Comfy-Org · comfyui-wiki · Jan 7, 2026 · Jan 7, 2026 · Jan 7, 2026 · Jan 7, 2026
diff --git a/changelog/index.mdx b/changelog/index.mdx
@@ -4,6 +4,37 @@ description: "Track ComfyUI's latest features, improvements, and bug fixes. For
 icon: "clock-rotate-left"
 ---
 
+
+<Update label="v0.8.0" description="January 7, 2026">
+
+**New Model Support & Features**
+- Support for LTXV 2 model with dedicated LTXAVTextEncoderLoader node for enhanced text encoding capabilities
+- Initial NVFP4 checkpoint support with fp4 matrix multiplication optimizations
+- Sage Attention 3 support available via CLI argument for improved attention mechanisms
+
+**API & Developer Experience**
+- V3 API improvements with DynamicCombo and Autogrow functionality exposed in the public API
+- Enhanced API nodes including 720p resolution support for Kling Omni nodes and WAN2.6 ReferenceToVideo
+- Improved Tripo3D integration with optimized face_limit parameter handling
+- Fixed percent-encoding preservation for signed URLs in API nodes
+
+**Performance & Memory Management**
+- Better memory debugging with OOM memory summary printing to help troubleshoot workflow issues
+- Fixed upscale model CPU offloading to improve memory efficiency
+- Resolved lowvram compatibility issues with LTXV2 text encoder
+- Enhanced CUDA compatibility with conditional comfy kitchen CUDA support based on PyTorch version
+
+**Workflow & Node Improvements**
+- Updated workflow templates to v0.7.67 with latest node configurations
+- Improved Mahiro CFG with more appropriate display naming
+- MPO format image loading now properly handles multi-frame files by using only the first frame
+- Fixed fp8 processing issues for better model compatibility
+
+**Code Quality & Maintenance**
+- Comprehensive code cleanup and refactoring including CLIP preprocessing improvements
+- Integration with comfy-kitchen library for enhanced mathematical operations
+- Removed duplicate imports and cleaned up legacy code for better performance
+</Update>
 <Update label="v0.7.0" description="December 31, 2025">
 
 **New Nodes & Workflow Tools**
@@ -35,6 +66,7 @@ icon: "clock-rotate-left"
 - Optimized Lumina/Z image model performance by removing unused components
 - Better error handling for async operations and memory management
 
+
 </Update>
 
 <Update label="v0.6.0" description="December 24, 2025">

diff --git a/zh-CN/changelog/index.mdx b/zh-CN/changelog/index.mdx
@@ -1,9 +1,40 @@
 ---
 title: "更新日志"
-description: "跟踪 ComfyUI 的最新功能、改进和错误修复。详细发布说明请查看 [Github releases](https://github.com/comfyanonymous/ComfyUI/releases) 页面。"
+description: "追踪 ComfyUI 的最新功能、改进和错误修复。详细发布说明请查看 [Github 发布页面](https://github.com/comfyanonymous/ComfyUI/releases)。"
 icon: "clock-rotate-left"
 ---
 
+<Update label="v0.8.0" description="2026年1月7日">
+
+**新模型支持与功能**
+- 支持 LTXV 2 模型，配备专用的 LTXAVTextEncoderLoader 节点，增强文本编码能力
+- 初步支持 NVFP4 检查点，具备 fp4 矩阵乘法优化
+- 通过 CLI 参数提供 Sage Attention 3 支持，改进注意力机制
+
+**API 与开发者体验**
+- V3 API 改进，在公共 API 中公开了 DynamicCombo 和 Autogrow 功能
+- 增强的 API 节点，包括对 Kling Omni 节点的 720p 分辨率支持和 WAN2.6 ReferenceToVideo
+- 改进了 Tripo3D 集成，优化了 face_limit 参数处理
+- 修复了 API 节点中签名 URL 的百分号编码保留问题
+
+**性能与内存管理**
+- 改进内存调试功能，OOM 内存摘要打印有助于排查工作流问题
+- 修复了放大模型 CPU 卸载功能，提高内存效率
+- 解决了 LTXV2 文本编码器的 lowvram 兼容性问题
+- 增强了 CUDA 兼容性，基于 PyTorch 版本提供条件性 comfy kitchen CUDA 支持
+
+**工作流与节点改进**
+- 将工作流模板更新至 v0.7.67，采用最新节点配置
+- 改进了 Mahiro CFG，提供更合适的显示命名
+- MPO 格式图像加载现在通过仅使用第一帧正确处理多帧文件
+- 修复了 fp8 处理问题，提高模型兼容性
+
+**代码质量与维护**
+- 全面的代码清理和重构，包括 CLIP 预处理改进
+- 与 comfy-kitchen 库集成，增强数学运算功能
+- 移除重复导入并清理遗留代码，提升性能
+</Update>
+
 <Update label="v0.7.0" description="2025年12月31日">
 
 **新节点和工作流工具**