:
+  * [**Qwen Image 2.1 Turbo: Text to Image**](https://github.com/Comfy-Org/workflow_templates/blob/main/templates/image_qwen_image_2_1_turbo_t2i.json): 1024×1024 images in 8 sampling steps, with an optional Qwen 3.5 prompt enhancer
+  * [**Qwen Image 2.1 Turbo: Image Edit**](https://github.com/Comfy-Org/workflow_templates/blob/main/templates/image_qwen_image_2_1_turbo_image_edit.json): Edit an image from two reference images with the Turbo checkpoint
+  * [**LTX-2.5 DFR: Image to Video**](https://github.com/Comfy-Org/workflow_templates/blob/main/templates/video_ltx2_5_dfr_i2v.json): Three-stage image-to-video with spatial and optional temporal upscaling, plus audio generated in the same pass
+  * [**Higgsfield Genjutsu: Motion Transfer**](https://github.com/Comfy-Org/workflow_templates/blob/main/templates/api_higgsfield_genjutsu_motion_transfer.json): Recast a video from 1 to 8 reference images while keeping its motion, camera movement, timing, and audio
+  * [**Fish Audio Drama 3: Two-Speaker Dialogue**](https://github.com/Comfy-Org/workflow_templates/blob/main/templates/api_fishaudio_drama3_dialogue.json): A dialogue scene between two voices in one script
+  * [**Fish Audio Drama 3: Directed Performance**](https://github.com/Comfy-Org/workflow_templates/blob/main/templates/api_fishaudio_drama3_directed.json): A single voice directed with plain-language directions and word tags
+  * The Luma Ray 2 image-to-video and text-to-video templates are deprecated, following the [Ray 2 node deprecation in v0.39.0](https://github.com/Comfy-Org/ComfyUI/pull/16741). The Ray 2 endpoints shut down on October 24
+
+</Update>
+
 <Update label="v0.39.2" description="October 8, 2026">
 
 **Partner Node Updates**
diff --git a/ja/changelog/index.mdx b/ja/changelog/index.mdx
index cda427a404..1c15ddf6ef 100644
--- a/ja/changelog/index.mdx
+++ b/ja/changelog/index.mdx
@@ -2,9 +2,10 @@
 title: "変更履歴"
 description: "ComfyUI の変更ログ：各リリースの最新機能、改善点、バグ修正を、新バージョンのリリースに合わせて更新。"
 icon: "clock-rotate-left"
-translationSourceHash: e62a9398
+translationSourceHash: b069c831
 translationFrom: changelog/index.mdx
 translationBlockHashes:
+  "v0.40.0": 3854bd15
   "v0.39.2": 2d0fc331
   "v0.39.1": 495ace40
   "v0.39.0": 9d56d69e
@@ -141,6 +142,69 @@ translationBlockHashes:
   "v0.3.40": 24608eaf
 ---
 
+<Update label="v0.40.0" description="2026年10月13日">
+
+**新しいオープンソースモデルのサポート**
+* [**Qwen-Image 2.1 Turbo**](https://github.com/Comfy-Org/workflow_templates/pull/1328): 8ステップに高速化されたQwen-Image 2.1 checkpointと、新しいテキストから画像への生成および画像編集のテンプレート
+
+**新しいノードの更新**
+* [**LoRAスタックローダー**](https://github.com/Comfy-Org/ComfyUI/pull/16309): 1つのノードから複数のLoRAを順番に適用できる。それぞれに専用のファイル、強度、オン／オフスイッチがあり、diffusionモデルまたはテキストエンコーダーのいずれかに適用できる
+* [**カメラアングル**](https://github.com/Comfy-Org/ComfyUI/pull/16251): 水平角度、垂直角度、ズームを選んで、`camera_info` と、プロンプト用の平易な英語によるショット説明を出力する
+* [**カメラ情報の作成**](https://github.com/Comfy-Org/ComfyUI/pull/14964): orbit、look-at、quaternionモードで `camera_info` を構築し、スプラットをレンダリングやその他の3Dカメラノードで使用する
+* [**潜在操作ブレンド**](https://github.com/Comfy-Org/ComfyUI/pull/16923): 新しいブレンド操作に加えて、`LatentApplyOperationCFG` の開始と終了のパーセント
+* [**LoRAアテンション設定**](https://github.com/Comfy-Org/ComfyUI/pull/16880): LoRAがモデルのレイヤーごとのアテンション設定を置き換えられるため、turbo LoRAはレイヤーをsolまたはkitchenアテンションに切り替えられる
+
+**パートナーノードの更新**
+* [**Fish Audio Drama 3**](https://github.com/Comfy-Org/ComfyUI/pull/16999): Text to Speechノードで使えるFish Audioの音声演出モデル。平易な言葉による指示、単語タグ、最大5つの音声に対応
+* [**Higgsfield Genjutsu Motion Transfer**](https://github.com/Comfy-Org/ComfyUI/pull/16913): 参照画像から動画の出演者、場所、スタイルを再構築し、モーションと音声はそのまま維持する
+* [**HeyGen Video 1.0**](https://github.com/Comfy-Org/ComfyUI/pull/16876): HeyGen Video 1.0ノードに2K解像度を追加
+
+**パフォーマンスと安定性**
+* [**Qwen-Image 2.1 低VRAM**](https://github.com/Comfy-Org/ComfyUI/pull/16870): comfy-aimdo 0.5.6、およびKVキャッシュをCPUへオフロードする際のコンパイラの問題を削減
+* [**Qwen 3.5 LLM**](https://github.com/Comfy-Org/ComfyUI/pull/16820): 低VRAM環境で高速化
+* [**Qwen 3.5 MTP**](https://github.com/Comfy-Org/ComfyUI/pull/16922): 画像を含むプロンプトでもMTPデコードが実行されるようになった
+* [**comfy_attention**](https://github.com/Comfy-Org/ComfyUI/pull/16806): 残りのモデルにも拡張され、[モデルファイルがkitchen sol attentionを使用できるようになった](https://github.com/Comfy-Org/ComfyUI/pull/16831)
+* [**AMD gfx1151**](https://github.com/Comfy-Org/ComfyUI/pull/16726): キーと値がL2キャッシュに収まらない場合のアテンションを高速化
+* [**保存されるEXR**](https://github.com/Comfy-Org/ComfyUI/pull/16948): EXRファイルが圧縮付きで保存されるようになった
+* [**GLBテクスチャ**](https://github.com/Comfy-Org/ComfyUI/pull/16867): PNG圧縮レベル4による保存の高速化
+* [**3D出力**](https://github.com/Comfy-Org/ComfyUI/pull/16200): すべての3Dノードが、モデルをスタンダードな `3d` 出力項目として報告するようになった
+* [**cryptographyの削除**](https://github.com/Comfy-Org/ComfyUI/pull/16988): cryptographyパッケージの依存関係を削除
+
+**バグ修正**
+* [**バイパスLoRA**](https://github.com/Comfy-Org/ComfyUI/pull/16862): fused LinearパスでのバイパスLoRAを修正
+* [**Qwen 3.5 MTPオフロード**](https://github.com/Comfy-Org/ComfyUI/pull/16877): MTP embeddingのオフロードを修正
+* [**MiniMax-H3の単一画像**](https://github.com/Comfy-Org/ComfyUI/pull/16881): 単一画像がクリップの最初の潜在としてデコードされるようになった
+* [**half float動画**](https://github.com/Comfy-Org/ComfyUI/pull/16949): PyAVでhalf floatファイルを読み込む際の問題を修正
+* [**動的入力**](https://github.com/Comfy-Org/ComfyUI/pull/16377): 検証と遅延実行が動的入力で機能するようになった
+* [**アセットの日付**](https://github.com/Comfy-Org/ComfyUI/pull/16810): スキャンされたアセットには、ファイルの更新時刻に基づく日付が付与される
+
+**アセットライブラリ**
+* [**有効化フラグ**](https://github.com/Comfy-Org/ComfyUI/pull/16929): アセットシステムは、ComfyUIが `--enable-assets` 付きで起動しない限り無効のままで、有効な場合は出力フォルダーが再度スキャンされる
+* [**Windowsポータブル**](https://github.com/Comfy-Org/ComfyUI/pull/16928): Windowsスタンドアロンビルドでは、アセットシステムがデフォルトで有効
+* [**アセットエクスポートAPI**](https://github.com/Comfy-Org/ComfyUI/pull/16578): アセットエクスポートAPIがローカルで動作するようになった
+* [**動画メタデータ**](https://github.com/Comfy-Org/ComfyUI/pull/15180): 動画メタデータが取り込み時とスキャン時に抽出される
+* [**EXRプレビュー**](https://github.com/Comfy-Org/ComfyUI/pull/16898): EXRアセットのプレビュー。出力用に `SaveImageAdvanced` が書き出す
+
+**開発者エクスペリエンス**
+* [**プロンプトメタデータ**](https://github.com/Comfy-Org/ComfyUI/pull/16763): プロンプトのwebsocketメッセージと[画像プレビューのフレーム](https://github.com/Comfy-Org/ComfyUI/pull/16809)にメタデータを付加
+* [**カスタムノードのガバナンス**](https://github.com/Comfy-Org/ComfyUI/pull/16167): ガバナンス付きビルドではComfyUIを承認済みのカスタムノードパックに制限できる。通常のインストールは変更されない
+* [**コンテンツセキュリティポリシー**](https://github.com/Comfy-Org/ComfyUI/pull/15565): CSPが `blob:` と `data:` ソースを許可するようになった
+
+**インストール**
+* [**ARM64 NVIDIAポータブル**](https://github.com/Comfy-Org/ComfyUI/pull/16985): NVIDIA GPUを搭載したARM64デバイス向けの新しいWindowsポータブルビルド
+
+**ワークフローテンプレート**
+* [**テンプレート v0.11.82**](https://github.com/Comfy-Org/ComfyUI/pull/17001): 同梱のワークフローテンプレートを更新。以下の新しいテンプレートを追加:
+  * [**Qwen Image 2.1 Turbo: テキストから画像へ**](https://github.com/Comfy-Org/workflow_templates/blob/main/templates/image_qwen_image_2_1_turbo_t2i.json): 8サンプリングステップで1024×1024の画像を生成。オプションのQwen 3.5プロンプトエンハンサー付き
+  * [**Qwen Image 2.1 Turbo: 画像編集**](https://github.com/Comfy-Org/workflow_templates/blob/main/templates/image_qwen_image_2_1_turbo_image_edit.json): Turbo checkpointを使って2つの参照画像から画像を編集
+  * [**LTX-2.5 DFR: 画像から動画へ**](https://github.com/Comfy-Org/workflow_templates/blob/main/templates/video_ltx2_5_dfr_i2v.json): 空間方向とオプションの時間方向のアップスケーリングを備えた3段階の画像から動画への変換に加え、同じパスでオーディオも生成します
+  * [**Higgsfield Genjutsu: Motion Transfer**](https://github.com/Comfy-Org/workflow_templates/blob/main/templates/api_higgsfield_genjutsu_motion_transfer.json): 1〜8枚の参照画像からビデオを再構成し、そのモーション、カメラの動き、タイミング、オーディオを維持します
+  * [**Fish Audio Drama 3: Two-Speaker Dialogue**](https://github.com/Comfy-Org/workflow_templates/blob/main/templates/api_fishaudio_drama3_dialogue.json): 1つのスクリプト内で2つの声による対話シーン
+  * [**Fish Audio Drama 3: Directed Performance**](https://github.com/Comfy-Org/workflow_templates/blob/main/templates/api_fishaudio_drama3_directed.json): 平易な言葉による指示と単語タグで演出された単一の声
+  * Luma Ray 2 の画像から動画へおよびテキストから動画へのテンプレートは非推奨になりました。[v0.39.0 での Ray 2 ノードの非推奨化](https://github.com/Comfy-Org/ComfyUI/pull/16741)に伴う変更です。Ray 2 のエンドポイントは 10 月 24 日に終了します
+
+</Update>
+
 <Update label="v0.39.2" description="2026年10月8日">
 
 **パートナーノードの更新**
diff --git a/ko/changelog/index.mdx b/ko/changelog/index.mdx
index a8eb188828..bbea3f0dc8 100644
--- a/ko/changelog/index.mdx
+++ b/ko/changelog/index.mdx
@@ -2,9 +2,10 @@
 title: "변경 로그"
 description: "ComfyUI 변경 로그: 각 릴리스의 최신 기능, 개선 사항, 버그 수정을 새 버전 출시에 맞춰 업데이트합니다."
 icon: "clock-rotate-left"
-translationSourceHash: e62a9398
+translationSourceHash: b069c831
 translationFrom: changelog/index.mdx
 translationBlockHashes:
+  "v0.40.0": fc0ac09c
   "v0.39.2": 2d0fc331
   "v0.39.1": 495ace40
   "v0.39.0": 9d56d69e
@@ -141,6 +142,69 @@ translationBlockHashes:
   "v0.3.40": 24608eaf
 ---
 
+<Update label="v0.40.0" description="2026년 10월 13일">
+
+**새 오픈소스 모델 지원**
+* [**Qwen-Image 2.1 Turbo**](https://github.com/Comfy-Org/workflow_templates/pull/1328): 8단계로 가속된 Qwen-Image 2.1 checkpoint로, 새로운 텍스트 기반 이미지 생성 및 이미지 편집 템플릿을 제공합니다
+
+**새 노드 업데이트**
+* [**LoRA stack loaders**](https://github.com/Comfy-Org/ComfyUI/pull/16309): 하나의 노드에서 여러 LoRA를 순서대로 적용합니다. 각 LoRA는 고유한 파일, 강도, 켜기/끄기 스위치를 가지며 diffusion model 또는 text encoder에 적용할 수 있습니다
+* [**Camera Angle**](https://github.com/Comfy-Org/ComfyUI/pull/16251): 수평 각도, 수직 각도, 줌을 선택하면 `camera_info`와 프롬프트에 쓸 평문 샷 설명을 출력합니다
+* [**Create Camera Info**](https://github.com/Comfy-Org/ComfyUI/pull/14964): Render Splat 및 기타 3D 카메라 노드용으로 orbit, look-at, quaternion 모드에서 `camera_info`를 생성합니다
+* [**Latent Operation Blend**](https://github.com/Comfy-Org/ComfyUI/pull/16923): 새로운 블렌드 연산과 `LatentApplyOperationCFG`의 시작 및 종료 퍼센트
+* [**LoRA attention config**](https://github.com/Comfy-Org/ComfyUI/pull/16880): LoRA가 모델의 레이어별 어텐션 설정을 교체할 수 있어, turbo LoRA가 레이어를 sol 또는 kitchen 어텐션으로 전환할 수 있습니다
+
+**파트너 노드 업데이트**
+* [**Fish Audio Drama 3**](https://github.com/Comfy-Org/ComfyUI/pull/16999): Text to Speech 노드에서 사용하는 Fish Audio의 음성 연출 모델로, 평문 지시문, 단어 태그, 최대 5개 음성을 지원합니다
+* [**Higgsfield Genjutsu Motion Transfer**](https://github.com/Comfy-Org/ComfyUI/pull/16913): 참조 이미지로 비디오의 등장인물, 장소, 스타일을 재구성하면서 모션과 오디오는 그대로 유지합니다
+* [**HeyGen Video 1.0**](https://github.com/Comfy-Org/ComfyUI/pull/16876): HeyGen Video 1.0 노드에 2K 해상도가 추가되었습니다
+
+**성능 및 안정성**
+* [**Qwen-Image 2.1 low VRAM**](https://github.com/Comfy-Org/ComfyUI/pull/16870): comfy-aimdo 0.5.6 및 KV cache가 CPU로 오프로드될 때 컴파일러 rogue 감소
+* [**Qwen 3.5 LLM**](https://github.com/Comfy-Org/ComfyUI/pull/16820): 저 VRAM 환경에서 더 빨라졌습니다
+* [**Qwen 3.5 MTP**](https://github.com/Comfy-Org/ComfyUI/pull/16922): 이제 MTP 디코딩이 이미지가 포함된 프롬프트에서도 실행됩니다
+* [**comfy_attention**](https://github.com/Comfy-Org/ComfyUI/pull/16806): 나머지 모델까지 확장되었으며, [이제 모델 파일이 kitchen sol 어텐션을 사용할 수 있습니다](https://github.com/Comfy-Org/ComfyUI/pull/16831)
+* [**AMD gfx1151**](https://github.com/Comfy-Org/ComfyUI/pull/16726): key와 value가 L2 cache에 들어가지 않을 때 어텐션이 더 빨라집니다
+* [**Saved EXR**](https://github.com/Comfy-Org/ComfyUI/pull/16948): 이제 EXR 파일이 압축되어 저장됩니다
+* [**GLB textures**](https://github.com/Comfy-Org/ComfyUI/pull/16867): PNG 압축 레벨 4로 저장 속도가 빨라졌습니다
+* [**3D outputs**](https://github.com/Comfy-Org/ComfyUI/pull/16200): 이제 모든 3D 노드가 모델을 표준 `3d` 출력 항목으로 보고합니다
+* [**cryptography removed**](https://github.com/Comfy-Org/ComfyUI/pull/16988): cryptography 패키지 의존성을 제거했습니다
+
+**버그 수정**
+* [**Bypass LoRAs**](https://github.com/Comfy-Org/ComfyUI/pull/16862): 퓨즈된 Linear 경로에서 LoRA 실행 건너뛰기를 수정했습니다
+* [**Qwen 3.5 MTP offload**](https://github.com/Comfy-Org/ComfyUI/pull/16877): MTP embedding 오프로드를 수정했습니다
+* [**MiniMax-H3 single images**](https://github.com/Comfy-Org/ComfyUI/pull/16881): 이제 단일 이미지가 클립의 첫 번째 잠재 데이터로 디코딩됩니다
+* [**Half float video**](https://github.com/Comfy-Org/ComfyUI/pull/16949): PyAV로 half float 파일을 로딩하는 문제를 수정했습니다
+* [**Dynamic inputs**](https://github.com/Comfy-Org/ComfyUI/pull/16377): 이제 검증과 지연 실행이 동적 입력에서도 작동합니다
+* [**Asset dates**](https://github.com/Comfy-Org/ComfyUI/pull/16810): 스캔된 에셋의 날짜는 파일 수정 시간을 기준으로 지정됩니다
+
+**에셋 라이브러리**
+* [**Enable flag**](https://github.com/Comfy-Org/ComfyUI/pull/16929): 에셋 시스템은 ComfyUI가 `--enable-assets`로 시작하지 않으면 꺼진 상태로 유지되며, 켜져 있으면 출력 폴더를 다시 스캔합니다
+* [**Windows portable**](https://github.com/Comfy-Org/ComfyUI/pull/16928): Windows 독립 실행 빌드에서는 에셋 시스템이 기본으로 켜져 있습니다
+* [**Asset export API**](https://github.com/Comfy-Org/ComfyUI/pull/16578): 이제 에셋 내보내기 API가 로컬에서 작동합니다
+* [**Video metadata**](https://github.com/Comfy-Org/ComfyUI/pull/15180): 비디오 메타데이터는 인제스트와 스캔 시 추출됩니다
+* [**EXR previews**](https://github.com/Comfy-Org/ComfyUI/pull/16898): EXR 에셋용 미리보기로, 출력 시 `SaveImageAdvanced`가 작성합니다
+
+**개발자 경험**
+* [**Prompt metadata**](https://github.com/Comfy-Org/ComfyUI/pull/16763): 프롬프트의 websocket 메시지와 [미리보기 이미지 프레임](https://github.com/Comfy-Org/ComfyUI/pull/16809)에 메타데이터를 첨부합니다
+* [**Custom node governance**](https://github.com/Comfy-Org/ComfyUI/pull/16167): 거버넌스 빌드에서는 ComfyUI를 승인된 커스텀 노드 팩으로 제한할 수 있으며, 일반 설치는 그대로입니다
+* [**Content Security Policy**](https://github.com/Comfy-Org/ComfyUI/pull/15565): 이제 CSP가 `blob:` 및 `data:` 소스를 허용합니다
+
+**설치**
+* [**ARM64 NVIDIA portable**](https://github.com/Comfy-Org/ComfyUI/pull/16985): NVIDIA GPU가 있는 ARM64 장치용 새 Windows 포터블 빌드
+
+**워크플로 템플릿**
+* [**Templates v0.11.82**](https://github.com/Comfy-Org/ComfyUI/pull/17001): 번들된 워크플로 템플릿을 업데이트했으며, 다음 새 템플릿이 포함됩니다:
+  * [**Qwen Image 2.1 Turbo: 텍스트 기반 이미지 생성**](https://github.com/Comfy-Org/workflow_templates/blob/main/templates/image_qwen_image_2_1_turbo_t2i.json): 선택적 Qwen 3.5 프롬프트 인핸서와 함께 8 샘플링 스텝으로 1024×1024 이미지 생성
+  * [**Qwen Image 2.1 Turbo: 이미지 편집**](https://github.com/Comfy-Org/workflow_templates/blob/main/templates/image_qwen_image_2_1_turbo_image_edit.json): Turbo checkpoint로 두 개의 참조 이미지에서 이미지를 편집합니다
+  * [**LTX-2.5 DFR: 이미지 기반 비디오 생성**](https://github.com/Comfy-Org/workflow_templates/blob/main/templates/video_ltx2_5_dfr_i2v.json): 공간 업스케일링과 선택적 시간 업스케일링을 포함한 3단계 이미지 기반 비디오 생성, 그리고 같은 패스에서 생성되는 오디오
+  * [**Higgsfield Genjutsu: 모션 전이**](https://github.com/Comfy-Org/workflow_templates/blob/main/templates/api_higgsfield_genjutsu_motion_transfer.json): 1~8장의 참조 이미지로 비디오를 다시 구성하면서 모션, 카메라 움직임, 타이밍, 오디오를 유지
+  * [**Fish Audio Drama 3: 두 화자 대화**](https://github.com/Comfy-Org/workflow_templates/blob/main/templates/api_fishaudio_drama3_dialogue.json): 하나의 스크립트에서 두 목소리가 주고받는 대화 장면
+  * [**Fish Audio Drama 3: 연출된 퍼포먼스**](https://github.com/Comfy-Org/workflow_templates/blob/main/templates/api_fishaudio_drama3_directed.json): 자연어 지시와 단어 태그로 연출되는 단일 목소리
+  * Luma Ray 2 이미지 기반 비디오 생성 및 텍스트 기반 비디오 생성 템플릿이 지원 중단되었습니다. [v0.39.0에서 지원 중단된 Ray 2 노드](https://github.com/Comfy-Org/ComfyUI/pull/16741)에 따른 변경입니다. Ray 2 엔드포인트는 10월 24일에 종료됩니다
+
+</Update>
+
 <Update label="v0.39.2" description="2026년 10월 8일">
 
 **파트너 노드 업데이트**
diff --git a/zh/changelog/index.mdx b/zh/changelog/index.mdx
index 4cce6964c9..741dc279b9 100644
--- a/zh/changelog/index.mdx
+++ b/zh/changelog/index.mdx
@@ -2,9 +2,10 @@
 title: "更新日志"
 description: "ComfyUI 变更日志：每个版本的最新功能、改进和错误修复，随新版本发布持续更新。"
 icon: "clock-rotate-left"
-translationSourceHash: e62a9398
+translationSourceHash: b069c831
 translationFrom: changelog/index.mdx
 translationBlockHashes:
+  "v0.40.0": 3854bd15
   "v0.39.2": 2d0fc331
   "v0.39.1": 495ace40
   "v0.39.0": 9d56d69e
@@ -141,6 +142,69 @@ translationBlockHashes:
   "v0.3.40": 24608eaf
 ---
 
+<Update label="v0.40.0" description="2026年10月13日">
+
+**新增开源模型支持**
+* [**Qwen-Image 2.1 Turbo**](https://github.com/Comfy-Org/workflow_templates/pull/1328)：8 步加速的 Qwen-Image 2.1 checkpoint，并附带新的文生图和图像编辑模板
+
+**新增节点更新**
+* [**LoRA 堆叠加载器**](https://github.com/Comfy-Org/ComfyUI/pull/16309)：在单个节点中按顺序应用多个 LoRA，每个 LoRA 都有自己的文件、强度和开关，可作用于 diffusion 模型或文本编码器
+* [**相机角度**](https://github.com/Comfy-Org/ComfyUI/pull/16251)：选择水平角度、竖直角度和缩放，输出一个 `camera_info` 以及用于提示词的纯英文镜头描述
+* [**创建相机信息**](https://github.com/Comfy-Org/ComfyUI/pull/14964)：以 orbit、look-at 或 quaternion 模式构建 `camera_info`，供渲染 Splat 及其他 3D 相机节点使用
+* [**Latent 操作混合**](https://github.com/Comfy-Org/ComfyUI/pull/16923)：新增一种混合操作，并为 `LatentApplyOperationCFG` 增加起始和结束百分比
+* [**LoRA 注意力配置**](https://github.com/Comfy-Org/ComfyUI/pull/16880)：LoRA 可以替换模型的逐层注意力配置，因此 turbo LoRA 可以将图层切换为 sol 或 kitchen 注意力
+
+**合作伙伴节点更新**
+* [**Fish Audio Drama 3**](https://github.com/Comfy-Org/ComfyUI/pull/16999)：Fish Audio 的语音导演模型登陆文本转语音节点，支持自然语言指令、词语标签以及最多 5 个音色
+* [**Higgsfield Genjutsu 运动迁移**](https://github.com/Comfy-Org/ComfyUI/pull/16913)：根据参考图像重建视频的演员阵容、场景和风格，同时保留其运动和音频
+* [**HeyGen Video 1.0**](https://github.com/Comfy-Org/ComfyUI/pull/16876)：为 HeyGen Video 1.0 节点新增了 2K 分辨率
+
+**性能与稳定性**
+* [**Qwen-Image 2.1 低显存**](https://github.com/Comfy-Org/ComfyUI/pull/16870)：comfy-aimdo 0.5.6，以及在 KV 缓存卸载到 CPU 时更少的编译器异常
+* [**Qwen 3.5 LLM**](https://github.com/Comfy-Org/ComfyUI/pull/16820)：在低显存条件下速度更快
+* [**Qwen 3.5 MTP**](https://github.com/Comfy-Org/ComfyUI/pull/16922)：MTP 解码现在也能在包含图像的提示词上运行
+* [**comfy_attention**](https://github.com/Comfy-Org/ComfyUI/pull/16806)：扩展到剩余模型，并且[模型文件现在可以使用 kitchen sol 注意力](https://github.com/Comfy-Org/ComfyUI/pull/16831)
+* [**AMD gfx1151**](https://github.com/Comfy-Org/ComfyUI/pull/16726)：当键和值无法装入 L2 缓存时，注意力速度更快
+* [**EXR 保存**](https://github.com/Comfy-Org/ComfyUI/pull/16948)：EXR 文件现在以压缩方式保存
+* [**GLB 纹理**](https://github.com/Comfy-Org/ComfyUI/pull/16867)：使用 PNG 压缩级别 4，保存速度更快
+* [**3D 输出**](https://github.com/Comfy-Org/ComfyUI/pull/16200)：现在每个 3D 节点都会将其模型报告为标准的 `3d` 输出项
+* [**移除 cryptography**](https://github.com/Comfy-Org/ComfyUI/pull/16988)：去掉了 cryptography 包依赖
+
+**Bug 修复**
+* [**绕过 LoRA**](https://github.com/Comfy-Org/ComfyUI/pull/16862)：修复了融合 Linear 路径上的绕过 LoRA
+* [**Qwen 3.5 MTP 卸载**](https://github.com/Comfy-Org/ComfyUI/pull/16877)：修复了 MTP embedding 卸载
+* [**MiniMax-H3 单张图像**](https://github.com/Comfy-Org/ComfyUI/pull/16881)：单张图像现在被解码为片段的第一个 latent
+* [**半精度浮点视频**](https://github.com/Comfy-Org/ComfyUI/pull/16949)：修复了使用 PyAV 加载半浮点文件的问题
+* [**动态输入**](https://github.com/Comfy-Org/ComfyUI/pull/16377)：验证和惰性执行现在可与动态输入配合工作
+* [**资产日期**](https://github.com/Comfy-Org/ComfyUI/pull/16810)：扫描到的资产以其文件修改时间作为日期
+
+**资产库**
+* [**启用开关**](https://github.com/Comfy-Org/ComfyUI/pull/16929)：除非 ComfyUI 以 `--enable-assets` 启动，否则资产系统保持关闭；开启后输出文件夹会被重新扫描
+* [**Windows 便携版**](https://github.com/Comfy-Org/ComfyUI/pull/16928)：在 Windows 独立构建中，资产系统默认开启
+* [**资产导出 API**](https://github.com/Comfy-Org/ComfyUI/pull/16578)：资产导出 API 现在可在本地使用
+* [**视频元数据**](https://github.com/Comfy-Org/ComfyUI/pull/15180)：视频元数据在导入和扫描时提取
+* [**EXR 预览**](https://github.com/Comfy-Org/ComfyUI/pull/16898)：为 EXR 资产提供预览，由 `SaveImageAdvanced` 为输出写入
+
+**开发者体验**
+* [**提示词元数据**](https://github.com/Comfy-Org/ComfyUI/pull/16763)：将元数据附加到提示词的 websocket 消息和[预览图像帧](https://github.com/Comfy-Org/ComfyUI/pull/16809)上
+* [**自定义节点治理**](https://github.com/Comfy-Org/ComfyUI/pull/16167)：受管控的构建可以将 ComfyUI 限定为已批准的自定义节点包；普通安装保持不变
+* [**内容安全策略**](https://github.com/Comfy-Org/ComfyUI/pull/15565)：CSP 现在允许 `blob:` 和 `data:` 来源
+
+**安装**
+* [**ARM64 NVIDIA 便携版**](https://github.com/Comfy-Org/ComfyUI/pull/16985)：面向配备 NVIDIA GPU 的 ARM64 设备的新 Windows 便携版构建
+
+**工作流模板**
+* [**模板 v0.11.82**](https://github.com/Comfy-Org/ComfyUI/pull/17001)：更新了内置工作流模板，新增以下模板：
+  * [**Qwen Image 2.1 Turbo：文生图**](https://github.com/Comfy-Org/workflow_templates/blob/main/templates/image_qwen_image_2_1_turbo_t2i.json)：在 8 个采样步骤内生成 1024×1024 图像，并提供可选的 Qwen 3.5 提示词增强器
+  * [**Qwen Image 2.1 Turbo：图像编辑**](https://github.com/Comfy-Org/workflow_templates/blob/main/templates/image_qwen_image_2_1_turbo_image_edit.json)：使用 Turbo checkpoint 基于两张参考图像编辑图像
+  * [**LTX-2.5 DFR：图生视频**](https://github.com/Comfy-Org/workflow_templates/blob/main/templates/video_ltx2_5_dfr_i2v.json)：三阶段图生视频，具备空间放大和可选的时间放大，并在同一次处理中生成音频
+  * [**Higgsfield Genjutsu：动作迁移**](https://github.com/Comfy-Org/workflow_templates/blob/main/templates/api_higgsfield_genjutsu_motion_transfer.json)：用 1 到 8 张参考图像重新演绎视频，同时保留其动作、相机运动、时序和音频
+  * [**Fish Audio Drama 3：双人对话**](https://github.com/Comfy-Org/workflow_templates/blob/main/templates/api_fishaudio_drama3_dialogue.json)：一个脚本中两段声音之间的对话场景
+  * [**Fish Audio Drama 3：定向表演**](https://github.com/Comfy-Org/workflow_templates/blob/main/templates/api_fishaudio_drama3_directed.json)：用自然语言指令和词语标签执导的单一声音
+  * Luma Ray 2 图生视频和文生视频模板已弃用，与 [v0.39.0 中弃用的 Ray 2 节点](https://github.com/Comfy-Org/ComfyUI/pull/16741)保持一致。Ray 2 接口将于 10 月 24 日停止服务
+
+</Update>
+
 <Update label="v0.39.2" description="2026年10月8日">
 
 **合作伙伴节点更新**