Refine changelog content for accuracy and clarity

- Update v0.3.55 to focus specifically on Wan2.2 S2V features
- Simplify model descriptions to reflect actual functionality
- Remove redundant marketing language
- Clarify technical details for better user understanding
- Streamline template and API descriptions
- Apply same improvements to both English and Chinese versions

Author: comfyui-wiki

changelog/index.mdx

@@ -6,26 +6,25 @@ icon: "clock-rotate-left"
 
 <Update label="v0.3.55" description="August 29, 2025">
 
-**Sound-to-Video Workflow Enhancements & Model Support Expansion**
+**Wan2.2 S2V Workflow Enhancements & Model Support Expansion**
 
-This release focuses on improving audio-visual workflow capabilities and expanding model support, particularly for sound-to-video generation and the latest Wan2.2 5B models:
+This release focuses on Wan2.2 S2V related video workflow capabilities and model support expansion:
 
-**Sound-to-Video Workflow Control**
-- **WanSoundImageToVideoExtend Node**: New manual video extension node for sound-to-video workflows, giving creators precise control over generated video length and timing. This enables fine-tuned control over how audio content translates to video sequences.
+**Wan2.2 S2V Workflow Control**
+- **WanSoundImageToVideoExtend Node**: New manual video extension node for audio-driven video workflows, giving creators precise control over generated video length and timing. This enables fine-tuned control over how audio content translates to video sequences.
 - **Audio-Video Synchronization**: Fixed critical issue where extending video past audio length caused workflow failures, ensuring reliable sound-to-video generation regardless of audio duration.
 - **Automatic Audio Trimming**: Video saves now automatically trim audio to match video length, eliminating audio-video sync issues in final output files.
 
 **Advanced Latent Processing**
-- **LatentCut Node**: New node for cutting latents at precise points, enabling more granular control over latent space manipulation in complex generation workflows. This is particularly useful for batch processing and temporal video workflows.
+- **LatentCut Node**: New node for cutting latents at precise points, enabling more granular control over latent space manipulation in complex generation workflows. This is particularly useful for batch processing and temporal video workflows, such as removing specific frames from videos.
 
 **Wan2.2 5B Model Integration**
-- **Fun Control Model Support**: Added support for Wan2.2 5B fun control model, expanding creative control options for video generation with enhanced parameter manipulation.
-- **Fun Inpaint Model Support**: Integrated Wan2.2 5B fun inpaint model, providing advanced inpainting capabilities for video workflows with improved quality and consistency.
+- **Fun Control Model Support**: Added support for Wan2.2 5B fun control model.
+- **Fun Inpaint Model Support**: Integrated Wan2.2 5B fun inpaint model.
 
-**Template System Updates**
-- **Template v0.1.70**: Updated template system with latest model integrations and workflow examples, ensuring users have access to optimized setups for new features.
+**Workflow Templates**
+- **Template v0.1.70**: Added initial version of Wan2.2 S2V workflows
 
-These improvements enhance ComfyUI's capabilities for audio-visual content creation, providing more reliable sound-to-video workflows and additional creative control through the latest Wan2.2 model series.
 
 </Update>
 
@@ -36,11 +35,10 @@ These improvements enhance ComfyUI's capabilities for audio-visual content creat
 This focused update improves the core node model patching system that underpins ComfyUI's flexible architecture:
 
 **Core Infrastructure Enhancement**
-- **Node Model Patch Updates**: Enhanced nodes_model_patch.py with improvements to the underlying model patching mechanism that enables ComfyUI's dynamic node system and model loading capabilities
+- **Node Model Patch Updates**: Enhanced nodes_model_patch.py with improvements to the underlying model patching mechanism, making ComfyUI extensions for Qwen-Image ControlNet easier
 
 **Workflow Benefits**
 - **Enhanced Stability**: Core model patching improvements contribute to more reliable node execution and model handling across different workflow configurations
-- **Foundation Update**: These backend improvements lay groundwork for better compatibility with future model architectures and node implementations
 
 </Update>
 
@@ -52,11 +50,11 @@ This release adds ComfyUI audio processing capabilities and includes performance
 
 **Audio Processing Updates**
 - **Wav2vec2 Audio Encoder**: Added native wav2vec2 implementation as an audio encoder model, enabling audio-to-embedding workflows for multimodal applications
-- **Audio Encoders Directory**: Introduced dedicated models/audio_encoders directory structure for organized audio model management
+- **Audio Encoders Directory**: Added models/audio_encoders directory, which is the audio encoder directory for Wan2.2 S2V
 - **AudioEncoderOutput V3 Support**: Made AudioEncoderOutput compatible with V3 node schema, ensuring seamless integration with modern workflow architectures
 
 **Google Gemini API Integration**
-- **Gemini Image API Node**: New Google Gemini Image API node by @Kosinkadink provides direct integration with Google's vision AI capabilities, expanding cloud-based image analysis options for workflows
+- **Gemini Image API Node**: Added new Google Gemini Image API node, the "nano-Nano-banana" image editing model API with high consistency
 
 **Video Generation Performance & Memory Optimizations**
 - **WAN 2.2 S2V Model Support**: Work-in-progress implementation of WAN 2.2 Sound-to-Video model with optimized memory usage and performance
@@ -74,10 +72,9 @@ This release adds ComfyUI audio processing capabilities and includes performance
 - **Flux Memory Optimization**: Adjusted Flux model memory usage factors for better resource utilization
 
 **Infrastructure & Reliability**
-- **Template Updates**: Updated to versions 0.1.66 and 0.1.68 with latest workflow templates and improvements
+- **Template Updates**: Updated to versions 0.1.66 and 0.1.68
 - **Documentation Cleanup**: Removed incompletely implemented models from readme to avoid user confusion
 
-This release particularly benefits creators working with multimodal AI workflows combining audio, image, and video generation, while providing essential stability improvements for all users.
 
 </Update>
 

zh-CN/changelog/index.mdx

@@ -6,26 +6,24 @@ icon: "clock-rotate-left"
 
 <Update label="v0.3.55" description="2025年8月29日">
 
-**音频转视频工作流增强与模型支持扩展**
+**Wan2.2 S2V 工作流增强与模型支持扩展**
 
-本次发布专注于改进音视频工作流功能并扩展模型支持，特别是针对音频转视频生成和最新的Wan2.2 5B模型：
+本次发布专注于 Wan2.2 S2V 的相关视频工作流功能并扩展模型支持：
 
-**音频转视频工作流控制**
-- **WanSoundImageToVideoExtend节点**：全新的音频转视频工作流手动视频扩展节点，为创作者提供对生成视频长度和时间的精确控制。这使得对音频内容如何转换为视频序列的精细调控成为可能。
+**Wan2.2 S2V工作流控制**
+- **WanSoundImageToVideoExtend节点**：全新的音频驱动视频工作流手动视频扩展节点，为创作者提供对生成视频长度和时间的精确控制。这使得对音频内容如何转换为视频序列的精细调控成为可能。
 - **音视频同步**：修复了当视频扩展超过音频长度时导致工作流失败的关键问题，确保无论音频持续时间如何都能可靠地生成音频转视频内容。
 - **自动音频裁剪**：视频保存现在会自动将音频裁剪至匹配视频长度，消除最终输出文件中的音视频同步问题。
 
 **高级潜在空间处理**
-- **LatentCut节点**：用于在精确点位切割潜在变量的新节点，在复杂生成工作流中实现对潜在空间操作的更精细控制。这对于批处理和时序视频工作流特别有用。
+- **LatentCut节点**：用于在精确点位切割潜在变量的新节点，在复杂生成工作流中实现对潜在空间操作的更精细控制。这对于批处理和时序视频工作流特别有用，比如删除视频中的某些帧。
 
 **Wan2.2 5B模型集成**
-- **Fun Control模型支持**：增加了对Wan2.2 5B fun control模型的支持，通过增强的参数操作为视频生成扩展了创意控制选项。
-- **Fun Inpaint模型支持**：集成了Wan2.2 5B fun inpaint模型，为视频工作流提供高级修复功能，具有更好的质量和一致性。
+- **Fun Control模型支持**：增加了对Wan2.2 5B fun control模型的支持，。
+- **Fun Inpaint模型支持**：集成了Wan2.2 5B fun inpaint模型。
 
-**模板系统更新**
-- **模板v0.1.70**：更新了模板系统，集成了最新的模型和工作流示例，确保用户能够访问针对新功能优化的设置。
-
-这些改进增强了ComfyUI在音视频内容创作方面的能力，通过最新的Wan2.2模型系列提供了更可靠的音频转视频工作流和额外的创意控制。
+**工作流模板**
+- **模板v0.1.70**：添加了 Wan2.2 S2V 初步版本的工作流
 
 </Update>
 
@@ -36,11 +34,10 @@ icon: "clock-rotate-left"
 此次专项更新改进了支撑 ComfyUI 灵活架构的核心节点模型补丁系统：
 
 **核心基础设施增强**
-- **节点模型补丁更新**：增强了 nodes_model_patch.py，改进了底层模型补丁机制，该机制支持 ComfyUI 的动态节点系统和模型加载功能
+- **节点模型补丁更新**：增强了 nodes_model_patch.py，改进了底层模型补丁机制，使得 ComfyUI 对 Qwen-Image ControlNet 的扩展更为容易
 
 **工作流程优势**
 - **增强的稳定性**：核心模型补丁改进有助于在不同工作流程配置中实现更可靠的节点执行和模型处理
-- **基础更新**：这些后端改进为未来模型架构和节点实现的更好兼容性奠定了基础
 
 </Update>
 
@@ -52,11 +49,11 @@ icon: "clock-rotate-left"
 
 **音频处理更新**
 - **Wav2vec2 音频编码器**：新增原生 wav2vec2 实现作为音频编码器模型，为多模态应用启用音频到嵌入工作流
-- **音频编码器目录**：引入专用的 models/audio_encoders 目录结构，用于有序的音频模型管理
+- **音频编码器目录**：新增 models/audio_encoders 目录，此为 Wan2.2 S2V 音频编码器目录
 - **AudioEncoderOutput V3 支持**：使 AudioEncoderOutput 与 V3 节点架构兼容，确保与现代工作流架构的无缝集成
 
 **Google Gemini API 集成**
-- **Gemini Image API 节点**：@Kosinkadink 提供的全新 Google Gemini Image API 节点，可直接集成 Google 的视觉 AI 功能，为工作流扩展基于云的图像分析选项
+- **Gemini Image API 节点**： 新增全新 Google Gemini Image API 节点，即 “nano-Nano-banana” 图像编辑模型 API，具有高度的一致性
 
 **视频生成性能与内存优化**
 - **WAN 2.2 S2V 模型支持**：正在开发的 WAN 2.2 声音到视频模型实现，具有优化的内存使用和性能
@@ -74,11 +71,9 @@ icon: "clock-rotate-left"
 - **Flux 内存优化**：调整 Flux 模型内存使用因子以获得更好的资源利用
 
 **基础设施与可靠性**
-- **模板更新**：更新至 0.1.66 和 0.1.68 版本，包含最新的工作流模板和改进
+- **模板更新**：更新至 0.1.66 和 0.1.68 版本
 - **文档清理**：从自述文件中移除未完全实现的模型，以避免用户混淆
 
-此版本特别有利于从事结合音频、图像和视频生成的多模态 AI 工作流的创作者，同时为所有用户提供基本的稳定性改进。
-
 </Update>
 <Update label="v0.3.52" description="2025年8月23日">