diff --git a/changelog/index.mdx b/changelog/index.mdx index f2b612fd..ee095cd0 100644 --- a/changelog/index.mdx +++ b/changelog/index.mdx @@ -4,73 +4,104 @@ description: "Track ComfyUI's latest features, improvements, and bug fixes" icon: "clock-rotate-left" --- + + +**Model Integration & Performance Enhancements** + +This release expands ComfyUI's model ecosystem with enhanced Qwen support, async API capabilities, and stability improvements for complex workflows: + +**Qwen Model Ecosystem** +- **Qwen Image Model Support**: Improved integration including proper LoRA loading and model merging capabilities for sophisticated vision workflows +- **Qwen Model Merging Node**: New dedicated node for merging Qwen image models, allowing creators to combine different model strengths +- **SimpleTuner Lycoris LoRA Support**: Extended compatibility with SimpleTuner-trained Lycoris LoRAs for Qwen-Image models + +**API & Performance Infrastructure** +- **Async API Nodes**: Introduction of asynchronous API nodes, enabling non-blocking workflow execution for better performance +- **Memory Handling**: Enhanced RepeatLatentBatch node now properly handles multi-dimensional latents, fixing workflow interruptions +- **WAN 2.2 Fun Control Support**: Added support for WAN 2.2 fun control features, expanding creative control for video workflows + +**Hardware Optimization & Compatibility** +- **AMD GPU Improvements**: Enhanced AMD Radeon support with improved FP16 accuracy handling and performance optimization +- **RDNA3 Architecture Fixes**: Resolved issues with gfx1201 GPUs when using Flux models with PyTorch attention +- **Updated PyTorch Support**: Bumped CUDA and ROCM PyTorch versions with testing on Python 3.13 and CUDA 12.9 + +**Developer Experience Enhancements** +- **Cleaner Logging**: Feature flags now only display in verbose mode, reducing console noise +- **Audio Processing Safety**: Enhanced torchaudio import safety checks prevent crashes when audio dependencies are unavailable +- **Kling API Improvements**: Fixed image type parameter handling in Kling Image API nodes + +**Workflow Benefits** +- **Async Workflow Execution**: New async API capabilities enable more responsive workflows when integrating external services +- **Model Flexibility**: Expanded Qwen support allows for more diverse vision-language workflows with improved LoRA compatibility +- **Hardware Utilization**: AMD GPU optimizations and updated PyTorch support improve performance across hardware configurations +- **Batch Processing**: Fixed RepeatLatentBatch ensures reliable operation with complex multi-dimensional data structures +- **Video Control**: WAN 2.2 fun control features provide advanced creative control for video generation workflows + + + -**Enhanced UI Experience & Advanced Model Support** +**UI Experience & Model Support** -This release brings significant user experience improvements and cutting-edge model support that enhance workflow creation and performance across diverse AI applications: +This release brings user experience improvements and model support that enhance workflow creation and performance: -### User Interface Enhancements -- **Recently Used Items API**: New API for tracking recently used items in the interface, streamlining workflow creation by providing quick access to frequently used nodes and components -- **Improved Workflow Navigation**: Enhanced user experience with better organization of commonly accessed elements, reducing time spent searching for nodes +**User Interface Enhancements** +- **Recently Used Items API**: New API for tracking recently used items in the interface, streamlining workflow creation +- **Workflow Navigation**: Enhanced user experience with better organization of commonly accessed elements -### Advanced Model Integration -- **Qwen Vision Model Support**: Initial support for Qwen image models with comprehensive configuration options including default shift settings and flexible latent size handling -- **Optimized Image Processing**: Enhanced Qwen model integration allows for more versatile image analysis and generation workflows, expanding AI capabilities for vision tasks +**Model Integration** +- **Qwen Vision Model Support**: Initial support for Qwen image models with configuration options +- **Image Processing**: Enhanced Qwen model integration allows for more versatile image analysis and generation workflows -### Revolutionary Video Generation -- **Veo3 Video Generation**: Added powerful Veo3 video generation node with integrated audio support, enabling creators to produce high-quality video content with synchronized audio directly in ComfyUI workflows -- **Audio-Visual Synthesis**: Breakthrough capability combining video and audio generation in a single node, perfect for content creators and multimedia professionals +**Video Generation** +- **Veo3 Video Generation**: Added Veo3 video generation node with integrated audio support +- **Audio-Visual Synthesis**: Capability combining video and audio generation in a single node -### Performance & Stability Improvements -- **Enhanced Memory Management**: Optimized conditional (cond) VRAM usage through improved casting and device transfer operations, reducing memory overhead during complex generation tasks -- **Device Consistency**: Comprehensive fixes ensuring all conditioning data and context remain on correct devices, preventing crashes and improving workflow reliability -- **ControlNet Stability**: Resolved critical ControlNet compatibility issues, restoring full functionality for precise image control workflows +**Performance & Stability Improvements** +- **Memory Management**: Optimized conditional VRAM usage through improved casting and device transfer operations +- **Device Consistency**: Fixes ensuring all conditioning data and context remain on correct devices +- **ControlNet Stability**: Resolved ControlNet compatibility issues, restoring functionality for image control workflows -### Developer & System Enhancements -- **Robust Error Handling**: Added intelligent warnings and crash prevention when conditioning devices don't match, improving workflow debugging and stability -- **Template Updates**: Multiple template version updates (0.1.47, 0.1.48, 0.1.51) maintaining compatibility with latest development standards and ensuring smooth node integration +**Developer & System Enhancements** +- **Error Handling**: Added warnings and crash prevention when conditioning devices don't match +- **Template Updates**: Multiple template version updates (0.1.47, 0.1.48, 0.1.51) maintaining compatibility -### Workflow Benefits +**Workflow Benefits** - **Faster Iteration**: Recently used items API enables quicker workflow assembly and modification - **Enhanced Creativity**: Qwen vision models open new possibilities for image understanding and manipulation workflows -- **Professional Video Production**: Veo3 integration transforms ComfyUI into a comprehensive multimedia creation platform -- **Improved Reliability**: Memory optimizations and device management fixes ensure stable operation with complex, multi-model workflows -- **Better Performance**: Optimized VRAM usage allows for more ambitious projects on systems with limited resources - -This release significantly expands ComfyUI's capabilities, particularly for multimedia creators and professionals working with advanced vision models, while improving the overall user experience through better interface organization and enhanced system stability. +- **Video Production**: Veo3 integration transforms ComfyUI into a comprehensive multimedia creation platform +- **Reliability**: Memory optimizations and device management fixes ensure stable operation with complex workflows +- **Performance**: Optimized VRAM usage allows for more ambitious projects on systems with limited resources -**Core API Enhancement & Performance Optimizations** - -This release introduces significant backend improvements and performance optimizations that enhance workflow execution and node development capabilities: +**API Enhancement & Performance Optimizations** -### ComfyAPI Core Framework -- **ComfyAPI Core v0.0.2**: Major update to the core API framework, providing improved stability and extensibility for custom node development and third-party integrations -- **Partial Execution Support**: New backend support for partial workflow execution, enabling more efficient processing of complex multi-stage workflows by allowing selective node execution +This release introduces backend improvements and performance optimizations that enhance workflow execution and node development: -### Video Processing Improvements -- **WAN Camera Memory Optimization**: Enhanced memory management for WAN-based camera workflows, reducing VRAM usage during video processing operations -- **WanFirstLastFrameToVideo Fix**: Resolved critical issue preventing proper video generation when clip vision components are not available, improving workflow reliability +**ComfyAPI Core Framework** +- **ComfyAPI Core v0.0.2**: Update to the core API framework, providing improved stability and extensibility +- **Partial Execution Support**: New backend support for partial workflow execution, enabling efficient processing of multi-stage workflows -### Performance & Model Optimizations -- **VAE Nonlinearity Enhancement**: Replaced manual activation functions with optimized torch.silu in VAE operations, providing better performance and numerical stability for image encoding/decoding -- **WAN VAE Optimizations**: Additional fine-tuning optimizations for WAN VAE operations, improving processing speed and memory efficiency in video generation workflows +**Video Processing Improvements** +- **WAN Camera Memory Optimization**: Enhanced memory management for WAN-based camera workflows, reducing VRAM usage +- **WanFirstLastFrameToVideo Fix**: Resolved issue preventing proper video generation when clip vision components are not available -### Node Schema Evolution -- **V3 Node Schema Definition**: Initial implementation of next-generation node schema system, laying the groundwork for enhanced node type definitions and improved workflow validation -- **Template Updates**: Multiple template version updates (0.1.44, 0.1.45) ensuring compatibility with latest node development standards and best practices +**Performance & Model Optimizations** +- **VAE Nonlinearity Enhancement**: Replaced manual activation functions with optimized torch.silu in VAE operations +- **WAN VAE Optimizations**: Fine-tuning optimizations for WAN VAE operations, improving processing speed and memory efficiency -### Workflow Development Benefits -- **Enhanced Video Workflows**: Improved stability and performance for video generation pipelines, particularly those using WAN-based models -- **Better Memory Management**: Optimized memory usage patterns enable more complex workflows on systems with limited VRAM -- **Improved API Reliability**: Core API enhancements provide more stable foundation for custom node development and workflow automation -- **Partial Execution Flexibility**: New partial execution capabilities allow for more efficient debugging and iterative workflow development +**Node Schema Evolution** +- **V3 Node Schema Definition**: Implementation of next-generation node schema system +- **Template Updates**: Multiple template version updates (0.1.44, 0.1.45) ensuring compatibility -These foundational improvements strengthen ComfyUI's core architecture while delivering immediate benefits for video processing workflows and memory-intensive operations, making the platform more robust for both casual creators and professional AI development workflows. +**Workflow Development Benefits** +- **Video Workflows**: Improved stability and performance for video generation pipelines +- **Memory Management**: Optimized memory usage patterns enable more complex workflows on systems with limited VRAM +- **API Reliability**: Core API enhancements provide more stable foundation for custom node development +- **Execution Flexibility**: New partial execution capabilities allow for more efficient debugging and development @@ -78,227 +109,220 @@ These foundational improvements strengthen ComfyUI's core architecture while del **Memory Optimization & Large Model Performance** -This release focuses on critical memory optimizations for large model workflows, particularly improving performance with WAN 2.2 models and enhancing VRAM management for high-end systems: +This release focuses on memory optimizations for large model workflows, improving performance with WAN 2.2 models and VRAM management: -### WAN 2.2 Model Optimizations -- **Reduced Memory Footprint**: Eliminated unnecessary memory clones in WAN 2.2 VAE operations, significantly reducing memory usage during image encoding/decoding workflows -- **5B I2V Model Support**: Major memory optimization for WAN 2.2 5B image-to-video models, making these large-scale models more accessible for creators with limited VRAM +**WAN 2.2 Model Optimizations** +- **Reduced Memory Footprint**: Eliminated unnecessary memory clones in WAN 2.2 VAE operations, reducing memory usage +- **5B I2V Model Support**: Memory optimization for WAN 2.2 5B image-to-video models, making these models more accessible -### Enhanced VRAM Management -- **Windows Large Card Support**: Added extra reserved VRAM allocation for high-end graphics cards on Windows, preventing system instability during intensive generation workflows -- **Better Memory Allocation**: Improved memory management for users working with multiple large models simultaneously +**Enhanced VRAM Management** +- **Windows Large Card Support**: Added reserved VRAM allocation for high-end graphics cards on Windows +- **Memory Allocation**: Improved memory management for users working with multiple large models simultaneously -### Workflow Performance Benefits -- **Faster VAE Processing**: WAN 2.2 VAE operations now run more efficiently with reduced memory overhead, enabling smoother image generation pipelines -- **Stable Large Model Inference**: Enhanced stability when working with billion-parameter models, crucial for professional AI art creation and research workflows -- **Improved Batch Processing**: Memory optimizations enable better handling of batch operations with large models - -These targeted optimizations make ComfyUI more reliable for professional workflows involving large-scale models, particularly benefiting creators working with cutting-edge image-to-video generation and high-resolution image processing tasks. +**Workflow Performance Benefits** +- **VAE Processing**: WAN 2.2 VAE operations now run more efficiently with reduced memory overhead +- **Large Model Inference**: Enhanced stability when working with billion-parameter models +- **Batch Processing**: Memory optimizations enable better handling of batch operations with large models -**Hardware Acceleration & Audio Processing Improvements** - -This release focuses on expanding hardware support and enhancing audio processing capabilities for workflow creators: +**Hardware Acceleration & Audio Processing** -### Audio Processing Enhancements -- **PyAV Audio Backend**: Replaced torchaudio.load with PyAV for more reliable audio processing in video workflows, improving compatibility and performance -- **Better Audio Integration**: Enhanced audio handling for multimedia generation workflows, particularly beneficial for video content creators +This release expands hardware support and enhances audio processing capabilities: -### Expanded Hardware Support -- **Iluvatar CoreX Support**: Added native support for Iluvatar CoreX accelerators, expanding hardware options for AI inference -- **Intel XPU Optimization**: Comprehensive XPU support improvements including async offload capabilities and device-specific optimizations -- **AMD ROCm Enhancements**: Enabled PyTorch attention by default for gfx1201 on Torch 2.8, improving performance on AMD hardware -- **CUDA Memory Management**: Fixed CUDA malloc to only activate on CUDA-enabled PyTorch installations, preventing conflicts on other platforms +**Audio Processing Enhancements** +- **PyAV Audio Backend**: Replaced torchaudio.load with PyAV for more reliable audio processing in video workflows +- **Audio Integration**: Enhanced audio handling for multimedia generation workflows -### Sampling Algorithm Improvements -- **Euler CFG++ Enhancement**: Separated denoised and noise estimation processes in Euler CFG++ sampler for improved numerical precision and quality -- **WAN Model Support**: Added comprehensive support for WAN (Wavelet-based Attention Network) models including ATI support and WAN 2.2 compatibility +**Hardware Support** +- **Iluvatar CoreX Support**: Added native support for Iluvatar CoreX accelerators +- **Intel XPU Optimization**: XPU support improvements including async offload capabilities +- **AMD ROCm Enhancements**: Enabled PyTorch attention by default for gfx1201 on Torch 2.8 +- **CUDA Memory Management**: Fixed CUDA malloc to only activate on CUDA-enabled PyTorch installations -### Advanced Training Features -- **Enhanced Training Nodes**: Added algorithm support, gradient accumulation, and optional gradient checkpointing to training workflows -- **Improved Training Flexibility**: Better memory management and performance optimization for custom model training +**Sampling Algorithm Improvements** +- **Euler CFG++ Enhancement**: Separated denoised and noise estimation processes in Euler CFG++ sampler +- **WAN Model Support**: Added support for WAN (Wavelet-based Attention Network) models -### Node & Workflow Enhancements -- **Moonvalley V2V Node**: Added Moonvalley Marey V2V node with enhanced input validation for video-to-video workflows -- **Negative Prompt Updates**: Improved negative prompt handling for Moonvalley nodes, providing better control over generation outputs -- **History API Enhancement**: Added map_function parameter to get_history API for more flexible workflow history management +**Training Features** +- **Training Nodes**: Added algorithm support, gradient accumulation, and optional gradient checkpointing +- **Training Flexibility**: Better memory management and performance optimization for custom model training -### API & System Improvements -- **Frontend Version Tracking**: Added required_frontend_version parameter in /system_stats API response for better version compatibility -- **Device Information**: Enhanced XPU device name printing for better hardware identification and debugging -- **Template Updates**: Multiple template updates (0.1.40, 0.1.41) ensuring compatibility with latest node development standards +**Node & Workflow Enhancements** +- **Moonvalley V2V Node**: Added Moonvalley Marey V2V node with enhanced input validation +- **Negative Prompt Updates**: Improved negative prompt handling for Moonvalley nodes +- **History API Enhancement**: Added map_function parameter to get_history API -### Developer Experience -- **Documentation Updates**: Enhanced README with HiDream E1.1 examples and updated model integration guides -- **Line Ending Fixes**: Improved cross-platform compatibility by standardizing line endings in workflows -- **Code Cleanup**: Removed deprecated code and optimized various components for better maintainability +**API & System Improvements** +- **Frontend Version Tracking**: Added required_frontend_version parameter in /system_stats API response +- **Device Information**: Enhanced XPU device name printing for better hardware identification +- **Template Updates**: Multiple template updates (0.1.40, 0.1.41) ensuring compatibility -These improvements make ComfyUI more accessible across different hardware platforms while enhancing audio processing capabilities essential for modern multimedia AI workflows. +**Developer Experience** +- **Documentation Updates**: Enhanced README with examples and updated model integration guides +- **Line Ending Fixes**: Improved cross-platform compatibility by standardizing line endings +- **Code Cleanup**: Removed deprecated code and optimized components + -**Advanced Sampling & Training Infrastructure Improvements** +**Sampling & Training Improvements** -This release introduces significant enhancements to sampling algorithms, training capabilities, and node functionality for AI researchers and workflow creators: +This release introduces enhancements to sampling algorithms, training capabilities, and node functionality: -### New Sampling & Generation Features -- **SA-Solver Sampler**: New reconstructed SA-Solver sampling algorithm providing enhanced numerical stability and quality for complex generation workflows -- **Experimental CFGNorm Node**: Advanced classifier-free guidance normalization for improved control over generation quality and style consistency -- **Nested Dual CFG Support**: Added nested style configuration to DualCFGGuider node, offering more sophisticated guidance control patterns -- **SamplingPercentToSigma Node**: New utility node for precise sigma calculation from sampling percentages, improving workflow flexibility +**Sampling & Generation Features** +- **SA-Solver Sampler**: New reconstructed SA-Solver sampling algorithm providing enhanced numerical stability +- **Experimental CFGNorm Node**: Classifier-free guidance normalization for improved control over generation quality +- **Nested Dual CFG Support**: Added nested style configuration to DualCFGGuider node +- **SamplingPercentToSigma Node**: New utility node for precise sigma calculation from sampling percentages -### Enhanced Training Capabilities -- **Multi Image-Caption Dataset Support**: LoRA training node now handles multiple image-caption datasets simultaneously, streamlining training workflows -- **Better Training Loop Implementation**: Optimized training algorithms for improved convergence and stability during model fine-tuning -- **Enhanced Error Detection**: Added model detection error hints for LoRA operations, providing clearer feedback when issues occur +**Training Capabilities** +- **Multi Image-Caption Dataset Support**: LoRA training node now handles multiple image-caption datasets simultaneously +- **Training Loop Implementation**: Optimized training algorithms for improved convergence and stability +- **Error Detection**: Added model detection error hints for LoRA operations -### Platform & Performance Improvements -- **Async Node Support**: Full support for asynchronous node functions with earlier execution optimization, improving workflow performance for I/O intensive operations -- **Chroma Flexibility**: Un-hardcoded patch_size parameter in Chroma, allowing better adaptation to different model configurations -- **LTXV VAE Decoder**: Switched to improved default padding mode for better image quality with LTXV models -- **Safetensors Memory Management**: Added workaround for mmap issues, improving reliability when loading large model files +**Platform & Performance Improvements** +- **Async Node Support**: Full support for asynchronous node functions with earlier execution optimization +- **Chroma Flexibility**: Un-hardcoded patch_size parameter in Chroma +- **LTXV VAE Decoder**: Switched to improved default padding mode for better image quality +- **Safetensors Memory Management**: Added workaround for mmap issues -### API & Integration Enhancements -- **Custom Prompt IDs**: API now allows specifying prompt IDs for better workflow tracking and management -- **Kling API Optimization**: Increased polling timeout to prevent user timeouts during video generation workflows -- **History Token Cleanup**: Removed sensitive tokens from history items for improved security +**API & Integration Enhancements** +- **Custom Prompt IDs**: API now allows specifying prompt IDs for better workflow tracking +- **Kling API Optimization**: Increased polling timeout to prevent user timeouts +- **History Token Cleanup**: Removed sensitive tokens from history items - **Python 3.9 Compatibility**: Fixed compatibility issues ensuring broader platform support -### Bug Fixes & Stability -- **MaskComposite Fixes**: Resolved errors when destination masks have 2 dimensions, improving mask workflow reliability +**Bug Fixes & Stability** +- **MaskComposite Fixes**: Resolved errors when destination masks have 2 dimensions - **Fresca Input/Output**: Corrected input and output handling for Fresca model workflows - **Reference Bug Fixes**: Resolved incorrect reference bugs in Gemini node implementations -- **Line Ending Standardization**: Automated detection and removal of Windows line endings for cross-platform consistency +- **Line Ending Standardization**: Automated detection and removal of Windows line endings -### Developer Experience +**Developer Experience** - **Warning Systems**: Added torch import mistake warnings to catch common configuration issues - **Template Updates**: Multiple template version updates (0.1.36, 0.1.37, 0.1.39) for improved custom node development -- **Documentation**: Enhanced fast_fp16_accumulation documentation in portable configurations - -These improvements make ComfyUI more robust for production workflows while introducing powerful new sampling techniques and training capabilities essential for advanced AI research and creative applications. +- **Documentation**: Enhanced fast_fp16_accumulation documentation + -**Advanced Sampling & Model Control Enhancements** +**Sampling & Model Control Enhancements** -This release delivers significant improvements to sampling algorithms and model control systems, particularly benefiting advanced AI researchers and workflow creators: +This release delivers improvements to sampling algorithms and model control systems: -### New Sampling Capabilities -- **TCFG Node**: Enhanced classifier-free guidance control for more nuanced generation control in your workflows -- **ER-SDE Sampler**: Migrated from VE to VP algorithm with new sampler node, providing better numerical stability for complex generation tasks -- **Skip Layer Guidance (SLG)**: Alternative implementation for precise layer-level control during inference, perfect for advanced model steering workflows +**Sampling Capabilities** +- **TCFG Node**: Enhanced classifier-free guidance control for more nuanced generation control +- **ER-SDE Sampler**: Migrated from VE to VP algorithm with new sampler node +- **Skip Layer Guidance (SLG)**: Implementation for precise layer-level control during inference -### Enhanced Development Tools -- **Custom Node Management**: New `--whitelist-custom-nodes` argument pairs with `--disable-all-custom-nodes` for precise development control -- **Performance Optimizations**: Dual CFG node now optimizes automatically when CFG is 1.0, reducing computational overhead -- **GitHub Actions Integration**: Automated release webhook notifications keep developers informed of new updates +**Development Tools** +- **Custom Node Management**: New `--whitelist-custom-nodes` argument pairs with `--disable-all-custom-nodes` +- **Performance Optimizations**: Dual CFG node now optimizes automatically when CFG is 1.0 +- **GitHub Actions Integration**: Automated release webhook notifications -### Image Processing Improvements -- **New Transform Nodes**: Added ImageRotate and ImageFlip nodes for enhanced image manipulation workflows -- **ImageColorToMask Fix**: Corrected mask value returns for more accurate color-based masking operations -- **3D Model Support**: Upload 3D models to custom subfolders for better organization in complex projects +**Image Processing Improvements** +- **Transform Nodes**: Added ImageRotate and ImageFlip nodes for enhanced image manipulation +- **ImageColorToMask Fix**: Corrected mask value returns for more accurate color-based masking +- **3D Model Support**: Upload 3D models to custom subfolders for better organization -### Guidance & Conditioning Enhancements -- **PerpNeg Guider**: Updated with improved pre and post-CFG handling plus performance optimizations +**Guidance & Conditioning Enhancements** +- **PerpNeg Guider**: Updated with improved pre and post-CFG handling - **Latent Conditioning Fix**: Resolved issues with conditioning at index > 0 for multi-step workflows -- **Denoising Steps**: Added denoising step support to several samplers for cleaner outputs +- **Denoising Steps**: Added denoising step support to several samplers -### Platform Stability +**Platform Stability** - **PyTorch Compatibility**: Fixed contiguous memory issues with PyTorch nightly builds - **FP8 Fallback**: Automatic fallback to regular operations when FP8 operations encounter exceptions -- **Audio Processing**: Removed deprecated torchaudio.save function dependencies with warning fixes +- **Audio Processing**: Removed deprecated torchaudio.save function dependencies -### Model Integration +**Model Integration** - **Moonvalley Nodes**: Added native support for Moonvalley model workflows -- **Scheduler Reordering**: Simple scheduler now defaults first for better user experience -- **Template Updates**: Multiple template version updates (0.1.31-0.1.35) for improved custom node development - -### Security & Safety -- **Safe Loading**: Added warnings when loading files unsafely, with documentation noting that checkpoint files are loaded safely by default -- **File Validation**: Enhanced checkpoint loading safety measures for secure workflow execution +- **Scheduler Reordering**: Simple scheduler now defaults first +- **Template Updates**: Multiple template version updates (0.1.31-0.1.35) -These improvements make ComfyUI more robust for production workflows while expanding creative possibilities for AI artists working with advanced sampling techniques and model control systems. +**Security & Safety** +- **Safe Loading**: Added warnings when loading files unsafely +- **File Validation**: Enhanced checkpoint loading safety measures - -**Enhanced Model Support & Workflow Reliability** + -This release brings significant improvements to model compatibility and workflow stability: +**Model Support & Workflow Reliability** -- **Expanded Model Documentation**: Added comprehensive support documentation for Flux Kontext and Omnigen 2 models, making it easier for creators to integrate these powerful models into their workflows -- **VAE Encoding Improvements**: Removed unnecessary random noise injection during VAE encoding, resulting in more consistent and predictable outputs across workflow runs -- **Memory Management Fix**: Resolved a critical memory estimation bug specifically affecting Kontext model usage, preventing out-of-memory errors and improving workflow stability +This release brings improvements to model compatibility and workflow stability: -These changes enhance the reliability of advanced model workflows while maintaining ComfyUI's flexibility for AI artists and researchers working with cutting-edge generative models. +**Expanded Model Documentation**: Added support documentation for Flux Kontext and Omnigen 2 models +**VAE Encoding Improvements**: Removed unnecessary random noise injection during VAE encoding +**Memory Management Fix**: Resolved a memory estimation bug affecting Kontext model usage + -**Major Model Support Additions** -- **Cosmos Predict2 Support**: Full implementation for both text-to-image (2B and 14B models) and image-to-video generation workflows, expanding video creation capabilities -- **Enhanced Flux Compatibility**: Chroma Text Encoder now works seamlessly with regular Flux models, improving text conditioning quality -- **LoRA Training Integration**: New native LoRA training node using weight adapter scheme, enabling direct model fine-tuning within ComfyUI workflows +**Model Support Additions** +- **Cosmos Predict2 Support**: Implementation for text-to-image (2B and 14B models) and image-to-video generation workflows +- **Flux Compatibility**: Chroma Text Encoder now works with regular Flux models +- **LoRA Training Integration**: New native LoRA training node using weight adapter scheme **Performance & Hardware Optimizations** -- **AMD GPU Enhancements**: Enabled FP8 operations and PyTorch attention on GFX1201 and other compatible AMD GPUs for faster inference -- **Apple Silicon Fixes**: Addressed long-standing FP16 attention issues on Apple devices, improving stability for Mac users -- **Flux Model Stability**: Resolved black image generation issues with certain Flux models in FP16 precision +- **AMD GPU Enhancements**: Enabled FP8 operations and PyTorch attention on AMD GPUs +- **Apple Silicon Fixes**: Addressed FP16 attention issues on Apple devices +- **Flux Model Stability**: Resolved black image generation issues with certain Flux models -**Advanced Sampling Improvements** -- **Rectified Flow (RF) Samplers**: Added SEEDS and multistep DPM++ SDE samplers with RF support, providing more sampling options for cutting-edge models -- **ModelSamplingContinuousEDM**: New cosmos_rflow option for enhanced sampling control with Cosmos models -- **Memory Optimization**: Improved memory estimation for Cosmos models with uncapped resolution support +**Sampling Improvements** +- **Rectified Flow Samplers**: Added SEEDS and multistep DPM++ SDE samplers with RF support +- **ModelSamplingContinuousEDM**: New cosmos_rflow option for enhanced sampling control +- **Memory Optimization**: Improved memory estimation for Cosmos models **Developer & Integration Features** -- **SQLite Database Support**: Enhanced data management capabilities for custom nodes and workflow storage -- **PyProject.toml Integration**: Automatic web folder registration and settings configuration from pyproject files -- **Frontend Flexibility**: Support for semver suffixes and prerelease frontend versions for custom deployments -- **Tokenizer Enhancements**: Configurable min_length settings with tokenizer_data for better text processing +- **SQLite Database Support**: Enhanced data management capabilities for custom nodes +- **PyProject.toml Integration**: Automatic web folder registration from pyproject files +- **Frontend Flexibility**: Support for semver suffixes and prerelease frontend versions +- **Tokenizer Enhancements**: Configurable min_length settings with tokenizer_data **Quality of Life Improvements** -- **Kontext Aspect Ratio Fix**: Resolved widget-only limitation, now works properly in all connection modes -- **SaveLora Consistency**: Standardized filename format across all save nodes for better file organization -- **Python Version Warnings**: Added alerts for outdated Python installations to prevent compatibility issues -- **WebcamCapture Fixes**: Corrected IS_CHANGED signature for reliable live input workflows +- **Kontext Aspect Ratio Fix**: Resolved widget-only limitation +- **SaveLora Consistency**: Standardized filename format across all save nodes +- **Python Version Warnings**: Added alerts for outdated Python installations +- **WebcamCapture Fixes**: Corrected IS_CHANGED signature -This release significantly expands ComfyUI's model ecosystem support while delivering crucial stability improvements and enhanced hardware compatibility across different platforms. -This release brings powerful new workflow utilities and performance optimizations for ComfyUI creators: +**Workflow Tools & Performance Optimizations** -### New Workflow Tools -- **ImageStitch Node**: Concatenate multiple images seamlessly in your workflows - perfect for creating comparison grids or composite outputs -- **GetImageSize Node**: Extract image dimensions with batch processing support, essential for dynamic sizing workflows -- **Regex Replace Node**: Advanced text manipulation capabilities for prompt engineering and string processing workflows +This release brings new workflow utilities and performance optimizations: -### Enhanced Model Compatibility -- **Improved Tensor Handling**: Streamlined list processing makes complex multi-model workflows more reliable -- **BFL API Optimization**: Refined support for Kontext [pro] and [max] models with cleaner node interfaces -- **Performance Boost**: Fused multiply-add operations in chroma processing for faster generation times +**Workflow Tools** +- **ImageStitch Node**: Concatenate multiple images seamlessly in your workflows +- **GetImageSize Node**: Extract image dimensions with batch processing support +- **Regex Replace Node**: Advanced text manipulation capabilities for workflows -### Developer Experience Improvements -- **Custom Node Support**: Added pyproject.toml support for better custom node dependency management -- **Help Menu Integration**: New help system in the Node Library sidebar for faster node discovery -- **API Documentation**: Enhanced API nodes documentation for workflow automation +**Model Compatibility** +- **Tensor Handling**: Streamlined list processing makes multi-model workflows more reliable +- **BFL API Optimization**: Refined support for Kontext models with cleaner node interfaces +- **Performance Boost**: Fused multiply-add operations in chroma processing for faster generation -### Frontend & UI Enhancements -- **Frontend Updated to v1.21.7**: Multiple stability fixes and performance improvements +**Developer Experience** +- **Custom Node Support**: Added pyproject.toml support for better dependency management +- **Help Menu Integration**: New help system in the Node Library sidebar +- **API Documentation**: Enhanced API nodes documentation + +**Frontend & UI Enhancements** +- **Frontend Updated to v1.21.7**: Stability fixes and performance improvements - **Custom API Base Support**: Better subpath handling for custom deployment configurations -- **Security Hardening**: XSS vulnerability fixes for safer workflow sharing +- **Security Hardening**: XSS vulnerability fixes -### Bug Fixes & Stability -- **Pillow Compatibility**: Updated deprecated API calls to maintain compatibility with latest image processing libraries +**Bug Fixes & Stability** +- **Pillow Compatibility**: Updated deprecated API calls - **ROCm Support**: Improved version detection for AMD GPU users - **Template Updates**: Enhanced project templates for custom node development -These updates strengthen ComfyUI's foundation for complex AI workflows while making the platform more accessible to new users through improved documentation and helper tools. - - + \ No newline at end of file diff --git a/zh-CN/changelog/index.mdx b/zh-CN/changelog/index.mdx index 0ce72947..9971c298 100644 --- a/zh-CN/changelog/index.mdx +++ b/zh-CN/changelog/index.mdx @@ -1,304 +1,297 @@ --- 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、改进和错误修复" icon: "clock-rotate-left" --- - + -**增强的用户界面体验与先进模型支持** +**模型集成与性能提升** -此版本带来了重大的用户体验改进和前沿的模型支持，提升了工作流创建和在各种AI应用中的性能表现： +本次更新扩展了ComfyUI的模型支持，优化了API功能，并提升了工作流程的稳定性： -### 用户界面增强 -- **最近使用项目 API**：新增用于跟踪界面中最近使用项目的 API，通过提供对常用节点和组件的快速访问来简化工作流创建 -- **改进的工作流导航**：通过更好地组织常用元素来增强用户体验，减少搜索节点所花费的时间 +**Qwen模型生态** +- **Qwen图像模型支持**：改进了LoRA加载和模型合并功能，支持更复杂的视觉工作流程 +- **Qwen模型合并节点**：新增节点，支持合并Qwen图像模型 +- **SimpleTuner Lycoris LoRA支持**：扩展了对Qwen-Image模型的Lycoris LoRA兼容性 -### 先进模型集成 -- **Qwen 视觉模型支持**：初步支持 Qwen 图像模型，包含全面的配置选项，包括默认偏移设置和灵活的潜在空间尺寸处理 -- **优化的图像处理**：增强的 Qwen 模型集成允许更多样化的图像分析和生成工作流，扩展了视觉任务的AI能力 +**API与性能** +- **异步API节点**：引入异步API节点，支持非阻塞工作流程执行 +- **内存处理优化**：RepeatLatentBatch节点改进，能正确处理多维latent +- **WAN 2.2 Fun Control支持**：新增对WAN 2.2 fun control功能的支持 -### 革命性的视频生成 -- **Veo3 视频生成**：添加了强大的 Veo3 视频生成节点，集成了音频支持，使创作者能够直接在 ComfyUI 工作流中制作具有同步音频的高质量视频内容 -- **音视频合成**：突破性功能，在单个节点中结合视频和音频生成，非常适合内容创作者和多媒体专业人士 +**硬件优化** +- **AMD GPU改进**：提升了AMD Radeon的FP16精度处理和性能 +- **RDNA3架构修复**：解决了gfx1201 GPU使用Flux模型的问题 +- **PyTorch支持更新**：升级了CUDA和ROCM PyTorch版本 -### 性能与稳定性改进 -- **增强的内存管理**：通过改进的类型转换和设备传输操作优化条件 (cond) VRAM 使用，减少复杂生成任务期间的内存开销 -- **设备一致性**：全面修复确保所有条件数据和上下文保持在正确的设备上，防止崩溃并提高工作流可靠性 -- **ControlNet 稳定性**：解决了关键的 ControlNet 兼容性问题，恢复了精确图像控制工作流的完整功能 +**开发体验** +- **日志记录优化**：功能标志仅在详细模式下显示 +- **音频处理安全**：增强了torchaudio导入安全检查 +- **Kling API改进**：修复了Kling Image API节点的图像类型参数 -### 开发者与系统增强 -- **强大的错误处理**：当条件设备不匹配时添加智能警告和崩溃预防，改进工作流调试和稳定性 -- **模板更新**：多个模板版本更新 (0.1.47, 0.1.48, 0.1.51)，保持与最新开发标准的兼容性，确保平滑的节点集成 + + -### 工作流优势 -- **更快的迭代**：最近使用项目 API 实现更快的工作流组装和修改 -- **增强的创造力**：Qwen 视觉模型为图像理解和操作工作流开辟了新的可能性 -- **专业视频制作**：Veo3 集成将 ComfyUI 转变为综合的多媒体创作平台 -- **改进的可靠性**：内存优化和设备管理修复确保复杂的多模型工作流稳定运行 -- **更好的性能**：优化的 VRAM 使用允许在资源有限的系统上进行更雄心勃勃的项目 +**界面优化与模型支持** -此版本显著扩展了 ComfyUI 的功能，特别是对于使用先进视觉模型的多媒体创作者和专业人士，同时通过更好的界面组织和增强的系统稳定性改善了整体用户体验。 +此版本改进了用户体验，增加了前沿模型支持： - - +**用户界面** +- **最近项目 API**：新增跟踪最近使用项目的API +- **工作流导航优化**：改进了常用元素的组织 -**核心 API 增强与性能优化** +**模型集成** +- **Qwen视觉模型支持**：初步支持Qwen图像模型 +- **图像处理优化**：增强了Qwen模型集成 -此版本引入了重要的后端改进和性能优化，增强了工作流执行和节点开发能力： +**视频生成** +- **Veo3视频生成**：新增Veo3视频生成节点，支持音频 +- **音视频合成**：在单个节点中结合视频和音频生成 + +**性能与稳定** +- **内存管理优化**：优化了条件VRAM使用 +- **设备一致性**：修复了条件数据和上下文的设备问题 +- **ControlNet稳定性**：解决了ControlNet兼容性问题 + +**开发与系统** +- **错误处理**：添加了条件设备不匹配的警告 +- **模板更新**：更新了多个模板版本 + + + -### ComfyAPI 核心框架 -- **ComfyAPI Core v0.0.2**：核心 API 框架的重大更新，为自定义节点开发和第三方集成提供了更好的稳定性和可扩展性 -- **部分执行支持**：新的后端支持部分工作流执行，通过允许选择性节点执行，实现复杂多阶段工作流的更高效处理 +**API增强与性能优化** -### 视频处理改进 -- **WAN Camera 内存优化**：增强了基于 WAN 的相机工作流的内存管理，减少视频处理操作期间的 VRAM 使用 -- **WanFirstLastFrameToVideo 修复**：解决了当 clip vision 组件不可用时阻止正确生成视频的关键问题，提高了工作流可靠性 +此版本引入了后端改进和性能优化： -### 性能与模型优化 -- **VAE 非线性增强**：在 VAE 操作中用优化的 torch.silu 替换手动激活函数，为图像编码/解码提供更好的性能和数值稳定性 -- **WAN VAE 优化**：对 WAN VAE 操作进行额外的微调优化，提高视频生成工作流中的处理速度和内存效率 +**ComfyAPI框架** +- **ComfyAPI Core v0.0.2**：核心API框架更新，提升了稳定性和可扩展性 +- **部分执行支持**：新增后端支持部分工作流执行 -### 节点架构演进 -- **V3 节点架构定义**：下一代节点架构系统的初始实现，为增强节点类型定义和改进工作流验证奠定基础 -- **模板更新**：多个模板版本更新（0.1.44、0.1.45），确保与最新节点开发标准和最佳实践的兼容性 +**视频处理** +- **WAN Camera内存优化**：改进了基于WAN的相机工作流内存管理 +- **WanFirstLastFrameToVideo修复**：解决了视频生成的关键问题 -### 工作流开发优势 -- **增强的视频工作流**：改善了视频生成管道的稳定性和性能，特别是那些使用基于 WAN 模型的工作流 -- **更好的内存管理**：优化的内存使用模式使有限 VRAM 系统能够运行更复杂的工作流 -- **改进的 API 可靠性**：核心 API 增强为自定义节点开发和工作流自动化提供了更稳定的基础 -- **部分执行灵活性**：新的部分执行功能允许更高效的调试和迭代式工作流开发 +**性能与模型** +- **VAE优化**：在VAE操作中优化了torch.silu +- **WAN VAE优化**：对WAN VAE操作进行了优化 -这些基础性改进强化了 ComfyUI 的核心架构，同时为视频处理工作流和内存密集型操作提供即时收益，使平台对于休闲创作者和专业 AI 开发工作流都更加强大。 +**节点架构** +- **V3节点架构**：实现了下一代节点架构系统 +- **模板更新**：更新了多个模板版本 **内存优化与大模型性能** -本次发布专注于大模型工作流的关键内存优化，特别是改进了 WAN 2.2 模型的性能，并增强了高端显卡的 VRAM 管理： +本次更新优化了大模型工作流的内存使用： -### WAN 2.2 模型优化 -- **减少内存占用**：去除了 WAN 2.2 VAE 操作中不必要的内存克隆，显著减少了图像编码/解码工作流中的内存使用 -- **5B I2V 模型支持**：对 WAN 2.2 5B 图像到视频模型进行内存优化，使这些模型对 VRAM 有限的创作者更加易用 +**WAN 2.2模型** +- **内存占用减少**：减少了WAN 2.2 VAE操作的内存使用 +- **5B I2V模型支持**：优化了WAN 2.2 5B图像到视频模型 -### 增强的 VRAM 管理 -- **Windows 大显卡支持**：为 Windows 上的高端显卡增加了额外的保留 VRAM 分配，防止在密集生成工作流中出现系统不稳定 -- **更好的内存分配**：改进了同时使用多个大模型的用户的内存管理 - -### 工作流性能优势 -- **更快的 VAE 处理**：WAN 2.2 VAE 操作现在运行更高效，内存开销更少，实现更流畅的图像生成管道 -- **稳定的大模型推理**：增强了处理数十亿参数模型时的稳定性 -- **改进的批处理**：内存优化使大模型的批操作处理能力更强 - -这些针对性优化使 ComfyUI 在涉及大体量模型的专业工作流中更加可靠。 +**VRAM管理** +- **Windows大显卡支持**：为Windows高端显卡增加了VRAM分配 +- **内存分配改进**：改进了多大模型用户的内存管理 -**硬件加速和音频处理改进** - -此版本专注于扩展硬件支持并增强工作流创建者的音频处理能力： +**硬件加速和音频处理** -### 音频处理增强 -- **PyAV 音频后端**：用 PyAV 替换 torchaudio.load，在视频工作流中提供更可靠的音频处理，改善兼容性和性能 -- **更好的音频集成**：增强多媒体生成工作流的音频处理，特别有利于视频内容创作者 +此版本扩展了硬件支持并增强了音频处理： -### 扩展的硬件支持 -- **Iluvatar CoreX 支持**：添加对 Iluvatar CoreX 加速器的原生支持，为 AI 推理扩展硬件选项 -- **Intel XPU 优化**：全面的 XPU 支持改进，包括异步卸载功能和设备特定优化 -- **AMD ROCm 增强**：在 Torch 2.8 上为 gfx1201 默认启用 PyTorch attention，提升 AMD 硬件性能 -- **CUDA 内存管理**：修复 CUDA malloc 仅在启用 CUDA 的 PyTorch 安装上激活，防止在其他平台上发生冲突 +**音频处理** +- **PyAV音频后端**：用PyAV替换torchaudio.load +- **音频集成优化**：增强了多媒体生成工作流的音频处理 -### 采样算法改进 -- **Euler CFG++ 增强**：在 Euler CFG++ 采样器中分离去噪和噪声估计过程，改善数值精度和质量 -- **WAN 模型支持**：添加对 WAN（基于小波的注意力网络）模型的全面支持，包括 ATI 支持和 WAN 2.2 兼容性 +**硬件支持** +- **Iluvatar CoreX支持**：添加了对Iluvatar CoreX加速器的支持 +- **Intel XPU优化**：改进了XPU支持 +- **AMD ROCm增强**：在Torch 2.8上为gfx1201启用了PyTorch attention +- **CUDA内存管理**：修复了CUDA malloc激活问题 -### 高级训练功能 -- **增强的训练节点**：向训练工作流添加算法支持、梯度累积和可选梯度检查点 -- **改进的训练灵活性**：为自定义模型训练提供更好的内存管理和性能优化 +**采样算法** +- **Euler CFG++增强**：分离了去噪和噪声估计过程 +- **WAN模型支持**：添加了对WAN模型的全面支持 -### 节点和工作流增强 -- **Moonvalley V2V 节点**：添加 Moonvalley Marey V2V 节点，为视频到视频工作流提供增强的输入验证 -- **负面提示词更新**：改进 Moonvalley 节点的负面提示词处理，提供对生成输出的更好控制 -- **历史 API 增强**：向 get_history API 添加 map_function 参数，实现更灵活的工作流历史管理 +**训练功能** +- **训练节点增强**：添加了算法支持、梯度累积和可选梯度检查点 +- **训练灵活性**：提供了更好的内存管理和性能优化 -### API 和系统改进 -- **前端版本跟踪**：在 /system_stats API 响应中添加 required_frontend_version 参数，改善版本兼容性 -- **设备信息**：增强 XPU 设备名称打印，改善硬件识别和调试 -- **模板更新**：多个模板更新（0.1.40、0.1.41），确保与最新节点开发标准的兼容性 +**节点和工作流** +- **Moonvalley V2V节点**：添加了Moonvalley Marey V2V节点 +- **负面提示词更新**：改进了Moonvalley节点的负面提示词处理 +- **历史API增强**：向get_history API添加了map_function参数 -### 开发者体验 -- **文档更新**：使用 HiDream E1.1 示例增强 README，并更新模型集成指南 -- **行结束符修复**：通过标准化工作流中的行结束符改善跨平台兼容性 -- **代码清理**：移除已弃用的代码并优化各种组件以提高可维护性 +**API和系统** +- **前端版本跟踪**：在/system_stats API响应中添加了required_frontend_version +- **设备信息**：增强了XPU设备名称打印 +- **模板更新**：更新了多个模板版本 -这些改进使 ComfyUI 在不同硬件平台上更易于使用，同时增强了现代多媒体 AI 工作流所必需的音频处理能力。 +**开发体验** +- **文档更新**：增强了README和模型集成指南 +- **行结束符修复**：标准化了工作流中的行结束符 +- **代码清理**：移除了已弃用的代码 -**高级采样与训练基础设施改进** +**采样与训练功能改进** -本版本为AI研究人员和工作流程创建者引入了采样算法、训练功能和节点功能的重大增强： +本版本增强了采样算法和训练功能： -### 新的采样和生成功能 -- **SA-Solver采样器**：新的重构SA-Solver采样算法，为复杂生成工作流提供增强的数值稳定性和质量 -- **实验性CFGNorm节点**：高级无分类器引导标准化，用于改进生成质量和风格一致性的控制 -- **嵌套双CFG支持**：为DualCFGGuider节点添加嵌套风格配置，提供更复杂的引导控制模式 -- **SamplingPercentToSigma节点**：用于从采样百分比精确计算sigma的新实用节点，提高工作流程灵活性 +**采样和生成功能** +- **SA-Solver采样器**：新的重构SA-Solver采样算法 +- **实验性CFGNorm节点**：无分类器引导标准化节点 +- **嵌套双CFG支持**：为DualCFGGuider节点添加嵌套风格配置 +- **SamplingPercentToSigma节点**：用于计算sigma的新实用节点 -### 增强的训练功能 -- **多图像-描述数据集支持**：LoRA训练节点现在可以同时处理多个图像-描述数据集，简化训练工作流程 -- **更好的训练循环实现**：优化的训练算法，在模型微调过程中改善收敛性和稳定性 -- **增强的错误检测**：为LoRA操作添加模型检测错误提示，在出现问题时提供更清晰的反馈 +**训练功能** +- **多数据集支持**：LoRA训练节点支持多个图像-描述数据集 +- **训练循环优化**：优化了训练算法 +- **错误检测增强**：为LoRA操作添加了模型检测错误提示 -### 平台和性能改进 -- **异步节点支持**：完全支持异步节点函数，优化早期执行，改善I/O密集型操作的工作流程性能 -- **Chroma灵活性**：在Chroma中取消硬编码的patch_size参数，允许更好地适应不同的模型配置 -- **LTXV VAE解码器**：切换到改进的默认填充模式，提高LTXV模型的图像质量 -- **Safetensors内存管理**：为mmap问题添加解决方案，提高加载大型模型文件时的可靠性 +**平台和性能** +- **异步节点支持**：完全支持异步节点函数 +- **Chroma灵活性**：取消了Chroma中硬编码的patch_size参数 +- **LTXV VAE解码器**：切换到改进的默认填充模式 +- **Safetensors内存管理**：为mmap问题添加了解决方案 -### API和集成增强 -- **自定义提示ID**：API现在允许指定提示ID，以便更好地跟踪和管理工作流程 -- **Kling API优化**：增加轮询超时时间，防止视频生成工作流程中的用户超时 -- **历史令牌清理**：从历史项目中删除敏感令牌以提高安全性 -- **Python 3.9兼容性**：修复兼容性问题，确保更广泛的平台支持 +**API和集成** +- **自定义提示ID**：API允许指定提示ID +- **Kling API优化**：增加了轮询超时时间 +- **历史令牌清理**：从历史项目中删除了敏感令牌 +- **Python 3.9兼容性**：修复了兼容性问题 -### 错误修复和稳定性 -- **MaskComposite修复**：解决目标蒙版具有2个维度时的错误，提高蒙版工作流程可靠性 -- **Fresca输入/输出**：修正Fresca模型工作流程的输入和输出处理 -- **引用错误修复**：解决Gemini节点实现中的错误引用问题 -- **行结束标准化**：自动检测和删除Windows行结束符，确保跨平台一致性 +**错误修复和稳定性** +- **MaskComposite修复**：解决了目标蒙版的错误 +- **Fresca输入/输出**：修正了Fresca模型工作流程的处理 +- **引用错误修复**：解决了Gemini节点实现中的引用问题 +- **行结束标准化**：自动检测和删除Windows行结束符 -### 开发者体验 -- **警告系统**：添加torch导入错误警告，以捕获常见配置问题 -- **模板更新**：多个模板版本更新（0.1.36、0.1.37、0.1.39），改进自定义节点开发 -- **文档**：增强便携式配置中fast_fp16_accumulation的文档 - -这些改进使ComfyUI在生产工作流程中更加稳健，同时引入了对高级AI研究和创意应用必不可少的强大新采样技术和训练功能。 +**开发体验** +- **警告系统**：添加了torch导入错误警告 +- **模板更新**：更新了多个模板版本 +- **文档**：增强了fast_fp16_accumulation的文档 -**高级采样和模型控制增强** +**采样和模型控制增强** -此版本在采样算法和模型控制系统方面提供了重大改进，特别有利于高级AI研究人员和工作流创建者： +此版本改进了采样算法和模型控制系统： -### 新采样功能 -- **TCFG节点**：增强的分类器无关引导控制，为您的工作流提供更细致的生成控制 -- **ER-SDE采样器**：从VE迁移到VP算法，配备新的采样器节点，为复杂生成任务提供更好的数值稳定性 -- **跳层引导（SLG）**：用于推理期间精确层级控制的替代实现，完美适用于高级模型导向工作流 +**新采样功能** +- **TCFG节点**：增强的分类器无关引导控制 +- **ER-SDE采样器**：从VE迁移到VP算法 +- **跳层引导（SLG）**：用于推理期间精确层级控制 -### 增强的开发工具 -- **自定义节点管理**：新的`--whitelist-custom-nodes`参数与`--disable-all-custom-nodes`配对，提供精确的开发控制 -- **性能优化**：双CFG节点现在在CFG为1.0时自动优化，减少计算开销 -- **GitHub Actions集成**：自动化发布webhook通知让开发者及时了解新更新 +**开发工具** +- **自定义节点管理**：新的`--whitelist-custom-nodes`参数 +- **性能优化**：双CFG节点在CFG为1.0时自动优化 +- **GitHub Actions集成**：自动化发布webhook通知 -### 图像处理改进 -- **新变换节点**：添加了ImageRotate和ImageFlip节点，增强图像操作工作流 -- **ImageColorToMask修复**：修正了掩码值返回，提供更准确的基于颜色的掩码操作 -- **3D模型支持**：上传3D模型到自定义子文件夹，为复杂项目提供更好的组织 +**图像处理** +- **新变换节点**：添加了ImageRotate和ImageFlip节点 +- **ImageColorToMask修复**：修正了掩码值返回 +- **3D模型支持**：上传3D模型到自定义子文件夹 -### 引导和条件增强 -- **PerpNeg引导器**：更新了改进的前后CFG处理以及性能优化 -- **潜在条件修复**：解决了多步骤工作流中索引 > 0 的条件问题 -- **去噪步骤**：为多个采样器添加去噪步骤支持，获得更清洁的输出 +**引导和条件** +- **PerpNeg引导器**：更新了前后CFG处理 +- **潜在条件修复**：解决了多步骤工作流中的条件问题 +- **去噪步骤**：为多个采样器添加去噪步骤支持 -### 平台稳定性 -- **PyTorch兼容性**：修复了PyTorch nightly构建的连续内存问题 -- **FP8回退**：当FP8操作遇到异常时自动回退到常规操作 -- **音频处理**：移除了已弃用的torchaudio.save函数依赖并修复警告 +**平台稳定性** +- **PyTorch兼容性**：修复了PyTorch nightly构建的问题 +- **FP8回退**：当FP8操作遇到异常时自动回退 +- **音频处理**：移除了已弃用的torchaudio.save函数依赖 -### 模型集成 +**模型集成** - **Moonvalley节点**：为Moonvalley模型工作流添加原生支持 -- **调度器重新排序**：简单调度器现在默认优先，提供更好的用户体验 -- **模板更新**：多个模板版本更新（0.1.31-0.1.35），改进自定义节点开发 - -### 安全性和安全保护 -- **安全加载**：在不安全加载文件时添加警告，文档说明检查点文件默认安全加载 -- **文件验证**：增强检查点加载安全措施，确保工作流安全执行 +- **调度器重新排序**：简单调度器现在默认优先 +- **模板更新**：更新了多个模板版本 -这些改进使ComfyUI在生产工作流中更加稳健，同时为使用高级采样技术和模型控制系统的AI艺术家扩展了创作可能性。 +**安全性** +- **安全加载**：在不安全加载文件时添加警告 +- **文件验证**：增强检查点加载安全措施 -**增强模型支持与工作流可靠性** +**模型支持与工作流可靠性** -本次发布在模型兼容性和工作流稳定性方面带来了重大改进： +本次更新改进了模型兼容性和工作流稳定性： -- **扩展模型文档**：为 Flux Kontext 和 Omnigen 2 模型添加了全面的支持文档，让创作者更容易将这些强大的模型集成到他们的工作流中 -- **VAE 编码改进**：移除了 VAE 编码过程中不必要的随机噪声注入，使工作流运行的输出更加一致和可预测 -- **内存管理修复**：解决了专门影响 Kontext 模型使用的关键内存估算错误，防止内存不足错误并提高工作流稳定性 - -这些变更提升了高级模型工作流的可靠性，同时保持了 ComfyUI 为从事前沿生成模型工作的 AI 艺术家和研究人员提供的灵活性。 +**扩展模型文档**：为Flux Kontext和Omnigen 2模型添加了支持文档 +**VAE编码改进**：移除了VAE编码过程中不必要的随机噪声注入 +**内存管理修复**：解决了影响Kontext模型使用的关键内存估算错误 -**主要模型支持新增** -- **Cosmos Predict2 支持**：全面实现文本到图像（2B 和 14B 模型）和图像到视频生成工作流，扩展视频创作功能 -- **增强的 Flux 兼容性**：Chroma Text Encoder 现在能与常规 Flux 模型无缝协作，提升文本条件质量 -- **LoRA 训练集成**：使用权重适配器方案的全新原生 LoRA 训练节点，支持在 ComfyUI 工作流中直接进行模型微调 +**模型支持新增** +- **Cosmos Predict2支持**：实现文本到图像和图像到视频生成工作流 +- **增强的Flux兼容性**：Chroma Text Encoder能与常规Flux模型协作 +- **LoRA训练集成**：新增原生LoRA训练节点 **性能和硬件优化** -- **AMD GPU 增强**：在 GFX1201 和其他兼容的 AMD GPU 上启用 FP8 操作和 PyTorch 注意力机制，加速推理 -- **Apple Silicon 修复**：解决了 Apple 设备上长期存在的 FP16 注意力问题，提升 Mac 用户的稳定性 -- **Flux 模型稳定性**：解决了特定 Flux 模型在 FP16 精度下生成黑色图像的问题 +- **AMD GPU增强**：在AMD GPU上启用FP8操作和PyTorch注意力机制 +- **Apple Silicon修复**：解决了Apple设备上的FP16注意力问题 +- **Flux模型稳定性**：解决了特定Flux模型生成黑色图像的问题 -**高级采样改进** -- **Rectified Flow (RF) 采样器**：新增支持 RF 的 SEEDS 和多步 DPM++ SDE 采样器，为前沿模型提供更多采样选项 -- **ModelSamplingContinuousEDM**：新增 cosmos_rflow 选项，增强对 Cosmos 模型的采样控制 -- **内存优化**：改进了支持无限分辨率的 Cosmos 模型的内存估算 +**采样改进** +- **Rectified Flow采样器**：新增支持RF的SEEDS和多步DPM++ SDE采样器 +- **ModelSamplingContinuousEDM**：新增cosmos_rflow选项 +- **内存优化**：改进了Cosmos模型的内存估算 -**开发者和集成功能** -- **SQLite 数据库支持**：增强自定义节点和工作流存储的数据管理功能 -- **PyProject.toml 集成**：从 pyproject 文件自动注册 web 文件夹和配置设置 -- **前端灵活性**：支持语义化版本后缀和预发布前端版本，适用于自定义部署 -- **分词器增强**：通过 tokenizer_data 配置 min_length 设置，优化文本处理 +**开发和集成功能** +- **SQLite数据库支持**：增强自定义节点的数据管理功能 +- **PyProject.toml集成**：从pyproject文件自动注册web文件夹 +- **前端灵活性**：支持语义化版本后缀和预发布前端版本 +- **分词器增强**：通过tokenizer_data配置min_length设置 **使用体验改进** -- **Kontext 宽高比修复**：解决了仅限小组件的限制，现在在所有连接模式下都能正常工作 -- **SaveLora 一致性**：统一所有保存节点的文件名格式，优化文件组织 -- **Python 版本警告**：为过时的 Python 安装添加警报，防止兼容性问题 -- **WebcamCapture 修复**：修正了 IS_CHANGED 签名，确保实时输入工作流的可靠性 - -此版本显著扩展了 ComfyUI 的模型生态系统支持，同时提供了关键的稳定性改进和跨平台硬件兼容性增强。 +- **Kontext宽高比修复**：解决了小组件限制 +- **SaveLora一致性**：统一了所有保存节点的文件名格式 +- **Python版本警告**：为过时的Python安装添加警报 +- **WebcamCapture修复**：修正了IS_CHANGED签名 -本次发布为 ComfyUI 创作者带来了强大的新工作流实用工具和性能优化： +**工作流工具和性能优化** -### 新的工作流工具 -- **ImageStitch 节点**：在工作流中无缝拼接多个图像 - 非常适合创建对比网格或复合输出 -- **GetImageSize 节点**：提取图像尺寸并支持批处理，对于动态调整大小的工作流至关重要 -- **Regex Replace 节点**：高级文本处理功能，适用于提示词工程和字符串处理工作流 +本次更新带来了新的工作流工具和性能优化： -### 增强的模型兼容性 -- **改进的张量处理**：简化的列表处理使复杂的多模型工作流更加可靠 -- **BFL API 优化**：完善了对 Kontext [pro] 和 [max] 模型的支持，提供更清晰的节点界面 -- **性能提升**：在色度处理中使用融合乘加运算，加快生成速度 +**新工作流工具** +- **ImageStitch节点**：在工作流中拼接多个图像 +- **GetImageSize节点**：提取图像尺寸并支持批处理 +- **Regex Replace节点**：高级文本处理功能 -### 开发者体验改进 -- **自定义节点支持**：添加 pyproject.toml 支持，改善自定义节点依赖管理 -- **帮助菜单集成**：在节点库侧边栏中新增帮助系统，加快节点发现速度 -- **API 文档**：增强 API 节点文档，支持工作流自动化 +**模型兼容性** +- **张量处理改进**：简化的列表处理使多模型工作流更可靠 +- **BFL API优化**：完善了对Kontext模型的支持 +- **性能提升**：在色度处理中使用融合乘加运算 -### 前端和 UI 增强 -- **前端更新至 v1.21.7**：多项稳定性修复和性能改进 -- **自定义 API 基础支持**：改进了自定义部署配置的子路径处理 -- **安全加固**：修复 XSS 漏洞，确保工作流分享更安全 +**开发体验** +- **自定义节点支持**：添加pyproject.toml支持 +- **帮助菜单集成**：在节点库侧边栏中新增帮助系统 +- **API文档**：增强API节点文档 -### 错误修复和稳定性 -- **Pillow 兼容性**：更新了已弃用的 API 调用，保持与最新图像处理库的兼容性 -- **ROCm 支持**：改进了 AMD GPU 用户的版本检测 -- **模板更新**：增强了自定义节点开发的项目模板 +**前端和UI** +- **前端更新至v1.21.7**：多项稳定性修复和性能改进 +- **自定义API基础支持**：改进了自定义部署配置的子路径处理 +- **安全加固**：修复XSS漏洞 -这些更新强化了 ComfyUI 处理复杂 AI 工作流的基础，同时通过改进的文档和辅助工具让平台对新用户更加友好。 +**错误修复和稳定性** +- **Pillow兼容性**：更新了已弃用的API调用 +- **ROCm支持**：改进了AMD GPU用户的版本检测 +- **模板更新**：增强了自定义节点开发的项目模板