Refine API node docs

comfyui-wiki · comfyui-wiki · commit 11d640c149cd · 2025-05-27T22:06:19.000+08:00
diff --git a/images/tutorial/api_nodes/rodin/other_nodes.jpg b/images/tutorial/api_nodes/rodin/other_nodes.jpg
diff --git a/images/tutorial/api_nodes/tripo/other_nodes.jpg b/images/tutorial/api_nodes/tripo/other_nodes.jpg
diff --git a/tutorials/api-nodes/google/gemini.mdx b/tutorials/api-nodes/google/gemini.mdx
@@ -6,7 +6,7 @@ sidebarTitle: "Google Gemini"
 
 import ReqHint from "/snippets/tutorials/api-nodes/req-hint.mdx";
 
-This node allows you to use Google Gemini's API to complete conversational functions.
+Google Gemini is a powerful AI model developed by Google, supporting conversational and text generation functions. Currently, ComfyUI has integrated the Google Gemini API, allowing you to directly use the related nodes in ComfyUI to complete conversational functions.
 
 In this guide, we will walk you through completing the corresponding conversational functionality.
 
diff --git a/tutorials/api-nodes/openai/chat.mdx b/tutorials/api-nodes/openai/chat.mdx
@@ -6,7 +6,7 @@ sidebarTitle: "OpenAI Chat"
 
 import ReqHint from "/snippets/tutorials/api-nodes/req-hint.mdx";
 
-This node allows you to use OpenAI's Chat API to complete conversational functions.
+OpenAI is a company focused on generative AI, providing powerful conversational capabilities. Currently, ComfyUI has integrated the OpenAI API, allowing you to directly use the related nodes in ComfyUI to complete conversational functions.
 
 In this guide, we will walk you through completing the corresponding conversational functionality.
 
diff --git a/tutorials/api-nodes/rodin/model-generation.mdx b/tutorials/api-nodes/rodin/model-generation.mdx
@@ -6,9 +6,13 @@ sidebarTitle: "Model Generation"
 
 import ReqHint from "/snippets/tutorials/api-nodes/req-hint.mdx";
 
+Hyper3D Rodin (hyper3d.ai) is a platform focused on rapidly generating high-quality, production-ready 3D models and materials through artificial intelligence.
+ComfyUI has now natively integrated the corresponding Rodin model generation API, allowing you to conveniently use the related nodes in ComfyUI for model generation.
+
 Currently, ComfyUI's API nodes support the following Rodin model generation capabilities:
 - Single-view model generation
 - Multi-view model generation
+- Model generation with different levels of detail
 
 <ReqHint/>
 
@@ -75,3 +79,9 @@ You can refer to the numbers in the image to complete the basic text-to-image wo
 2. Click the `Run` button, or use the shortcut `Ctrl(cmd) + Enter` to execute model generation. After the workflow completes, the corresponding model will be automatically saved to the `ComfyUI/output/Rodin` directory
 3. In the `Preview 3D` node, click to expand the menu
 4. Select `Export` to directly export the corresponding model
+
+## Other Related Nodes
+
+Currently, Rodin provides different types of model generation nodes in ComfyUI, since the corresponding input conditions are the same as the workflow introduced in this article, you can enable them as needed. In addition, we have provided corresponding nodes in the corresponding templates, you can also modify the corresponding node mode as needed to enable them
+
+![Rodin Other Related Nodes](/images/tutorial/api_nodes/rodin/other_nodes.jpg)
diff --git a/tutorials/api-nodes/runway/image-generation.mdx b/tutorials/api-nodes/runway/image-generation.mdx
@@ -6,9 +6,11 @@ sidebarTitle: "Runway Image Generation"
 
 import ReqHint from "/snippets/tutorials/api-nodes/req-hint.mdx";
 
-This node allows you to use Runway's image generation models to create high-quality, detail-rich image content through text prompts or reference images.
+Runway is a company focused on generative AI, providing powerful image generation capabilities. Its models support features such as style transfer, image extension, and detail control. Currently, ComfyUI has integrated the Runway API, allowing you to directly use the related nodes in ComfyUI for image generation.
 
-In this guide, we will walk you through setting up the corresponding text-to-image and reference-to-image workflows.
+In this guide, we will walk you through the following workflows:
+- Text-to-image
+- Reference-to-image
 
 <ReqHint/>
 
diff --git a/tutorials/api-nodes/runway/video-generation.mdx b/tutorials/api-nodes/runway/video-generation.mdx
@@ -6,6 +6,8 @@ sidebarTitle: "Runway Video Generation"
 
 import ReqHint from "/snippets/tutorials/api-nodes/req-hint.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
 - Runway Gen4 turbo
diff --git a/tutorials/api-nodes/tripo/model-generation.mdx b/tutorials/api-nodes/tripo/model-generation.mdx
@@ -6,12 +6,15 @@ sidebarTitle: "Model Generation"
 
 import ReqHint from "/snippets/tutorials/api-nodes/req-hint.mdx";
 
+Tripo AI is a company focused on generative AI 3D modeling. It provides user-friendly platforms and API services that can quickly convert text prompts or 2D images (single or multiple) into high-quality 3D models.
+ComfyUI has now natively integrated the corresponding Tripo API, allowing you to conveniently use the related nodes in ComfyUI for model generation.
+
 Currently, ComfyUI's API nodes support the following Tripo model generation capabilities:
 - Text-to-model
 - Image-to-model
 - Multi-view model generation
-- Bone binding
-- Bone animation
+- Rig model
+- Retarget rigged model
 
 <ReqHint/>
 
@@ -95,3 +98,13 @@ You can refer to the numbers in the image to complete the basic multi-view to mo
 3. Click the `Run` button, or use the shortcut `Ctrl(cmd) + Enter` to execute model generation. After the workflow completes, the corresponding model will be automatically saved to the `ComfyUI/output/` directory
 4. For other view inputs, you can refer to the step diagram and set the corresponding node mode to `Always` to enable it
 5. For model download, please refer to the instructions in the text-to-model section
+
+##  Subsequent Task Processing for the Same Task
+
+Tripo's corresponding nodes provide subsequent processing for the same task, you only need to input the corresponding `model_task_id` in the relevant nodes, and we have also provided the corresponding nodes in the relevant templates, you can also modify the corresponding node mode as needed to enable it
+
+![Tripo Task Processing](/images/tutorial/api_nodes/tripo/other_nodes.jpg)
+
+<Error>
+    The `Tripo: Refine Draft model` node only supports V1.4 model, other models do not support it
+</Error>
diff --git a/tutorials/video/wan/vace.mdx b/tutorials/video/wan/vace.mdx
@@ -209,14 +209,16 @@ Please follow the numbered steps in the image to ensure smooth workflow executio
 ## VACE Video Outpainting Workflow
 
 [To be updated]
-- The Portable version template has been updated, please refer to the template notes
-- The Desktop version has not been updated yet
+
 
 ## VACE First-Last Frame Video Generation
 
 [To be updated]
-- The Portable version template has been updated, please refer to the template notes
-- The Desktop version has not been updated yet
+
+To ensure that the first and last frames are effective, the video `length` setting must satisfy that `length-1` is divisible by 4.
+
+The corresponding `Batch_size` setting must satisfy `Batch_size = length - 2`
+
 
 ## Related Node Documentation
 
diff --git a/zh-CN/tutorials/api-nodes/google/gemini.mdx b/zh-CN/tutorials/api-nodes/google/gemini.mdx
@@ -6,7 +6,7 @@ sidebarTitle: "Google Gemini"
 
 import ReqHint from "/snippets/zh/tutorials/api-nodes/req-hint.mdx";
 
-节点允许你使用节点允许你使用 Google Gemini 的 API 来完成对话功能。
+Google Gemini 是 Google 推出的一款强大的 AI 模型，支持对话、文本生成等多种功能。目前 ComfyUI 已集成 Google Gemini API，你可以直接在 ComfyUI 中使用相关节点来完成对话功能。
 
 本篇指南中，我们将引导你完成对应对话功能。
 
diff --git a/zh-CN/tutorials/api-nodes/openai/chat.mdx b/zh-CN/tutorials/api-nodes/openai/chat.mdx
@@ -6,7 +6,7 @@ sidebarTitle: "OpenAI Chat"
 
 import ReqHint from "/snippets/zh/tutorials/api-nodes/req-hint.mdx";
 
-节点允许你使用节点允许你使用 OpenAI 的 Chat API 来完成对话功能。
+OpenAI 是一家专注于生成式 AI 的科技公司，提供强大的对话功能。目前 ComfyUI 已集成 OpenAI API，你可以直接在 ComfyUI 中使用相关节点来完成对话功能。
 
 本篇指南中，我们将引导你完成对应对话功能。
 
diff --git a/zh-CN/tutorials/api-nodes/rodin/model-generation.mdx b/zh-CN/tutorials/api-nodes/rodin/model-generation.mdx
@@ -6,9 +6,13 @@ sidebarTitle: "模型生成"
 
 import ReqHint from "/snippets/zh/tutorials/api-nodes/req-hint.mdx";
 
+Hyper3D Rodin (hyper3d.ai) 是一个专注于通过人工智能快速生成高质量、可直接用于生产环境的3D模型和材质的平台。
+目前 ComfyUI 已原生集成了对应 Rodin 模型生成 API ，现在你可以在 ComfyUI 中便捷地使用相关节点来进行模型生成
+
 目前 ComfyUI 的 API 节点中已经支持 Rodin 以下模型生成能力：
 - 单视角模型生成
 - 多视角模型生成
+- 多种不同精度的模型生成
 
 <ReqHint/>
 
@@ -75,3 +79,9 @@ style={{ display: 'inline-block', backgroundColor: '#0078D6', color: '#ffffff',
 2. 点击 `Run` 按钮，或者使用快捷键 `Ctrl(cmd) + Enter(回车)` 来执行模型的生成，工作流完成后对应的模型会自动保存至 `ComfyUI/output/Rodin` 目录下
 3. 在 `Preview 3D` 节点中点击展开菜单
 4. 选择`Export` 可以直接将对应模型导出
+
+## 其它相关节点
+
+目前在 ComfyUI 中， Rodin 提供了不同类型的模型生成节点，由于对应输入条件与本文介绍的工作流相同，你可以按需启用，另外在对应模板中，我们提供了对应的节点，你也可以按需修改对应节点模式来启用
+
+![Rodin 其它相关节点](/images/tutorial/api_nodes/rodin/other_nodes.jpg)
diff --git a/zh-CN/tutorials/api-nodes/runway/image-generation.mdx b/zh-CN/tutorials/api-nodes/runway/image-generation.mdx
@@ -6,9 +6,11 @@ sidebarTitle: "Runway Image Generation"
 
 import ReqHint from "/snippets/zh/tutorials/api-nodes/req-hint.mdx";
 
-节点允许你使用 Runway 的图像生成模型，通过文本提示词或参考图像创建高质量、细节丰富的图像内容。
+Runway 是一家专注于生成式AI的科技公司，提供强大的图像生成功能。其模型支持风格迁移、图像扩展和细节控制等特性。目前 ComfyUI 已集成 Runway API，你可以直接在 ComfyUI 中使用相关节点进行图像生成。
 
-本篇指南中，我们将引导你完成对应文生图和参考生图的工作流设置。
+本篇指南中，我们将引导你完成下面的工作流:
+- 文生图
+- 参考生图
 
 <ReqHint/>
 
diff --git a/zh-CN/tutorials/api-nodes/runway/video-generation.mdx b/zh-CN/tutorials/api-nodes/runway/video-generation.mdx
@@ -6,6 +6,8 @@ sidebarTitle: "Runway Video Generation"
 
 import ReqHint from "/snippets/zh/tutorials/api-nodes/req-hint.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
 - Runway Gen4 turbo
diff --git a/zh-CN/tutorials/api-nodes/tripo/model-generation.mdx b/zh-CN/tutorials/api-nodes/tripo/model-generation.mdx
@@ -6,6 +6,9 @@ sidebarTitle: "模型生成"
 
 import ReqHint from "/snippets/zh/tutorials/api-nodes/req-hint.mdx";
 
+Tripo AI 是一家专注于生成式 AI 3D 建模的公司，它提供用户友好的平台和 API 服务，能够快速地将文本提示或2D图像（单张或多张）转换成高质量的3D模型。
+目前 ComfyUI 已原生集成了对应 Tripo API ,现在你可以在 ComfyUI 中便捷地使用相关节点来进行模型生成
+
 目前 ComfyUI 的 API 节点中已经支持 Tripo 以下模型生成能力：
 - 文生模型
 - 图生模型
@@ -95,3 +98,14 @@ import ReqHint from "/snippets/zh/tutorials/api-nodes/req-hint.mdx";
 3. 点击 `Run` 按钮，或者使用快捷键 `Ctrl(cmd) + Enter(回车)` 来执行模型的生成，工作流完成后对应的模型会自动保存至 `ComfyUI/output/` 目录下
 4. 其它视图输入可以参考步骤图中的示意将对应节点的模式设置为 `总是（always）` 来启用
 5. 模型下载请参考文生图部分的说明
+
+
+##  对应任务的后续任务处理
+
+Tripo 的对应节点提供了对于同一任务的后续处理，只需要在相关节点中输入对应的`model_task_id` 即可,我们在相关模板中也已提供了对应的节点，你也可以按需通过修改对应节点模式来启用
+
+![Tripo 任务处理](/images/tutorial/api_nodes/tripo/other_nodes.jpg)
+
+<Error>
+    其中 `Tripo: Refine Draft model` 节点只对 V1.4 模型支持，其它模型不支持
+</Error>
diff --git a/zh-CN/tutorials/video/wan/vace.mdx b/zh-CN/tutorials/video/wan/vace.mdx
@@ -212,15 +212,13 @@ VACE 还支持在一张图像中输入多个参考图像，来生成对应的视
 
 [待更新]
 
-- Portable 版本模板已更新，请参照中的模板说明
-- Desktop 版本目前尚未更新
-
 ## VACE 首尾帧视频生成
 
 [待更新]
 
-- Portable 版本中模板已更新，请参照模板说明
-- Desktop 版本目前尚未更新
+要保证首尾帧生效，需要满足：
+- 对应视频 `lenght` 设置需要满足 `lenght-1` 后能够被 `4` 整除
+- 对应的 `Batch_size` 设置需要满足 `Batch_size = lenght - 2`
 
 ## 相关节点文档
 
