Comfy-Org · coderfromthenorth93 · Jul 9, 2025 · Jul 9, 2025
diff --git a/changelog/index.mdx b/changelog/index.mdx
@@ -4,6 +4,35 @@ description: "Track ComfyUI's latest features, improvements, and bug fixes"
 icon: "clock-rotate-left"
 ---
 
+<Update label="v0.3.37" description="July 9, 2025">
+
+**Error Handling & Hardware Compatibility Improvements**
+
+This release focuses on enhanced error detection and platform-specific optimizations to improve workflow reliability:
+
+## Enhanced Error Detection
+- **Diffusion Model Validation**: Added proper error reporting when diffusion models aren't detected correctly, helping users quickly identify and resolve model loading issues in their workflows
+- **Better Debugging**: Clearer error messages make it easier to troubleshoot model compatibility problems during workflow development
+
+## AMD GPU Optimizations
+- **GFX1151 Support**: Enabled PyTorch attention by default on AMD GFX1151 GPUs, providing better performance for users with this hardware configuration
+- **Improved AMD Performance**: Enhanced attention mechanisms deliver faster inference times for AMD users working with complex generation workflows
+
+## Memory Management Enhancements
+- **NoVRAM Mode Fix**: Disabled initial GPU load when using `--novram` flag, preventing unnecessary memory allocation and improving system stability for low-VRAM setups
+- **Resource Optimization**: Better memory handling for users running ComfyUI on resource-constrained systems
+
+## Frontend Updates
+- **UI Stability**: Updated frontend to version 1.20.6 with bug fixes that improve overall user interface reliability and workflow editor performance
+
+## New API Integration Nodes
+- **Expanded API Support**: Added new nodes for Gemini/OpenAI Chat, Tripo, Rodin, and Runway Image APIs, enabling seamless integration with popular AI services directly within ComfyUI workflows
+- **Enhanced Connectivity**: These API nodes allow creators to combine ComfyUI's powerful workflow system with external AI services for more comprehensive generation pipelines
+
+These improvements strengthen ComfyUI's foundation for reliable workflow execution while expanding integration possibilities with external AI services and optimizing performance across different hardware configurations.
+
+</Update>
+
 <Update label="v0.3.44" description="July 8, 2025">
 
 **Advanced Sampling & Model Control Enhancements**
@@ -93,7 +122,6 @@ These changes enhance the reliability of advanced model workflows while maintain
 
 This release significantly expands ComfyUI's model ecosystem support while delivering crucial stability improvements and enhanced hardware compatibility across different platforms.
 </Update>
-
 <Update label="v0.3.40" description="June 5, 2025">
 
 This release brings powerful new workflow utilities and performance optimizations for ComfyUI creators:

diff --git a/zh-CN/changelog/index.mdx b/zh-CN/changelog/index.mdx
@@ -1,9 +1,37 @@
 ---
 title: "更新日志"
-description: "跟踪ComfyUI的最新功能、改进和错误修复"
+description: "跟踪ComfyUI的最新功能、改进和bug修复"
 icon: "clock-rotate-left"
 ---
 
+<Update label="v0.3.37" description="2025年7月9日">
+
+**错误处理与硬件兼容性改进**
+
+本次发布专注于增强错误检测和平台特定优化，以提高工作流可靠性：
+
+## 增强的错误检测
+- **扩散模型验证**：当扩散模型未正确检测时，增加了适当的错误报告，帮助用户快速识别和解决工作流中的模型加载问题
+- **更好的调试体验**：更清晰的错误信息使得在工作流开发过程中更容易排除模型兼容性问题
+
+## AMD GPU优化
+- **GFX1151支持**：在AMD GFX1151 GPU上默认启用PyTorch注意力机制，为使用此硬件配置的用户提供更好的性能
+- **改进的AMD性能**：增强的注意力机制为使用复杂生成工作流的AMD用户提供更快的推理时间
+
+## 内存管理增强
+- **NoVRAM模式修复**：使用`--novram`标志时禁用初始GPU加载，防止不必要的内存分配，提高低显存设置的系统稳定性
+- **资源优化**：为在资源受限系统上运行ComfyUI的用户提供更好的内存处理
+
+## 前端更新
+- **UI稳定性**：前端更新至1.20.6版本，修复了bug，提高了整体用户界面可靠性和工作流编辑器性能
+
+## 新的API集成节点
+- **扩展的API支持**：新增了Gemini/OpenAI Chat、Tripo、Rodin和Runway Image API节点，实现了在ComfyUI工作流中与热门AI服务的无缝集成
+- **增强的连接性**：这些API节点允许创作者将ComfyUI强大的工作流系统与外部AI服务结合，构建更全面的生成管道
+
+这些改进加强了ComfyUI可靠工作流执行的基础，同时扩展了与外部AI服务的集成可能性，并优化了不同硬件配置下的性能。
+
+</Update>
 <Update label="v0.3.44" description="2025年7月8日">
 
 **高级采样和模型控制增强**