diff --git a/built-in-nodes/KlingDualCharacterVideoEffectNode.mdx b/built-in-nodes/KlingDualCharacterVideoEffectNode.mdx index 34be9207e..5b9066af0 100644 --- a/built-in-nodes/KlingDualCharacterVideoEffectNode.mdx +++ b/built-in-nodes/KlingDualCharacterVideoEffectNode.mdx @@ -6,7 +6,13 @@ icon: "circle" mode: wide --- -The Kling Dual Character Video Effect Node creates videos with special effects based on the selected scene. It takes two images and positions the first image on the left side and the second image on the right side of the composite video. Different visual effects are applied depending on the chosen effect scene. +--- + + + **End of life (EOL)**: Legacy model options (`kling-v1`, `kling-v1-5`, `kling-v1-6`) are scheduled for retirement on **September 15, 2026**. Use Kling 3.0 effect workflows instead. See [Kling 3.0 legacy retirement](/tutorials/partner-nodes/kling/kling-3-0#legacy-kling-models-eol). + + +The Kling Dual Character Video Effect Node creates videos with special effects based on the selected scene. ## Inputs diff --git a/built-in-nodes/KlingImage2VideoNode.mdx b/built-in-nodes/KlingImage2VideoNode.mdx index 7af2e292c..83da4ced6 100644 --- a/built-in-nodes/KlingImage2VideoNode.mdx +++ b/built-in-nodes/KlingImage2VideoNode.mdx @@ -6,7 +6,13 @@ icon: "circle" mode: wide --- -The Kling Image to Video Node generates a video from a starting reference image using text prompts. It takes an image as the first frame and creates a video sequence based on positive and negative text descriptions, with configurable options for model, duration, aspect ratio, and generation mode. +--- + + + **End of life (EOL)**: Legacy model options (`kling-v1-5`, `kling-v1-6`, `kling-v2-1`, `kling-v2-master`, and related variants) are scheduled for retirement on **September 15, 2026**. Use Kling 3.0 or 2.6 models instead. See [Kling 3.0 legacy retirement](/tutorials/partner-nodes/kling/kling-3-0#legacy-kling-models-eol). + + +The Kling Image to Video Node generates a video from a starting reference image using text prompts. ## Inputs diff --git a/built-in-nodes/KlingSingleImageVideoEffectNode.mdx b/built-in-nodes/KlingSingleImageVideoEffectNode.mdx index f7d228f14..d7072a97d 100644 --- a/built-in-nodes/KlingSingleImageVideoEffectNode.mdx +++ b/built-in-nodes/KlingSingleImageVideoEffectNode.mdx @@ -6,7 +6,13 @@ icon: "circle" mode: wide --- -The Kling Single Image Video Effect Node creates videos with different special effects based on a single reference image. It applies various visual effects and scenes to transform static images into dynamic video content. The node supports different effect scenes, model options, and video durations to achieve the desired visual outcome. +--- + + + **End of life (EOL)**: Legacy model options (`kling-v1-5`, `kling-v1-6`) are scheduled for retirement on **September 15, 2026**. Use Kling 3.0 effect workflows instead. See [Kling 3.0 legacy retirement](/tutorials/partner-nodes/kling/kling-3-0#legacy-kling-models-eol). + + +The Kling Single Image Video Effect Node creates videos with different special effects based on a single reference image. ## Inputs diff --git a/built-in-nodes/KlingStartEndFrameNode.mdx b/built-in-nodes/KlingStartEndFrameNode.mdx index cbfd41aea..3f7a0e00f 100644 --- a/built-in-nodes/KlingStartEndFrameNode.mdx +++ b/built-in-nodes/KlingStartEndFrameNode.mdx @@ -6,7 +6,13 @@ icon: "circle" mode: wide --- -This node creates a video sequence that transitions between your provided start and end images. It generates all the frames in between to produce a smooth transformation from the first frame to the last frame. This node calls the image-to-video API but only supports the input options that work with the `image_tail` request field. +--- + + + **End of life (EOL)**: Legacy model options using `kling-v1-5` and `kling-v1-6` are scheduled for retirement on **September 15, 2026**. Use [`api_kling_v3_flf2v`](/tutorials/partner-nodes/kling/kling-3-0#legacy-kling-models-eol) or Kling O3 FLF2V instead. + + +This node creates a video sequence that transitions between your provided start and end images. ## Inputs diff --git a/built-in-nodes/KlingVirtualTryOnNode.mdx b/built-in-nodes/KlingVirtualTryOnNode.mdx index a586c88fc..20bf69de5 100644 --- a/built-in-nodes/KlingVirtualTryOnNode.mdx +++ b/built-in-nodes/KlingVirtualTryOnNode.mdx @@ -6,7 +6,13 @@ icon: "circle" mode: wide --- -Kling Virtual Try On Node. Input a human image and a cloth image to try on the cloth on the human. You can merge multiple clothing item pictures into one image with a white background. +--- + + + **End of life (EOL)**: The Kolors Virtual Try-On API (`kolors-virtual-try-on`, `kolors-virtual-try-on-v1-5`) is scheduled for retirement on **September 15, 2026**. Use [Flux Virtual Try-On](/built-in-nodes/FluxVTONode) instead. + + +Kling Virtual Try On Node. Input a human image and a cloth image to try on the cloth on the human. ## Inputs diff --git a/built-in-nodes/OpenAIGPTImageNodeV2.mdx b/built-in-nodes/OpenAIGPTImageNodeV2.mdx index d7912d7d7..f2969cb91 100644 --- a/built-in-nodes/OpenAIGPTImageNodeV2.mdx +++ b/built-in-nodes/OpenAIGPTImageNodeV2.mdx @@ -28,7 +28,7 @@ This node generates images using OpenAI's GPT Image API. It supports multiple mo **Parameter Constraints and Limitations:** -- When using `gpt-image-2` with a `model.size` of "Custom", the `custom_width` and `custom_height` must be multiples of 16, the maximum edge must be <= 3840, the aspect ratio must not exceed 3:1, and the total pixel count must be between 655,360 and 8,294,400. +- When using `gpt-image-2` with a `model.size` of "Custom", the `custom_width` and `custom_height` must be multiples of 16, the maximum edge must not exceed 3840, the aspect ratio must not exceed 3:1, and the total pixel count must be between 655,360 and 8,294,400. - If a `mask` is provided, an input image (`model.images`) is required. A mask cannot be used without an input image. - A mask cannot be used with multiple input images. - When a mask is provided, the mask dimensions must match the input image dimensions. diff --git a/built-in-nodes/RunwayFirstLastFrameNode.mdx b/built-in-nodes/RunwayFirstLastFrameNode.mdx index cc472f963..cf020b574 100644 --- a/built-in-nodes/RunwayFirstLastFrameNode.mdx +++ b/built-in-nodes/RunwayFirstLastFrameNode.mdx @@ -6,7 +6,13 @@ icon: "circle" mode: wide --- -The Runway First-Last-Frame to Video node generates videos by uploading first and last keyframes along with a text prompt. It creates smooth transitions between the provided start and end frames using Runway's Gen-3 model. This is particularly useful for complex transitions where the end frame differs significantly from the start frame. +--- + + + **End of life (EOL)**: This node reached end of life on **July 30, 2026** when Runway retired Gen-3 Alpha Turbo. For first-last-frame video, use [Kling 3.0 FLF2V](/tutorials/partner-nodes/kling/kling-3-0) or other supported FLF2V templates. + + +The Runway First-Last-Frame to Video node generates videos by uploading first and last keyframes along with a text prompt. ## Inputs diff --git a/built-in-nodes/RunwayImageToVideoNodeGen3a.mdx b/built-in-nodes/RunwayImageToVideoNodeGen3a.mdx index 6a41652a4..31b966a86 100644 --- a/built-in-nodes/RunwayImageToVideoNodeGen3a.mdx +++ b/built-in-nodes/RunwayImageToVideoNodeGen3a.mdx @@ -6,6 +6,12 @@ icon: "circle" mode: wide --- +--- + + + **End of life (EOL)**: This node reached end of life on **July 30, 2026** when Runway retired Gen-3 Alpha Turbo. Use [Runway Gen4 Turbo](/built-in-nodes/RunwayImageToVideoNodeGen4) or the [Gen4 Turbo workflow](/tutorials/partner-nodes/runway/video-generation) instead. + + The Runway Image to Video (Gen3a Turbo) node generates a video from a single starting frame using Runway's Gen3a Turbo model. It takes a text prompt and an initial image frame, then creates a video sequence based on the specified duration and aspect ratio. This node connects to Runway's API to process the generation remotely. ## Inputs diff --git a/ja/tutorials/partner-nodes/kling/kling-3-0.mdx b/ja/tutorials/partner-nodes/kling/kling-3-0.mdx index 7457d6553..b19c3b808 100644 --- a/ja/tutorials/partner-nodes/kling/kling-3-0.mdx +++ b/ja/tutorials/partner-nodes/kling/kling-3-0.mdx @@ -2,10 +2,18 @@ title: "ComfyUI における Kling 3.0 の動画および画像生成" description: "ComfyUI で Kling 3.0 モデルを活用し、マルチショット動画生成、被写体の一貫性維持、多言語音声対応、およびネイティブなテキストレンダリングを実現する方法を学びましょう" sidebarTitle: "Kling 3.0" -translationSourceHash: 9ec27e2e +translationSourceHash: 888c48f3 translationFrom: tutorials/partner-nodes/kling/kling-3-0.mdx +translationBlockHashes: + "_intro": 6176006f + "About Kling 3.0": 2bae40cd + "Kling 3.0 workflows": 383f3e6a + "Learn more": 75a02ac4 + "Available models": f566da3f + "Legacy Kling models (EOL)": 8364a20e --- + import ReqHint from "/snippets/ja/tutorials/partner-nodes/req-hint.mdx"; import UpdateReminder from "/snippets/ja/tutorials/update-reminder.mdx"; @@ -55,4 +63,21 @@ Kling 3.0 の機能に関する詳細なサンプル、プロンプト例、お | **Kling Video 3.0** | 動画 | マルチショット対応の標準的な動画生成 | | **Kling Video 3.0 Omni** | 動画 | オーディオビジュアル機能を備えた高度な動画生成 | | **Kling Image 3.0** | 画像 | 高品質な画像生成 | -| **Kling Image 3.0 Omni** | 画像 | 機能強化済みのマルチモーダル画像生成 | \ No newline at end of file +| **Kling Image 3.0 Omni** | 画像 | 機能強化済みのマルチモーダル画像生成 | + +## レガシー Kling モデル（EOL） + + + **サービス終了（EOL）**：以下のレガシー Kling モデルおよびワークフローテンプレートは **2026年9月15日** に廃止予定です：Kling V1.5、V1.6、V2.1、V2.1 Master、および Kolors バーチャル試着 API。関連 Partner Nodes は ComfyUI に残りますが、これらのモデルオプションは廃止日以降使用できなくなります。 + + +### 廃止されたワークフローテンプレートと代替案 + +| 削除されたテンプレート | 推奨代替 | +| :--------------------- | :------- | +| `api_kling_i2v`（V2.1 Master） | [`api_kling_v3_i2v`](https://github.com/Comfy-Org/workflow_templates/blob/main/templates/api_kling_v3_i2v.json) または [`api_kling2_6_i2v`](https://github.com/Comfy-Org/workflow_templates/blob/main/templates/api_kling2_6_i2v.json) | +| `api_kling_effects`（V1.6） | Kling 3.0 エフェクトワークフロー（`api_kling_v3_*`） | +| `api_kling_flf`（V1.6） | [`api_kling_v3_flf2v`](https://github.com/Comfy-Org/workflow_templates/blob/main/templates/api_kling_v3_flf2v.json) または [`api_kling_o3_flf2v`](https://github.com/Comfy-Org/workflow_templates/blob/main/templates/api_kling_o3_flf2v.json) | +| `api_kling_dual_characters_effects`（V1.6） | Kling 3.0 エフェクトワークフロー（`api_kling_v3_*`） | + +バーチャル試着には [Flux バーチャル試着](/ja/built-in-nodes/FluxVTONode)（`api_flux_vto`）または他のサポート対象の代替手段を使用してください。Flux VTO と Gemini ベースのファッションテンプレートは今回の廃止の対象外です。 diff --git a/ja/tutorials/partner-nodes/pricing.mdx b/ja/tutorials/partner-nodes/pricing.mdx index 9640a750c..b46d38d0f 100644 --- a/ja/tutorials/partner-nodes/pricing.mdx +++ b/ja/tutorials/partner-nodes/pricing.mdx @@ -3,11 +3,11 @@ title: "料金" description: "この記事では、現在のパートナーノードの料金を一覧表示します。" sidebarTitle: "料金" mode: "wide" -translationSourceHash: 5f783396 +translationSourceHash: 7ffb68e7 translationFrom: tutorials/partner-nodes/pricing.mdx translationBlockHashes: - "_intro": 845592d4 - "Anthropic": 57a39b62 + "_intro": ada9999a + "Anthropic": 97b89fc6 "Beeble": d1b19f61 "BFL": 3ff6bff0 "Bria": 232ed8f6 @@ -16,23 +16,23 @@ translationBlockHashes: "Magnific": 4000e7e1 "Google": 21dc3165 "HappyHorse": bceb584a - "HeyGen": c9264f13 + "HeyGen": 47d0a040 "Hitpaw": 320c0537 "Ideogram": 9410bf72 "Krea": fb20c257 - "Kling": cdf2c899 + "Kling": 8b8fb275 "Lightricks": 4870964f "Luma": 655207a5 "Meshy": 6cd06881 "Minimax": 28c7cf5e "OpenAI": db11f921 - "OpenRouter": 06317890 + "OpenRouter": eb16e5b0 "Pixverse": 8612b816 "Quiver": b9d45a82 "Recraft": 7eb9a1a7 "Reve": 5be5c43a "Rodin 3D": 2eb41834 - "Runway": 94ec479a + "Runway": 63aa1c03 "Sonilo": 48b9c581 "sync.so": 590402a9 "Tencent": f1efbad9 @@ -46,6 +46,7 @@ translationBlockHashes: --- + 以下の表は、現在のパートナーノードの料金を一覧表示したものです。すべての価格はクレジット単位です。 ## Anthropic @@ -524,7 +525,11 @@ Seedream 5.0 Proは解像度ベースの課金方式を採用しています：* | motion control | — | std | 14.77 | | motion control | — | pro | 23.63 | -#### レガシー（v2-5-turbo, v2-master, v1.x） +#### レガシー（v2-5-turbo, v2-master, v1.x）— 2026年9月15日 EOL + + + **サービス終了（EOL）**：Kling V1.5、V1.6、V2.1、V2.1 Master、および Kolors バーチャル試着は **2026年9月15日** に廃止予定です。以下の料金表は削除まで参考用として残しています。 + | モデル | モード | クレジット / 秒 | | :------------------------------------------- | :------- | :------------ | @@ -564,7 +569,7 @@ Seedream 5.0 Proは解像度ベースの課金方式を採用しています：* | kling-v2 | — | なし, あり | 2.95 / 画像 | | kling-v1-5 | — | なし | 2.95 / 画像 | | kling-v1-5 | — | あり | 5.91 / 画像 | -| kolors-virtual-try-on-v1, kolors-virtual-try-on-v1-5 | — | — | 147.7 / 実行 | +| kolors-virtual-try-on-v1, kolors-virtual-try-on-v1-5 | — | — | 147.7 / 実行（2026-09-15 EOL） | 画像クレジット合計 = **（クレジット / 画像）× `n`**（**Kling 3.0 Image**の場合）。**Kling 3.0 Omni Image**の場合は `series_amount` を乗算（`kling-image-o1` は常に×1）。 @@ -849,13 +854,17 @@ Fast edit/remixモデルはフラットな基本レートを使用します。 ### 動画 -Gen3a Turbo、Gen4 Turbo、および First-Last-Frame: **5秒** または **10秒**。合計クレジット = **（クレジット / 秒）× `duration`**。 +Gen4 Turbo：**5秒** または **10秒**。合計クレジット = **（クレジット / 秒）× `duration`**。 + + + **サービス終了（EOL）**：`gen3a_turbo` および Runway 首尾フレームノードは **2026年7月30日** にサービス終了しました。画像から動画への生成には Gen4 Turbo を使用してください。 + -| モデル | クレジット | -| :---------- | :---------- | -| gen3a_turbo | 15.09 / 秒 | -| gen4_turbo | 15.09 / 秒 | -| aleph2 | 84.48 / 秒 | +| モデル | クレジット | ステータス | +| :---------- | :---------- | :------- | +| gen4_turbo | 15.09 / 秒 | 利用可能 | +| gen3a_turbo | 15.09 / 秒 | EOL（2026-07-30） | +| aleph2 | 84.48 / 秒 | 利用可能 | **Runway Aleph2 Keyframe** および **Runway Aleph2 Prompt Image** は個別に課金されないヘルパーノードです。コストは **Runway Aleph2 Video to Video** にかかります。 diff --git a/ja/tutorials/partner-nodes/runway/video-generation.mdx b/ja/tutorials/partner-nodes/runway/video-generation.mdx index e85367f8e..20c16a971 100644 --- a/ja/tutorials/partner-nodes/runway/video-generation.mdx +++ b/ja/tutorials/partner-nodes/runway/video-generation.mdx @@ -2,13 +2,8 @@ title: "Runway パートナーノードによる動画生成：ComfyUI 公式サンプル" description: "本記事では、ComfyUI で Runway ノードを用いた動画生成ワークフローの使用方法について説明します。" sidebarTitle: "Runway 動画生成" -translationSourceHash: 4fe3a8fe +translationSourceHash: 3238866a translationFrom: tutorials/partner-nodes/runway/video-generation.mdx -translationBlockHashes: - "_intro": 726f6d02 - "Gen3a turbo Image-to-Video Workflow": 4d85b252 - "Gen4 turbo Image-to-Video Workflow": aed55b59 - "First-Last Frame Video Generation Workflow": b7f1102b --- @@ -18,48 +13,27 @@ import UpdateReminder from "/snippets/ja/tutorials/update-reminder.mdx"; Runway は、生成AIに特化した企業であり、強力な動画生成機能を提供しています。現在、ComfyUI には Runway API が統合されており、関連ノードを ComfyUI 上で直接利用して動画を生成できます。 現在、ComfyUI では以下の Runway 動画生成モデルがネイティブ対応しています： -- Runway Gen3a turbo - Runway Gen4 turbo -- Runway First Last Frame to video - - - -## Gen3a turbo 画像→動画ワークフロー - -### 1. ワークフローファイルのダウンロード - -以下の動画の `metadata` にはワークフロー情報が含まれています。ダウンロード後、ComfyUI へドラッグ＆ドロップすることで、対応するワークフローを読み込むことができます。 - - - - -

JSON形式ワークフローファイルをダウンロード

- - -以下の画像を入力画像としてダウンロードしてください。 + + **サービス終了（EOL）**：**Runway Gen3a Turbo** と **Runway 最初と最後のフレームから動画へ** は **2026年7月30日** にサービス終了しました。Runway は同日に Gen-3 Alpha Turbo を廃止しました。関連 Partner Nodes（`RunwayImageToVideoNodeGen3a`、`RunwayFirstLastFrameNode`）およびワークフローテンプレートは非推奨となり、サポート対象外です。 + -![ComfyUI Runway gen3a turbo 画像→動画 入力画像](https://raw.githubusercontent.com/Comfy-Org/example_workflows/refs/heads/main/api_nodes/runway/gen3a_turbo_image_to_video/steampunk.png) +### 廃止されたワークフローと代替案 -### 2. ワークフロー実行手順（ステップバイステップ） +| 削除されたテンプレート | 推奨代替 | +| :--------------------- | :------- | +| `api_runway_gen3a_turbo_image_to_video` | [`api_runway_gen4_turo_image_to_video`](https://github.com/Comfy-Org/workflow_templates/blob/main/templates/api_runway_gen4_turo_image_to_video.json)（Gen4 Turbo） | +| `api_runway_first_last_frame` | [Kling 3.0 FLF2V](/ja/tutorials/partner-nodes/kling/kling-3-0)（`api_kling_v3_flf2v`）または他の首尾フレームテンプレート | -![ComfyUI Runway gen3a turbo 画像→動画 手順ガイド](/images/tutorial/api_nodes/runway/runway_gen3a_turbo_image_to_video_step_guide.jpg) - -画像中の番号を参考に、基本的な画像→動画ワークフローを実行してください。 -1. `Load Image` ノードで、提供された入力画像を読み込みます。 -2. `Runway Gen3a turbo` ノードで、動画内容を記述する `prompt` を設定し、動画長を指定する `duration` パラメーターと、アスペクト比を指定する `ratio` パラメーターをそれぞれ調整します。 -3. `Run` ボタンをクリックするか、ショートカットキー `Ctrl（macOS の場合は Cmd）+ Enter` を押して動画生成を実行します。 -4. API からの結果が返ってくるまで待ち、生成された動画を `Save Video` ノードで確認します（右クリックで保存可能）。また、対応する動画ファイルは `ComfyUI/output/` ディレクトリにも自動保存されます。 + + ## Gen4 turbo 画像→動画ワークフロー ### 1. ワークフローファイルのダウンロード -以下の動画の `metadata` にはワークフロー情報が含まれています。ダウンロード後、ComfyUI へドラッグ＆ドロップすることで、対応するワークフローを読み込むことができます。 +以下の動画の `metadata` にはワークフロー情報が含まれています。ダウンロードして ComfyUI にドラッグ＆ドロップし、対応するワークフローを読み込んでください。 -

JSON形式ワークフローファイルをダウンロード

+

JSON形式のワークフローファイルをダウンロード

 -以下の画像を入力画像としてダウンロードしてください。 +以下の画像を入力画像としてダウンロードしてください ![ComfyUI Runway gen4 turbo 画像→動画 入力画像](https://raw.githubusercontent.com/Comfy-Org/example_workflows/refs/heads/main/api_nodes/runway/gen4_turbo_image_to_video/godfather.jpg) -### 2. ワークフロー実行手順（ステップバイステップ） +### 2. 手順に沿ってワークフローを実行する ![ComfyUI Runway gen4 turbo 画像→動画 手順ガイド](/images/tutorial/api_nodes/runway/runway_gen4_turbo_image_to_video_step_guide.jpg) -画像中の番号を参考に、基本的な画像→動画ワークフローを実行してください。 -1. `Load Image` ノードで、提供された入力画像を読み込みます。 -2. `Runway Gen4 turbo` ノードで、動画内容を記述する `prompt` を設定し、動画長を指定する `duration` パラメーターと、アスペクト比を指定する `ratio` パラメーターをそれぞれ調整します。 -3. `Run` ボタンをクリックするか、ショートカットキー `Ctrl（macOS の場合は Cmd）+ Enter` を押して動画生成を実行します。 -4. API からの結果が返ってくるまで待ち、生成された動画を `Save Video` ノードで確認します（右クリックで保存可能）。また、対応する動画ファイルは `ComfyUI/output/` ディレクトリにも自動保存されます。 - -## 先頭・末尾フレームから動画生成するワークフロー - -### 1. ワークフローファイルのダウンロード - -以下の動画の `metadata` にはワークフロー情報が含まれています。ダウンロード後、ComfyUI へドラッグ＆ドロップすることで、対応するワークフローを読み込むことができます。 - - - - -

JSON形式ワークフローファイルをダウンロード

- - -以下の画像を入力画像としてダウンロードしてください。 - -![ComfyUI Runway gen4 turbo 画像→動画 入力画像](https://raw.githubusercontent.com/Comfy-Org/example_workflows/refs/heads/main/api_nodes/runway/first_last_frame_to_video/first.jpg) -![ComfyUI Runway gen4 turbo 画像→動画 入力画像](https://raw.githubusercontent.com/Comfy-Org/example_workflows/refs/heads/main/api_nodes/runway/first_last_frame_to_video/last.jpg) - -### 2. ワークフロー実行手順（ステップバイステップ） - -![ComfyUI Runway gen4 turbo 画像→動画 手順ガイド](/images/tutorial/api_nodes/runway/runway_first_last_frame_step_guide.jpg) +画像内の番号を参考に、基本的な画像→動画ワークフローの実行を行ってください。 -画像中の番号を参考に、先頭・末尾フレームから動画を生成する基本ワークフローを実行してください。 -1. `Load Image` ノードで、先頭フレーム（開始フレーム）を読み込みます。 -2. `Load Image` ノードで、末尾フレーム（終了フレーム）を読み込みます。 -3. `Runway First-Last-Frame to Video` ノードで、動画内容を記述する `prompt` を設定し、動画長を指定する `duration` パラメーターと、アスペクト比を指定する `ratio` パラメーターをそれぞれ調整します。 -4. `Run` ボタンをクリックするか、ショートカットキー `Ctrl（macOS の場合は Cmd）+ Enter` を押して動画生成を実行します。 -5. API からの結果が返ってくるまで待ち、生成された動画を `Save Video` ノードで確認します（右クリックで保存可能）。また、対応する動画ファイルは `ComfyUI/output/` ディレクトリにも自動保存されます。 +1. `Load Image` ノードで、提供された入力画像を読み込みます。 +2. `Runway Gen4 turbo` ノードで、動画内容を記述する `prompt` を設定し、動画長を指定する `duration` パラメーターと、アスペクト比を指定する `ratio` パラメーターをそれぞれ調整します。 +3. `Run` ボタンをクリックするか、ショートカット `Ctrl（cmd）+ Enter` で動画生成を実行します。 +4. API の結果が返るまで待機した後、`Save Video` ノードで生成された動画を確認できます（右クリックで保存可能）。対応する動画は `ComfyUI/output/` ディレクトリにも保存されます。 diff --git a/ko/tutorials/partner-nodes/kling/kling-3-0.mdx b/ko/tutorials/partner-nodes/kling/kling-3-0.mdx index 6b774aa87..b880cfdb2 100644 --- a/ko/tutorials/partner-nodes/kling/kling-3-0.mdx +++ b/ko/tutorials/partner-nodes/kling/kling-3-0.mdx @@ -2,10 +2,18 @@ title: "ComfyUI에서 Kling 3.0 동영상 및 이미지 생성" description: "멀티샷 동영상 생성, 피사체 일관성, 다국어 오디오, 네이티브 텍스트 렌더링을 위해 ComfyUI에서 Kling 3.0 모델을 사용하는 방법을 알아보세요" sidebarTitle: "Kling 3.0" -translationSourceHash: 9ec27e2e +translationSourceHash: 888c48f3 translationFrom: tutorials/partner-nodes/kling/kling-3-0.mdx +translationBlockHashes: + "_intro": 6176006f + "About Kling 3.0": 2bae40cd + "Kling 3.0 workflows": 383f3e6a + "Learn more": 75a02ac4 + "Available models": f566da3f + "Legacy Kling models (EOL)": 8364a20e --- + import ReqHint from "/snippets/ko/tutorials/partner-nodes/req-hint.mdx"; import UpdateReminder from "/snippets/ko/tutorials/update-reminder.mdx"; @@ -55,4 +63,21 @@ Kling 3.0의 세부적인 예시, 프롬프트, 동영상 시연을 확인하려 | **Kling Video 3.0** | 동영상 | 멀티샷 지원을 갖춘 표준 동영상 생성 | | **Kling Video 3.0 Omni** | 동영상 | 오디오-비주얼 기능을 갖춘 고급 동영상 생성 | | **Kling Image 3.0** | 이미지 | 고품질 이미지 생성 | -| **Kling Image 3.0 Omni** | 이미지 | 향상된 기능을 갖춘 멀티모달 이미지 생성 | \ No newline at end of file +| **Kling Image 3.0 Omni** | 이미지 | 향상된 기능을 갖춘 멀티모달 이미지 생성 | + +## 레거시 Kling 모델 (EOL) + + + **서비스 종료(EOL)**: 다음 레거시 Kling 모델 및 워크플로 템플릿은 **2026년 9월 15일**에 폐기될 예정입니다: Kling V1.5, V1.6, V2.1, V2.1 Master 및 Kolors 가상 피팅 API. 관련 Partner Nodes는 ComfyUI에 남아 있지만, 이러한 모델 옵션은 폐기일 이후 작동하지 않습니다. + + +### 제거된 워크플로 템플릿 및 대체안 + +| 제거된 템플릿 | 권장 대체 | +| :------------ | :-------- | +| `api_kling_i2v` (V2.1 Master) | [`api_kling_v3_i2v`](https://github.com/Comfy-Org/workflow_templates/blob/main/templates/api_kling_v3_i2v.json) 또는 [`api_kling2_6_i2v`](https://github.com/Comfy-Org/workflow_templates/blob/main/templates/api_kling2_6_i2v.json) | +| `api_kling_effects` (V1.6) | Kling 3.0 이펙트 워크플로 (`api_kling_v3_*`) | +| `api_kling_flf` (V1.6) | [`api_kling_v3_flf2v`](https://github.com/Comfy-Org/workflow_templates/blob/main/templates/api_kling_v3_flf2v.json) 또는 [`api_kling_o3_flf2v`](https://github.com/Comfy-Org/workflow_templates/blob/main/templates/api_kling_o3_flf2v.json) | +| `api_kling_dual_characters_effects` (V1.6) | Kling 3.0 이펙트 워크플로 (`api_kling_v3_*`) | + +가상 피팅은 [Flux 가상 피팅](/ko/built-in-nodes/FluxVTONode) (`api_flux_vto`) 또는 다른 지원되는 대안을 사용하세요. Flux VTO 및 Gemini 기반 패션 템플릿은 이번 폐기 대상이 아닙니다. diff --git a/ko/tutorials/partner-nodes/pricing.mdx b/ko/tutorials/partner-nodes/pricing.mdx index 5fc97d7e2..025e545c8 100644 --- a/ko/tutorials/partner-nodes/pricing.mdx +++ b/ko/tutorials/partner-nodes/pricing.mdx @@ -3,11 +3,11 @@ title: "Pricing" description: "이 문서에는 현재 파트너 노드의 가격 정책이 나와 있습니다." sidebarTitle: "가격 정책" mode: "wide" -translationSourceHash: 5f783396 +translationSourceHash: 7ffb68e7 translationFrom: tutorials/partner-nodes/pricing.mdx translationBlockHashes: - "_intro": 845592d4 - "Anthropic": 57a39b62 + "_intro": ada9999a + "Anthropic": 97b89fc6 "Beeble": d1b19f61 "BFL": 3ff6bff0 "Bria": 232ed8f6 @@ -16,23 +16,23 @@ translationBlockHashes: "Magnific": 4000e7e1 "Google": 21dc3165 "HappyHorse": bceb584a - "HeyGen": c9264f13 + "HeyGen": 47d0a040 "Hitpaw": 320c0537 "Ideogram": 9410bf72 "Krea": fb20c257 - "Kling": cdf2c899 + "Kling": 8b8fb275 "Lightricks": 4870964f "Luma": 655207a5 "Meshy": 6cd06881 "Minimax": 28c7cf5e "OpenAI": db11f921 - "OpenRouter": 06317890 + "OpenRouter": eb16e5b0 "Pixverse": 8612b816 "Quiver": b9d45a82 "Recraft": 7eb9a1a7 "Reve": 5be5c43a "Rodin 3D": 2eb41834 - "Runway": 94ec479a + "Runway": 63aa1c03 "Sonilo": 48b9c581 "sync.so": 590402a9 "Tencent": f1efbad9 @@ -46,6 +46,7 @@ translationBlockHashes: --- + 다음 표에는 현재 파트너 노드의 가격 정책이 나와 있습니다. 모든 가격은 크레딧 단위로 표시됩니다. ## Anthropic @@ -523,7 +524,11 @@ Seedream 5.0 Pro는 해상도 기반 요금제를 사용합니다: **1K** (≤2. | 모션 컨트롤 | — | std | 14.77 | | 모션 컨트롤 | — | pro | 23.63 | -#### 레거시 (v2-5-turbo, v2-master, v1.x) +#### 레거시 (v2-5-turbo, v2-master, v1.x) — 2026년 9월 15일 EOL + + + **서비스 종료(EOL)**: Kling V1.5, V1.6, V2.1, V2.1 Master 및 Kolors 가상 피팅은 **2026년 9월 15일**에 폐기될 예정입니다. 아래 요금표는 제거 전까지 참고용으로 유지됩니다. + | 모델 | 모드 | 크레딧 / 초 | | :------------------------------------------- | :------- | :------------ | @@ -563,7 +568,7 @@ Seedream 5.0 Pro는 해상도 기반 요금제를 사용합니다: **1K** (≤2. | kling-v2 | — | 아니요, 예 | 2.95 / 이미지 | | kling-v1-5 | — | 아니요 | 2.95 / 이미지 | | kling-v1-5 | — | 예 | 5.91 / 이미지 | -| kolors-virtual-try-on-v1, kolors-virtual-try-on-v1-5 | — | — | 147.7 / 실행 | +| kolors-virtual-try-on-v1, kolors-virtual-try-on-v1-5 | — | — | 147.7 / 실행 (2026-09-15 EOL) | 총 이미지 크레딧 = **(크레딧 / 이미지) × `n`** (**Kling 3.0 Image**)에서; **Kling 3.0 Omni Image**에서는 `series_amount`를 곱합니다 (`kling-image-o1`은 항상 ×1). @@ -846,13 +851,17 @@ DALL·E와 Sora는 이미지당 또는 초당 고정 요금을 사용합니다. ### 비디오 -Gen3a Turbo, Gen4 Turbo, First-Last-Frame: **5초** 또는 **10초**. 총 크레딧 = **(크레딧 / 초) × `duration`**. +Gen4 Turbo: **5초** 또는 **10초**. 총 크레딧 = **(크레딧 / 초) × `duration`**. + + + **서비스 종료(EOL)**: `gen3a_turbo` 및 Runway 첫-마지막 프레임 노드는 **2026년 7월 30일**에 서비스가 종료되었습니다. 이미지-동영상 생성에는 Gen4 Turbo를 사용하세요. + -| 모델 | 크레딧 | -| :---------- | :---------- | -| gen3a_turbo | 15.09 / 초 | -| gen4_turbo | 15.09 / 초 | -| aleph2 | 84.48 / 초 | +| 모델 | 크레딧 | 상태 | +| :---------- | :---------- | :--- | +| gen4_turbo | 15.09 / 초 | 사용 가능 | +| gen3a_turbo | 15.09 / 초 | EOL (2026-07-30) | +| aleph2 | 84.48 / 초 | 사용 가능 | **Runway Aleph2 Keyframe** 및 **Runway Aleph2 Prompt Image**는 별도 요금이 없는 헬퍼 노드입니다. 요금은 **Runway Aleph2 Video to Video**에 부과됩니다. diff --git a/ko/tutorials/partner-nodes/runway/video-generation.mdx b/ko/tutorials/partner-nodes/runway/video-generation.mdx index aab91e761..095dab63e 100644 --- a/ko/tutorials/partner-nodes/runway/video-generation.mdx +++ b/ko/tutorials/partner-nodes/runway/video-generation.mdx @@ -1,65 +1,39 @@ --- title: "Runway 파트너 노드 동영상 생성 ComfyUI 공식 예제" -description: "이 글에서는 ComfyUI에서 Runway 노드를 사용해 동영상 생성 워크플로우를 어떻게 활용하는지 소개합니다." +description: "이 문서에서는 ComfyUI에서 Runway 노드를 사용한 동영상 생성 워크플로우 사용 방법을 소개합니다." sidebarTitle: "Runway 동영상 생성" -translationSourceHash: 4fe3a8fe +translationSourceHash: 3238866a translationFrom: tutorials/partner-nodes/runway/video-generation.mdx -translationBlockHashes: - "_intro": 726f6d02 - "Gen3a turbo Image-to-Video Workflow": 4d85b252 - "Gen4 turbo Image-to-Video Workflow": aed55b59 - "First-Last Frame Video Generation Workflow": b7f1102b --- import ReqHint from "/snippets/ko/tutorials/partner-nodes/req-hint.mdx"; import UpdateReminder from "/snippets/ko/tutorials/update-reminder.mdx"; -Runway는 생성형 AI에 중점을 둔 기업으로, 강력한 동영상 생성 기능을 제공합니다. 현재 ComfyUI는 Runway API를 통합하여, 동영상 생성을 위해 ComfyUI에서 관련 노드를 직접 사용할 수 있게 했습니다. +Runway는 생성형 AI에 특화된 기업으로, 강력한 동영상 생성 기능을 제공합니다. 현재 ComfyUI에는 Runway API가 통합되어 있어 관련 노드를 ComfyUI에서 직접 사용해 동영상을 생성할 수 있습니다. -현재 ComfyUI는 다음의 Runway 동영상 생성 모델을 기본적으로 통합하고 있습니다: -- Runway Gen3a 터보 -- Runway Gen4 터보 -- Runway 첫 번째 및 마지막 프레임을 동영상으로 +현재 ComfyUI에 네이티브로 통합된 Runway 동영상 생성 모델은 다음과 같습니다: +- Runway Gen4 turbo - - - -## Gen3a 터보 이미지-동영상 워크플로우 + + **서비스 종료(EOL)**: **Runway Gen3a Turbo** 및 **Runway 첫-마지막 프레임 동영상 변환**은 **2026년 7월 30일**에 서비스가 종료되었습니다. Runway는 해당일 Gen-3 Alpha Turbo를 폐기했습니다. 관련 Partner Nodes(`RunwayImageToVideoNodeGen3a`, `RunwayFirstLastFrameNode`) 및 워크플로 템플릿은 더 이상 지원되지 않습니다. + -### 1. 워크플로우 파일 다운로드 +### 제거된 워크플로 및 대체안 -아래 동영상에는 `메타데이터`에 워크플로우 정보가 포함되어 있습니다. 해당 워크플로우를 다운로드해 ComfyUI로 드래그하여 로드해 주세요. +| 제거된 템플릿 | 권장 대체 | +| :------------ | :-------- | +| `api_runway_gen3a_turbo_image_to_video` | [`api_runway_gen4_turo_image_to_video`](https://github.com/Comfy-Org/workflow_templates/blob/main/templates/api_runway_gen4_turo_image_to_video.json) (Gen4 Turbo) | +| `api_runway_first_last_frame` | [Kling 3.0 FLF2V](/ko/tutorials/partner-nodes/kling/kling-3-0) (`api_kling_v3_flf2v`) 또는 다른 첫-마지막 프레임 템플릿 | - - - -

Json 형식 워크플로우 파일 다운로드

- - -아래 이미지를 입력 이미지로 다운로드하세요. - -![ComfyUI Runway gen3a 터보 이미지-동영상 입력 이미지](https://raw.githubusercontent.com/Comfy-Org/example_workflows/refs/heads/main/api_nodes/runway/gen3a_turbo_image_to_video/steampunk.png) - -### 2. 워크플로우 단계별 완료하기 - -![ComfyUI Runway gen3a 터보 이미지-동영상 단계 안내](/images/tutorial/api_nodes/runway/runway_gen3a_turbo_image_to_video_step_guide.jpg) - -이미지의 숫자를 참고해 기본적인 이미지-동영상 워크플로우를 완료할 수 있습니다: -1. `Load Image` 노드에서 제공된 입력 이미지를 로드하세요. -2. `Runway Gen3a 터보` 노드에서 `prompt`을 설정해 동영상 내용을 설명하고, `duration` 매개변수를 수정해 동영상 길이를 설정하며, `ratio` 매개변수를 수정해 동영상 종횡비를 설정하세요. -3. `Run` 버튼을 클릭하거나, 단축키 `Ctrl(cmd) + Enter`를 사용해 동영상 생성을 실행하세요. -4. API가 결과를 반환할 때까지 기다린 후, `Save Video` 노드에서 생성된 동영상을 확인할 수 있습니다 (마우스 오른쪽 클릭해 저장). 해당 동영상은 `ComfyUI/output/` 디렉토리에도 저장됩니다. + + -## Gen4 터보 이미지-동영상 워크플로우 +## Gen4 turbo 이미지-동영상 워크플로 -### 1. 워크플로우 파일 다운로드 +### 1. 워크플로 파일 다운로드 -아래 동영상에는 `메타데이터`에 워크플로우 정보가 포함되어 있습니다. 해당 워크플로우를 다운로드해 ComfyUI로 드래그하여 로드해 주세요. +아래 동영상의 `metadata`에 워크플로 정보가 포함되어 있습니다. 다운로드하여 ComfyUI에 드래그하여 해당 워크플로를 로드하세요. -

Json 형식 워크플로우 파일 다운로드

- - -아래 이미지를 입력 이미지로 다운로드하세요. - -![ComfyUI Runway gen4 터보 이미지-동영상 입력 이미지](https://raw.githubusercontent.com/Comfy-Org/example_workflows/refs/heads/main/api_nodes/runway/gen4_turbo_image_to_video/godfather.jpg) - -### 2. 워크플로우 단계별 완료하기 - -![ComfyUI Runway gen4 터보 이미지-동영상 단계 안내](/images/tutorial/api_nodes/runway/runway_gen4_turbo_image_to_video_step_guide.jpg) - -이미지의 숫자를 참고해 기본적인 이미지-동영상 워크플로우를 완료할 수 있습니다: - -1. `Load Image` 노드에서 제공된 입력 이미지를 로드하세요. -2. `Runway Gen4 터보` 노드에서 `prompt`을 설정해 동영상 내용을 설명하고, `duration` 매개변수를 수정해 동영상 길이를 설정하며, `ratio` 매개변수를 수정해 동영상 종횡비를 설정하세요. -3. `Run` 버튼을 클릭하거나, 단축키 `Ctrl(cmd) + Enter`를 사용해 동영상 생성을 실행하세요. -4. API가 결과를 반환할 때까지 기다린 후, `Save Video` 노드에서 생성된 동영상을 확인할 수 있습니다 (마우스 오른쪽 클릭해 저장). 해당 동영상은 `ComfyUI/output/` 디렉토리에도 저장됩니다. - -## 첫 번째 및 마지막 프레임 동영상 생성 워크플로우 - - -### 1. 워크플로우 파일 다운로드 - -아래 동영상에는 `메타데이터`에 워크플로우 정보가 포함되어 있습니다. 해당 워크플로우를 다운로드해 ComfyUI로 드래그하여 로드해 주세요. - - - - -

Json 형식 워크플로우 파일 다운로드

+

JSON 형식 워크플로 파일 다운로드

 -아래 이미지를 입력 이미지로 다운로드하세요. +아래 이미지를 입력 이미지로 다운로드하세요 -![ComfyUI Runway gen4 터보 이미지-동영상 입력 이미지](https://raw.githubusercontent.com/Comfy-Org/example_workflows/refs/heads/main/api_nodes/runway/first_last_frame_to_video/first.jpg) -![ComfyUI Runway gen4 터보 이미지-동영상 입력 이미지](https://raw.githubusercontent.com/Comfy-Org/example_workflows/refs/heads/main/api_nodes/runway/first_last_frame_to_video/last.jpg) +![ComfyUI Runway gen4 turbo image to video Input Image](https://raw.githubusercontent.com/Comfy-Org/example_workflows/refs/heads/main/api_nodes/runway/gen4_turbo_image_to_video/godfather.jpg) -### 2. 워크플로우 단계별 완료하기 +### 2. 단계별로 워크플로 실행하기 -![ComfyUI Runway gen4 터보 이미지-동영상 단계 안내](/images/tutorial/api_nodes/runway/runway_first_last_frame_step_guide.jpg) +![ComfyUI Runway gen4 turbo image to video Step Guide](/images/tutorial/api_nodes/runway/runway_gen4_turbo_image_to_video_step_guide.jpg) -이미지의 숫자를 참고해 기본적인 첫 번째 및 마지막 프레임 동영상 워크플로우를 완료할 수 있습니다: +이미지의 번호를 참고하여 기본 이미지-동영상 워크플로를 실행할 수 있습니다: -1. `Load Image` 노드에서 시작 프레임을 로드하세요. -2. `Load Image` 노드에서 끝 프레임을 로드하세요. -3. `Runway 첫 번째 및 마지막 프레임을 동영상으로` 노드에서 `prompt`을 설정해 동영상 내용을 설명하고, `duration` 매개변수를 수정해 동영상 길이를 설정하며, `ratio` 매개변수를 수정해 동영상 종횡비를 설정하세요. -4. `Run` 버튼을 클릭하거나, 단축키 `Ctrl(cmd) + Enter`를 사용해 동영상 생성을 실행하세요. -5. API가 결과를 반환할 때까지 기다린 후, `Save Video` 노드에서 생성된 동영상을 확인할 수 있습니다 (마우스 오른쪽 클릭해 저장). 해당 동영상은 `ComfyUI/output/` 디렉토리에도 저장됩니다. +1. `Load Image` 노드에서 제공된 입력 이미지를 로드합니다. +2. `Runway Gen4 turbo` 노드에서 동영상 내용을 설명하는 `prompt`를 설정하고, `duration` 매개변수로 동영상 길이를, `ratio` 매개변수로 화면 비율을 설정합니다. +3. `Run` 버튼을 클릭하거나 `Ctrl(cmd) + Enter` 단축키로 동영상 생성을 실행합니다. +4. API 결과가 반환되면 `Save Video` 노드에서 생성된 동영상을 확인할 수 있습니다(우클릭으로 저장). 해당 동영상은 `ComfyUI/output/` 디렉터리에도 저장됩니다. diff --git a/snippets/ja/tutorials/partner-nodes/supported-models.mdx b/snippets/ja/tutorials/partner-nodes/supported-models.mdx index 4bcda0cd6..87cb9de42 100644 --- a/snippets/ja/tutorials/partner-nodes/supported-models.mdx +++ b/snippets/ja/tutorials/partner-nodes/supported-models.mdx @@ -2,7 +2,7 @@ - **Black Forest Labs**: Flux 1.1[pro] Ultra、Flux .1[pro]、Flux .1 Kontext Pro、Flux .1 Kontext Max、Flux.1 Canny Control、Flux.1 Depth Control、Flux.1 Expand、Flux.1 Fill - **Google**: Veo2、Veo 3.0、Gemini 2.5 Pro、Gemini 2.5 Flash、Gemini Image - **Ideogram**: V3、V2、V1 -- **Kling**: 2.0、1.6、1.5、v1、v2-1、v2-1-master、v2-maser、および各種エフェクト +- **Kling**: 3.0、3.0 Omni、2.6、O3、O3 Omni、モーションコントロールおよび各種エフェクト - **Magnific**: 画像リライティング、スタイル転送、クリエイティブアップスケール、プレサイスアップスケール、スキンエンハンサー - **Luma**: Photon、Ray2、Ray1.6、Ray-flash-2、Photo-flash-1 - **MiniMax**: テキストから動画へ（Text-to-Video）、画像から動画へ（Image-to-Video）、Hailuo-02、T2V-01、I2V-01 @@ -13,7 +13,7 @@ - **Recraft**: V3、V2、および各種ツール - **Hunyuan 3D**: テキストから3Dへ（Text-to-3D）、画像から3Dへ（Image-to-3D）、マルチビューから3Dへ（Multi-view-to-3D） - **Rodin**: 3D生成 -- **Runway**: テキストから画像へ（Text-to-Image）、最初と最後のフレームから動画へ（First-Last-Frame to Video）、画像から動画へ（Image to Video：Gen3a Turbo、Gen4 Turbo） +- **Runway**: テキストから画像へ（Text-to-Image）、画像から動画へ（Image to Video：Gen4 Turbo）、Aleph2 - **Stability AI**: Stable Image Ultra、Stable Diffusion 3.5 Large、Stable Diffusion 3.5 Medium、画像拡大（Image Upscale） - **Tripo**: v1-4、v2.0、v2.5 - **Vidu**: テキストから動画へ（Q1/Q2/Q3）、画像から動画へ（Q1/Q2/Q3）、参照動画（Q1/Q2）、開始・終了フレームから動画へ（Q1/Q2）、動画拡張（Q1） \ No newline at end of file diff --git a/snippets/ko/tutorials/partner-nodes/supported-models.mdx b/snippets/ko/tutorials/partner-nodes/supported-models.mdx index cf4a51fdd..8bb5b0955 100644 --- a/snippets/ko/tutorials/partner-nodes/supported-models.mdx +++ b/snippets/ko/tutorials/partner-nodes/supported-models.mdx @@ -3,7 +3,7 @@ - **Black Forest Labs**: Flux 1.1[pro] Ultra, Flux .1[pro], Flux .1 Kontext Pro, Flux .1 Kontext Max, Flux.1 Canny Control, Flux.1 Depth Control, Flux.1 Expand, Flux.1 Fill - **Google**: Veo2, Veo 3.0, Gemini 2.5 Pro, Gemini 2.5 Flash, Gemini Image - **Ideogram**: V3, V2, V1 -- **Kling**: 2.0, 1.6, 1.5, v1, v2-1, v2-1-master, v2-maser 및 다양한 효과 +- **Kling**: 3.0, 3.0 Omni, 2.6, O3, O3 Omni, 모션 컨트롤 및 다양한 효과 - **Luma**: Photon, Ray2, Ray1.6, Ray-flash-2, Photo-flash-1 - **MiniMax**: 텍스트 동영상 변환, 이미지 동영상 변환, Hailuo-02, T2V-01, I2V-01 - **Moonvalley**: 이미지 동영상 변환, 텍스트 동영상 변환, 동영상 대 동영상 @@ -13,7 +13,7 @@ - **Recraft**: V3, V2 및 다양한 도구 - **Hunyuan 3D**: 텍스트 3D 변환, 이미지 3D 변환, 다중 뷰 3D 변환 - **Rodin**: 3D 생성 -- **Runway**: 텍스트 이미지 변환, 첫 번째와 마지막 프레임 동영상 변환, 이미지 동영상 변환 (Gen3a Turbo, Gen4 Turbo) +- **Runway**: 텍스트 이미지 변환, 이미지 동영상 변환 (Gen4 Turbo), Aleph2 - **Stability AI**: Stable Image Ultra, Stable Diffusion 3.5 Large, Stable Diffusion 3.5 Medium, 이미지 업스케일링 - **Tripo**: v1-4, v2.0, v2.5 - **Vidu**: 이미지 동영상 변환, 참조 동영상, 시작과 끝을 동영상으로, 텍스트 동영상 변환 \ No newline at end of file diff --git a/snippets/tutorials/partner-nodes/supported-models.mdx b/snippets/tutorials/partner-nodes/supported-models.mdx index dcf3a7b04..77b1b5f33 100644 --- a/snippets/tutorials/partner-nodes/supported-models.mdx +++ b/snippets/tutorials/partner-nodes/supported-models.mdx @@ -2,7 +2,7 @@ - **Black Forest Labs**: Flux 1.1[pro] Ultra, Flux .1[pro], Flux .1 Kontext Pro, Flux .1 Kontext Max, Flux.1 Canny Control, Flux.1 Depth Control, Flux.1 Expand, Flux.1 Fill - **Google**: Veo2, Veo 3.0, Gemini 2.5 Pro, Gemini 2.5 Flash, Gemini Image - **Ideogram**: V3, V2, V1 -- **Kling**: 2.0, 1.6, 1.5, v1, v2-1, v2-1-master, v2-maser & Various Effects +- **Kling**: 3.0, 3.0 Omni, 2.6, O3, O3 Omni, Motion Control & Effects - **Luma**: Photon, Ray2, Ray1.6, Ray-flash-2, Photo-flash-1 - **MiniMax**: Text-to-Video, Image-to-Video, Hailuo-02, T2V-01, I2V-01 - **Moonvalley**: Image-to-Video, Text-to-Video, Video-to-Video @@ -12,7 +12,7 @@ - **Recraft**: V3, V2 & Various Tools - **Hunyuan 3D**: Text-to-3D, Image-to-3D, Multi-view-to-3D - **Rodin**: 3D Generation -- **Runway**: Text-to-Image, First-Last-Frame to Video, Image to Video (Gen3a Turbo, Gen4 Turbo) +- **Runway**: Text-to-Image, Image to Video (Gen4 Turbo), Aleph2 - **Stability AI**: Stable Image Ultra, Stable Diffusion 3.5 Large, Stable Diffusion 3.5 Medium, Image Upscale - **Tripo**: v1-4, v2.0, v2.5 - **Vidu**: Text-to-Video (Q1/Q2/Q3), Image-to-Video (Q1/Q2/Q3), Reference Video (Q1/Q2), Start-End to Video (Q1/Q2), Video Extension (Q1) diff --git a/snippets/zh/tutorials/partner-nodes/supported-models.mdx b/snippets/zh/tutorials/partner-nodes/supported-models.mdx index 51599c7a7..cf21a064b 100644 --- a/snippets/zh/tutorials/partner-nodes/supported-models.mdx +++ b/snippets/zh/tutorials/partner-nodes/supported-models.mdx @@ -2,7 +2,7 @@ - **Black Forest Labs**: Flux 1.1[pro] Ultra, Flux .1[pro], Flux .1 Kontext Pro, Flux .1 Kontext Max, Flux.1 Canny Control, Flux.1 Depth Control, Flux.1 Expand, Flux.1 Fill - **Google**: Veo2, Veo 3.0, Gemini 2.5 Pro, Gemini 2.5 Flash, Gemini Image - **Ideogram**: V3, V2, V1 -- **Kling**: 2.0, 1.6, 1.5, v1, v2-1, v2-1-master, v2-maser & 各种效果 +- **Kling**: 3.0、3.0 Omni、2.6、O3、O3 Omni、运动控制与特效 - **Magnific**: 图像重打光, 风格迁移, 创意放大, 精确放大, 皮肤增强 - **Luma**: Photon, Ray2, Ray1.6, Ray-flash-2, Photo-flash-1 - **MiniMax**: 文本转视频, 图像转视频, Hailuo-02, T2V-01, I2V-01 @@ -12,7 +12,7 @@ - **Pika**: 2.2 - **Recraft**: V3, V2 & 各种工具 - **Rodin**: 3D 生成 -- **Runway**: 文本转图像, 首尾帧转视频, 图像转视频 (Gen3a Turbo, Gen4 Turbo) +- **Runway**: 文本转图像, 图像转视频 (Gen4 Turbo), Aleph2 - **Stability AI**: Stable Image Ultra, Stable Diffusion 3.5 Large, Stable Diffusion 3.5 Medium, 图像放大 - **Tripo**: v1-4, v2.0, v2.5 - **Vidu**: 文本转视频 (Q1/Q2/Q3), 图像转视频 (Q1/Q2/Q3), 参考视频 (Q1/Q2), 开始-结束帧转视频 (Q1/Q2), 视频扩展 (Q1) diff --git a/tutorials/partner-nodes/kling/kling-3-0.mdx b/tutorials/partner-nodes/kling/kling-3-0.mdx index 648110e02..110fc7a68 100644 --- a/tutorials/partner-nodes/kling/kling-3-0.mdx +++ b/tutorials/partner-nodes/kling/kling-3-0.mdx @@ -54,3 +54,20 @@ For detailed examples, prompts, and video demonstrations of Kling 3.0's capabili | **Kling Video 3.0 Omni** | Video | Advanced video generation with audio-visual capabilities | | **Kling Image 3.0** | Image | High-quality image generation | | **Kling Image 3.0 Omni** | Image | Multi-modal image generation with enhanced features | + +## Legacy Kling models (EOL) + + + **End of life (EOL)**: The following legacy Kling models and workflow templates are scheduled for retirement on **September 15, 2026**: Kling V1.5, V1.6, V2.1, V2.1 Master, and the Kolors Virtual Try-On API. Related Partner Nodes remain in ComfyUI but these model options will stop working after the retirement date. + + +### Retired workflow templates and replacements + +| Removed template | Suggested replacement | +| :--------------- | :-------------------- | +| `api_kling_i2v` (V2.1 Master) | [`api_kling_v3_i2v`](https://github.com/Comfy-Org/workflow_templates/blob/main/templates/api_kling_v3_i2v.json) or [`api_kling2_6_i2v`](https://github.com/Comfy-Org/workflow_templates/blob/main/templates/api_kling2_6_i2v.json) | +| `api_kling_effects` (V1.6) | Kling 3.0 effect workflows (`api_kling_v3_*`) | +| `api_kling_flf` (V1.6) | [`api_kling_v3_flf2v`](https://github.com/Comfy-Org/workflow_templates/blob/main/templates/api_kling_v3_flf2v.json) or [`api_kling_o3_flf2v`](https://github.com/Comfy-Org/workflow_templates/blob/main/templates/api_kling_o3_flf2v.json) | +| `api_kling_dual_characters_effects` (V1.6) | Kling 3.0 effect workflows (`api_kling_v3_*`) | + +For virtual try-on, use [Flux Virtual Try-On](/built-in-nodes/FluxVTONode) (`api_flux_vto`) or other supported alternatives. Flux VTO and Gemini-based fashion templates are not affected by this retirement. diff --git a/tutorials/partner-nodes/pricing.mdx b/tutorials/partner-nodes/pricing.mdx index 38633bf94..13bf12705 100644 --- a/tutorials/partner-nodes/pricing.mdx +++ b/tutorials/partner-nodes/pricing.mdx @@ -483,7 +483,11 @@ Always generates audio; the audio toggle is ignored. | motion control | — | std | 14.77 | | motion control | — | pro | 23.63 | -#### Legacy (v2-5-turbo, v2-master, v1.x) +#### Legacy (v2-5-turbo, v2-master, v1.x) — EOL September 15, 2026 + + + **End of life (EOL)**: Kling V1.5, V1.6, V2.1, V2.1 Master, and Kolors Virtual Try-On are scheduled for retirement on **September 15, 2026**. Pricing below is retained for reference until removal. + | Model | mode | Credits / sec | | :------------------------------------------- | :------- | :------------ | @@ -523,7 +527,7 @@ Always generates audio; the audio toggle is ignored. | kling-v2 | — | No, Yes | 2.95 / image | | kling-v1-5 | — | No | 2.95 / image | | kling-v1-5 | — | Yes | 5.91 / image | -| kolors-virtual-try-on-v1, kolors-virtual-try-on-v1-5 | — | — | 147.7 / run | +| kolors-virtual-try-on-v1, kolors-virtual-try-on-v1-5 | — | — | 147.7 / run (EOL Sep 15, 2026) | Total image credits = **(credits / image) × `n`** on **Kling 3.0 Image**; multiply by `series_amount` on **Kling 3.0 Omni Image** (`kling-image-o1` always ×1). @@ -808,13 +812,17 @@ Fast edit/remix models use a flat base rate; upscale does not change the display ### Video -Gen3a Turbo, Gen4 Turbo, and First-Last-Frame: **5s** or **10s**. Total credits = **(credits / sec) × `duration`**. +Gen4 Turbo: **5s** or **10s**. Total credits = **(credits / sec) × `duration`**. + + + **End of life (EOL)**: `gen3a_turbo` and the Runway First-Last-Frame node reached end of life on **July 30, 2026**. Use Gen4 Turbo for image-to-video instead. + -| model | Credits | -| :---------- | :---------- | -| gen3a_turbo | 15.09 / sec | -| gen4_turbo | 15.09 / sec | -| aleph2 | 84.48 / sec | +| model | Credits | Status | +| :---------- | :---------- | :----- | +| gen4_turbo | 15.09 / sec | Active | +| gen3a_turbo | 15.09 / sec | EOL (July 30, 2026) | +| aleph2 | 84.48 / sec | Active | **Runway Aleph2 Keyframe** and **Runway Aleph2 Prompt Image** are helper nodes with no separate charge; cost is on **Runway Aleph2 Video to Video**. diff --git a/tutorials/partner-nodes/runway/video-generation.mdx b/tutorials/partner-nodes/runway/video-generation.mdx index 5e43ef55a..36e3eede8 100644 --- a/tutorials/partner-nodes/runway/video-generation.mdx +++ b/tutorials/partner-nodes/runway/video-generation.mdx @@ -9,43 +9,22 @@ import UpdateReminder from "/snippets/tutorials/update-reminder.mdx"; Runway is a company focused on generative AI, providing powerful video generation capabilities. Currently, ComfyUI has integrated the Runway API, allowing you to directly use the related nodes in ComfyUI for video generation. -Currently, ComfyUI natively integrates the following Runway video generation models: -- Runway Gen3a turbo +Currently, ComfyUI natively integrates the following Runway video generation model: - Runway Gen4 turbo -- Runway First Last Frame to video - - - -## Gen3a turbo Image-to-Video Workflow + + **End of life (EOL)**: **Runway Gen3a Turbo** and **Runway First-Last-Frame to Video** reached end of life on **July 30, 2026**. Runway retired Gen-3 Alpha Turbo on that date. The related Partner Nodes (`RunwayImageToVideoNodeGen3a`, `RunwayFirstLastFrameNode`) and workflow templates are deprecated and no longer supported. + -### 1. Workflow File Download - -The video below contains workflow information in its `metadata`. Please download and drag it into ComfyUI to load the corresponding workflow. +### Retired workflows and replacements - +| Removed template | Suggested replacement | +| :--------------- | :-------------------- | +| `api_runway_gen3a_turbo_image_to_video` | [`api_runway_gen4_turo_image_to_video`](https://github.com/Comfy-Org/workflow_templates/blob/main/templates/api_runway_gen4_turo_image_to_video.json) (Gen4 Turbo) | +| `api_runway_first_last_frame` | [Kling 3.0 FLF2V](/tutorials/partner-nodes/kling/kling-3-0) (`api_kling_v3_flf2v`) or other first-last-frame templates | - -

Download Json Format Workflow File

- - -Download the image below as input image - -![ComfyUI Runway gen3a turbo image to video Input Image](https://raw.githubusercontent.com/Comfy-Org/example_workflows/refs/heads/main/api_nodes/runway/gen3a_turbo_image_to_video/steampunk.png) - -### 2. Complete the Workflow Execution Step by Step - -![ComfyUI Runway gen3a turbo image to video Step Guide](/images/tutorial/api_nodes/runway/runway_gen3a_turbo_image_to_video_step_guide.jpg) - -You can refer to the numbers in the image to complete the basic image-to-video workflow execution: -1. In the `Load Image` node, load the provided input image -2. In the `Runway Gen3a turbo` node, set the `prompt` to describe video content, modify the `duration` parameter to set video length, modify the `ratio` parameter to set video aspect ratio -3. Click the `Run` button, or use the shortcut `Ctrl(cmd) + Enter` to execute video generation. -4. After waiting for the API to return results, you can view the generated video in the `Save Video` node (right-click to save). The corresponding video will also be saved to the `ComfyUI/output/` directory. + + ## Gen4 turbo Image-to-Video Workflow @@ -77,37 +56,3 @@ You can refer to the numbers in the image to complete the basic image-to-video w 2. In the `Runway Gen4 turbo` node, set the `prompt` to describe video content, modify the `duration` parameter to set video length, modify the `ratio` parameter to set video aspect ratio 3. Click the `Run` button, or use the shortcut `Ctrl(cmd) + Enter` to execute video generation. 4. After waiting for the API to return results, you can view the generated video in the `Save Video` node (right-click to save). The corresponding video will also be saved to the `ComfyUI/output/` directory. - -## First-Last Frame Video Generation Workflow - - -### 1. Workflow File Download - -The video below contains workflow information in its `metadata`. Please download and drag it into ComfyUI to load the corresponding workflow. - - - - -

Download Json Format Workflow File

- - -Download the images below as input images - -![ComfyUI Runway gen4 turbo image to video Input Image](https://raw.githubusercontent.com/Comfy-Org/example_workflows/refs/heads/main/api_nodes/runway/first_last_frame_to_video/first.jpg) -![ComfyUI Runway gen4 turbo image to video Input Image](https://raw.githubusercontent.com/Comfy-Org/example_workflows/refs/heads/main/api_nodes/runway/first_last_frame_to_video/last.jpg) - -### 2. Complete the Workflow Execution Step by Step - -![ComfyUI Runway gen4 turbo image to video Step Guide](/images/tutorial/api_nodes/runway/runway_first_last_frame_step_guide.jpg) - -You can refer to the numbers in the image to complete the basic first-last frame to video workflow execution: - -1. In the `Load Image` node, load the starting frame -2. In the `Load Image` node, load the ending frame -3. In the `Runway First-Last-Frame to Video` node, set the `prompt` to describe video content, modify the `duration` parameter to set video length, modify the `ratio` parameter to set video aspect ratio -4. Click the `Run` button, or use the shortcut `Ctrl(cmd) + Enter` to execute video generation. -5. After waiting for the API to return results, you can view the generated video in the `Save Video` node (right-click to save). The corresponding video will also be saved to the `ComfyUI/output/` directory. \ No newline at end of file diff --git a/zh/built-in-nodes/RunwayFirstLastFrameNode.mdx b/zh/built-in-nodes/RunwayFirstLastFrameNode.mdx index fce13e32a..d1088069e 100644 --- a/zh/built-in-nodes/RunwayFirstLastFrameNode.mdx +++ b/zh/built-in-nodes/RunwayFirstLastFrameNode.mdx @@ -6,7 +6,13 @@ icon: "circle" mode: wide --- -Runway 首尾帧生成视频节点通过上传首帧、尾帧及文本提示词来生成视频。该节点利用 Runway 的 Gen-3 模型，在提供的起始帧与结束帧之间创建平滑过渡。当结束帧与起始帧差异显著时，此功能尤其适用于复杂转场场景。 +--- + + + **已退役（EOL）**：此节点已于 **2026 年 7 月 30 日** 达到生命周期终点。首尾帧视频请使用 [Kling 3.0 首尾帧转视频](/zh/tutorials/partner-nodes/kling/kling-3-0) 或其他受支持的 FLF2V 模板。 + + +Runway 首尾帧生成视频节点通过上传首帧、尾帧及文本提示词来生成视频。 ## 输入 diff --git a/zh/built-in-nodes/RunwayImageToVideoNodeGen3a.mdx b/zh/built-in-nodes/RunwayImageToVideoNodeGen3a.mdx index 816c11381..780e2a056 100644 --- a/zh/built-in-nodes/RunwayImageToVideoNodeGen3a.mdx +++ b/zh/built-in-nodes/RunwayImageToVideoNodeGen3a.mdx @@ -6,7 +6,13 @@ icon: "circle" mode: wide --- -Runway 图像转视频（Gen3a Turbo）节点使用 Runway 的 Gen3a Turbo 模型，从单个起始帧生成视频。它接收文本提示和初始图像帧，然后根据指定的时长和宽高比创建视频序列。此节点连接到 Runway 的 API 以远程处理生成过程。 +--- + + + **已退役（EOL）**：此节点已于 **2026 年 7 月 30 日** 达到生命周期终点（Runway 下线 Gen-3 Alpha Turbo）。请改用 [Runway Gen4 Turbo](/zh/built-in-nodes/RunwayImageToVideoNodeGen4) 或 [Gen4 Turbo 工作流](/zh/tutorials/partner-nodes/runway/video-generation)。 + + +Runway 图像转视频（Gen3a Turbo）节点使用 Runway 的 Gen3a Turbo 模型，从单个起始帧生成视频。 ## 输入 diff --git a/zh/tutorials/partner-nodes/kling/kling-3-0.mdx b/zh/tutorials/partner-nodes/kling/kling-3-0.mdx index 3902797b6..21b1dd003 100644 --- a/zh/tutorials/partner-nodes/kling/kling-3-0.mdx +++ b/zh/tutorials/partner-nodes/kling/kling-3-0.mdx @@ -2,10 +2,18 @@ title: "Kling 3.0 视频和图像生成 ComfyUI 官方示例" description: "本文将介绍如何在 ComfyUI 中使用 Kling 3.0 模型，实现多镜头视频生成、主体一致性、多语言音频和原生文字渲染" sidebarTitle: "Kling 3.0" -translationSourceHash: 9ec27e2e +translationSourceHash: 888c48f3 translationFrom: tutorials/partner-nodes/kling/kling-3-0.mdx +translationBlockHashes: + "_intro": 6176006f + "About Kling 3.0": 2bae40cd + "Kling 3.0 workflows": 383f3e6a + "Learn more": 75a02ac4 + "Available models": f566da3f + "Legacy Kling models (EOL)": 8364a20e --- + import ReqHint from "/snippets/zh/tutorials/partner-nodes/req-hint.mdx"; import UpdateReminder from "/snippets/zh/tutorials/update-reminder.mdx"; @@ -56,3 +64,20 @@ Kling 3.0 是目前最先进的多模态生成系统之一，现已通过合作 | **Kling Video 3.0 Omni** | 视频 | 具有视听能力的高级视频生成 | | **Kling Image 3.0** | 图像 | 高质量图像生成 | | **Kling Image 3.0 Omni** | 图像 | 具有增强功能的多模态图像生成 | + +## 旧版 Kling 模型（EOL） + + + **已退役（EOL）**：以下旧版 Kling 模型及工作流模板计划于 **2026 年 9 月 15 日** 退役：Kling V1.5、V1.6、V2.1、V2.1 Master 及 Kolors 虚拟试穿 API。相关 Partner Nodes 仍保留在 ComfyUI 中，但这些模型选项在退役日期后将无法使用。 + + +### 已下架工作流模板与替代方案 + +| 已移除模板 | 建议替代 | +| :--------- | :------- | +| `api_kling_i2v`（V2.1 Master） | [`api_kling_v3_i2v`](https://github.com/Comfy-Org/workflow_templates/blob/main/templates/api_kling_v3_i2v.json) 或 [`api_kling2_6_i2v`](https://github.com/Comfy-Org/workflow_templates/blob/main/templates/api_kling2_6_i2v.json) | +| `api_kling_effects`（V1.6） | Kling 3.0 特效工作流（`api_kling_v3_*`） | +| `api_kling_flf`（V1.6） | [`api_kling_v3_flf2v`](https://github.com/Comfy-Org/workflow_templates/blob/main/templates/api_kling_v3_flf2v.json) 或 [`api_kling_o3_flf2v`](https://github.com/Comfy-Org/workflow_templates/blob/main/templates/api_kling_o3_flf2v.json) | +| `api_kling_dual_characters_effects`（V1.6） | Kling 3.0 特效工作流（`api_kling_v3_*`） | + +虚拟试穿请使用 [Flux 虚拟试穿](/zh/built-in-nodes/FluxVTONode)（`api_flux_vto`）或其他受支持的替代方案。Flux VTO 和基于 Gemini 的时尚模板不受本次退役影响。 diff --git a/zh/tutorials/partner-nodes/pricing.mdx b/zh/tutorials/partner-nodes/pricing.mdx index c7586e088..176386a07 100644 --- a/zh/tutorials/partner-nodes/pricing.mdx +++ b/zh/tutorials/partner-nodes/pricing.mdx @@ -3,11 +3,11 @@ title: "定价" description: "本文列出了当前合作伙伴节点的定价。" sidebarTitle: "定价" mode: "wide" -translationSourceHash: 5f783396 +translationSourceHash: 7ffb68e7 translationFrom: tutorials/partner-nodes/pricing.mdx translationBlockHashes: - "_intro": 845592d4 - "Anthropic": 57a39b62 + "_intro": ada9999a + "Anthropic": 97b89fc6 "Beeble": d1b19f61 "BFL": 3ff6bff0 "Bria": 232ed8f6 @@ -16,23 +16,23 @@ translationBlockHashes: "Magnific": 4000e7e1 "Google": 21dc3165 "HappyHorse": bceb584a - "HeyGen": c9264f13 + "HeyGen": 47d0a040 "Hitpaw": 320c0537 "Ideogram": 9410bf72 "Krea": fb20c257 - "Kling": cdf2c899 + "Kling": 8b8fb275 "Lightricks": 4870964f "Luma": 655207a5 "Meshy": 6cd06881 "Minimax": 28c7cf5e "OpenAI": db11f921 - "OpenRouter": 06317890 + "OpenRouter": eb16e5b0 "Pixverse": 8612b816 "Quiver": b9d45a82 "Recraft": 7eb9a1a7 "Reve": 5be5c43a "Rodin 3D": 2eb41834 - "Runway": 94ec479a + "Runway": 63aa1c03 "Sonilo": 48b9c581 "sync.so": 590402a9 "Tencent": f1efbad9 @@ -46,6 +46,7 @@ translationBlockHashes: --- + 下表列出了当前合作伙伴节点的定价。所有价格均以积分计。 ## Anthropic @@ -524,7 +525,11 @@ Seedream 5.0 Pro 使用基于分辨率的计费方式：**1K**（≤2.36 百 | 动作控制 | — | 标准 | 14.77 | | 动作控制 | — | 专业 | 23.63 | -#### 旧版（v2-5-turbo, v2-master, v1.x） +#### 旧版（v2-5-turbo, v2-master, v1.x）— 2026 年 9 月 15 日 EOL + + + **已退役（EOL）**：Kling V1.5、V1.6、V2.1、V2.1 Master 及 Kolors 虚拟试穿计划于 **2026 年 9 月 15 日** 退役。以下定价保留供参考，直至移除。 + | 模型 | 模式 | 积分 / 秒 | | :------------------------------------------- | :------- | :------------ | @@ -564,7 +569,7 @@ Seedream 5.0 Pro 使用基于分辨率的计费方式：**1K**（≤2.36 百 | kling-v2 | — | 否, 是 | 2.95 / 张 | | kling-v1-5 | — | 否 | 2.95 / 张 | | kling-v1-5 | — | 是 | 5.91 / 张 | -| kolors-virtual-try-on-v1, kolors-virtual-try-on-v1-5 | — | — | 147.7 / 次 | +| kolors-virtual-try-on-v1, kolors-virtual-try-on-v1-5 | — | — | 147.7 / 次（2026-09-15 EOL） | 总图片积分 = **(积分/张) × `n`**（**Kling 3.0 Image**）；**Kling 3.0 Omni Image** 乘以 `series_amount`（`kling-image-o1` 始终 ×1）。 @@ -849,13 +854,17 @@ DALL·E 和 Sora 使用固定的每张图片或每秒费率。**OpenAI GPT Image ### 视频 -Gen3a Turbo、Gen4 Turbo 和 First-Last-Frame：**5s** 或 **10s**。总积分 = **(积分/秒) × `时长`**。 +Gen4 Turbo：**5s** 或 **10s**。总积分 = **(积分/秒) × `时长`**。 + + + **已退役（EOL）**：`gen3a_turbo` 及 Runway 首尾帧节点已于 **2026 年 7 月 30 日** 达到生命周期终点。请改用 Gen4 Turbo 进行图生视频。 + -| 模型 | 积分 | -| :---------- | :---------- | -| gen3a_turbo | 15.09 / 秒 | -| gen4_turbo | 15.09 / 秒 | -| aleph2 | 84.48 / 秒 | +| 模型 | 积分 | 状态 | +| :---------- | :---------- | :--- | +| gen4_turbo | 15.09 / 秒 | 可用 | +| gen3a_turbo | 15.09 / 秒 | EOL（2026-07-30） | +| aleph2 | 84.48 / 秒 | 可用 | **Runway Aleph2 Keyframe** 和 **Runway Aleph2 Prompt Image** 为辅助节点，不单独收费；费用体现在 **Runway Aleph2 Video to Video** 上。 diff --git a/zh/tutorials/partner-nodes/runway/video-generation.mdx b/zh/tutorials/partner-nodes/runway/video-generation.mdx index 7000f87c8..64f4bcbc6 100644 --- a/zh/tutorials/partner-nodes/runway/video-generation.mdx +++ b/zh/tutorials/partner-nodes/runway/video-generation.mdx @@ -2,13 +2,8 @@ title: " Runway 合作伙伴节点 视频生成 ComfyUI 官方示例" description: "本文将介绍如何在 ComfyUI 中使用 Runway 节点进行视频生成的相关工作流" sidebarTitle: "Runway 视频生成" -translationSourceHash: 4fe3a8fe +translationSourceHash: 3238866a translationFrom: tutorials/partner-nodes/runway/video-generation.mdx -translationBlockHashes: - "_intro": 726f6d02 - "Gen3a turbo Image-to-Video Workflow": 4d85b252 - "Gen4 turbo Image-to-Video Workflow": aed55b59 - "First-Last Frame Video Generation Workflow": b7f1102b --- @@ -17,43 +12,22 @@ import UpdateReminder from "/snippets/zh/tutorials/update-reminder.mdx"; Runway 是一家专注于生成式 AI 的科技公司，提供强大的视频生成功能。目前 ComfyUI 已集成 Runway API，你可以直接在 ComfyUI 中使用相关节点进行视频生成。 -目前 ComfyUI 中原生集成了 Runway 的以下视频生成模型： -- Runway Gen3a turbo +目前 ComfyUI 中原生集成了以下 Runway 视频生成模型： - Runway Gen4 turbo -- Runway First Last Frame to video - - - -## Gen3a turbo 图生视频工作流 - -### 1. 工作流文件下载 - -下面的视频的`metadata`中已经包含工作流信息，请下载并拖入 ComfyUI 中加载对应工作流。 - - + + **已退役（EOL）**：**Runway Gen3a Turbo** 和 **Runway 首尾帧转视频** 已于 **2026 年 7 月 30 日** 达到生命周期终点。Runway 于该日下线 Gen-3 Alpha Turbo。相关 Partner Nodes（`RunwayImageToVideoNodeGen3a`、`RunwayFirstLastFrameNode`）及工作流模板已弃用，不再受支持。 + - -

下载 Json 格式工作流文件

- - -下载下面的图片作为输入图片 - -![ComfyUI Runway gen3a turbo image to video Input Image](https://raw.githubusercontent.com/Comfy-Org/example_workflows/refs/heads/main/api_nodes/runway/gen3a_turbo_image_to_video/steampunk.png) - -### 2. 按步骤完成工作流的运行 +### 已下架工作流与替代方案 -![ComfyUI Runway gen3a turbo image to video Step Guide](/images/tutorial/api_nodes/runway/runway_gen3a_turbo_image_to_video_step_guide.jpg) +| 已移除模板 | 建议替代 | +| :--------- | :------- | +| `api_runway_gen3a_turbo_image_to_video` | [`api_runway_gen4_turo_image_to_video`](https://github.com/Comfy-Org/workflow_templates/blob/main/templates/api_runway_gen4_turo_image_to_video.json)（Gen4 Turbo） | +| `api_runway_first_last_frame` | [Kling 3.0 首尾帧转视频](/zh/tutorials/partner-nodes/kling/kling-3-0)（`api_kling_v3_flf2v`）或其他首尾帧模板 | -你可参考图片中的序号来完成最基础的文生图工作流运行： -1. 在 `Load Image` 节点中加载提供的输入图片 -2. 在 `Runway Gen3a turbo` 节点中设置 `prompt` 描述视频内容，修改 `duration` 参数来设置视频时长, 修改 `ratio` 参数来设置视频宽高比 -3. 点击 `Run` 按钮，或者使用快捷键 `Ctrl(cmd) + Enter(回车)` 来执行视频的生成。 -4. 等待 API 返回结果后，你可在 `Save Video` 节点中查看生成的视频（右键菜单可以保存），对应的视频也会被保存至 `ComfyUI/output/` 目录下。 + + ## Gen4 turbo 图生视频工作流 @@ -85,37 +59,3 @@ Runway 是一家专注于生成式 AI 的科技公司，提供强大的视频生 2. 在 `Runway Gen4 turbo` 节点中设置 `prompt` 描述视频内容，修改 `duration` 参数来设置视频时长, 修改 `ratio` 参数来设置视频宽高比 3. 点击 `Run` 按钮，或者使用快捷键 `Ctrl(cmd) + Enter(回车)` 来执行视频的生成。 4. 等待 API 返回结果后，你可在 `Save Video` 节点中查看生成的视频（右键菜单可以保存），对应的视频也会被保存至 `ComfyUI/output/` 目录下。 - -## 首尾帧视频生成工作流 - - -### 1. 工作流文件下载 - -下面的视频的`metadata`中已经包含工作流信息，请下载并拖入 ComfyUI 中加载对应工作流。 - - - - -

下载 Json 格式工作流文件

- - -下载下面的图片作为输入图片 - -![ComfyUI Runway gen4 turbo image to video Input Image](https://raw.githubusercontent.com/Comfy-Org/example_workflows/refs/heads/main/api_nodes/runway/first_last_frame_to_video/first.jpg) -![ComfyUI Runway gen4 turbo image to video Input Image](https://raw.githubusercontent.com/Comfy-Org/example_workflows/refs/heads/main/api_nodes/runway/first_last_frame_to_video/last.jpg) - -### 2. 按步骤完成工作流的运行 - -![ComfyUI Runway gen4 turbo image to video Step Guide](/images/tutorial/api_nodes/runway/runway_first_last_frame_step_guide.jpg) - -你可参考图片中的序号来完成最基础的文生图工作流运行： - -1. 在 `Load Image` 节点中加载起始帧 -2. 在 `Load Image` 节点中加载结束帧 -3. 在 `Runway First-Last-Frame to Video` 节点中设置 `prompt` 描述视频内容，修改 `duration` 参数来设置视频时长, 修改 `ratio` 参数来设置视频宽高比 -4. 点击 `Run` 按钮，或者使用快捷键 `Ctrl(cmd) + Enter(回车)` 来执行视频的生成。 -5. 等待 API 返回结果后，你可在 `Save Video` 节点中查看生成的视频（右键菜单可以保存），对应的视频也会被保存至 `ComfyUI/output/` 目录下。