ByteDance Seedream 4.0 Integration
- New Seedream Node: Added ByteDanceSeedream (4.0) node.
New Model Support
- Hunyuan Image 2.1 regular model
- Hunyuan 3D 2.1
- Stable Audio 2.5 API
- Seedance Video API
ByteDance USO Model Support
- UXO Subject Identity LoRA Support: It’s a subject identity LoRA model based on FLUX architecture
- Related Workflow: Please find the workflow in the template
Flux->Flux.1 Dev USO Reference Image Generation
- ImageScaleToMaxDimension Node: New utility for intelligent image scaling
- SEEDS Noise System: Updated noise decomposition with improved algorithms
- Enhanced Prompt Control: Interrupt handler now accepts prompt_id parameters
- V3 Schema Migration: Converted some core nodes to V3 schema
- Convolution AutoTuning: Enabled automatic convolution optimization
- ByteDance Image Nodes: Added support for ByteDance image generation services
- Ideogram Character Reference: Ideogram v3 API now supports character reference
Performance Enhancement
- Reduced RAM Usage on Windows
Wan2.2 S2V Workflow Enhancements & Model Support ExpansionThis release focuses on Wan2.2 S2V related video workflow capabilities and model support expansion: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.
- 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.
- Fun Control Model Support: Added support for Wan2.2 5B fun control model.
- Fun Inpaint Model Support: Integrated Wan2.2 5B fun inpaint model.
Node Model Patch ImprovementsThis 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, making ComfyUI extensions for Qwen-Image ControlNet easier
- Enhanced Stability: Core model patching improvements contribute to more reliable node execution and model handling across different workflow configurations
Audio Workflow Integration & Enhanced Performance OptimizationsThis release adds ComfyUI audio processing capabilities and includes performance improvements and model compatibility updates: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: 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
- Gemini Image API Node: Added new Google Gemini Image API node, the “nano-Nano-banana” image editing model API with high consistency
- WAN 2.2 S2V Model Support: Work-in-progress implementation of WAN 2.2 Sound-to-Video model with optimized memory usage and performance
- Enhanced S2V Performance: Performance improvements for video generation longer than 120 frames, improving extended video workflows
- Better Memory Estimation: Improved memory usage estimation for S2V workflows prevents out-of-memory errors during long video generation
- Negative Audio Handling: Fixed negative audio input handling in S2V workflows to use proper zero values
- DPM++ 2M SDE Heun (RES) Sampler: New advanced sampler by @Balladie provides additional sampling options for fine-tuned generation control
- LatentConcat Node: New node for concatenating latent tensors, enabling advanced latent space manipulation workflows
- EasyCache/LazyCache Stability: Fixed critical crashes when tensor properties (shape/dtype/device) change during sampling, ensuring workflow reliability
- ControlNet Type Models: Enhanced compatibility fixes for ControlNet-type models working with Qwen Edit and Kontext workflows
- Flux Memory Optimization: Adjusted Flux model memory usage factors for better resource utilization
- Template Updates: Updated to versions 0.1.66 and 0.1.68
- Documentation Cleanup: Removed incompletely implemented models from readme to avoid user confusion
Enhanced Model Support & Qwen Image ControlNet IntegrationThis release significantly expands ControlNet capabilities and improves model compatibility, making ComfyUI workflows more versatile and reliable:Qwen ControlNet Ecosystem
- Diffsynth ControlNet Support: Added support for Qwen Diffsynth ControlNets with Canny and depth conditioning, enabling precise edge and depth-based image control
- InstantX Qwen ControlNet: Integrated InstantX Qwen ControlNet for expanded creative control options
- Inpaint ControlNet/Model Patches: Enhanced inpainting capabilities with dedicated Diffsynth inpaint ControlNet support
- V3 Architecture Migration: String nodes, Google Veo API, and Ideogram API nodes upgraded to V3 architecture for better performance and consistency
- Enhanced API Nodes: OpenAI Chat node renamed to “OpenAI ChatGPT” for clarity, Gemini Chat node now includes copy button functionality
- Improved Usability: API nodes now provide better user experience with clearer labeling and enhanced interaction features
- LTXV Noise Mask Fix: Resolved key frame noise mask dimension issues when real noise masks exist, ensuring stable video workflow execution
- 3D Latent Conditioning Control: Fixed conditioning masks on 3D latents, enabling proper depth-aware conditioning control in advanced workflows
- Invalid Filename Handling: Improved workflow save functionality with proper handling of invalid filenames, preventing save failures
- EasyCache & LazyCache: Implemented advanced caching systems for improved workflow execution performance
- Python 3.13 Support: Full compatibility with Python 3.13, keeping ComfyUI current with latest Python developments
- Frontend Update: Updated to v1.25.10 with improved navigation and user interface enhancements
- Elementwise Fusions: Added performance optimizations through elementwise operations fusion
- Navigation Mode Rollback: Rolled back navigation default to traditional legacy mode, avoiding user experience issues caused by default enabled standard navigation mode. Users can still enable standard navigation mode in settings
Model Support
- Qwen-Image-Edit Model: Native support for Qwen-Image-Edit
- FluxKontextMultiReferenceLatentMethod Node: Multi-reference input node for Flux workflows
- WAN 2.2 Fun Camera Model Support: Support for video generation through camera control
- Template Updates: Upgraded to version 0.1.62, added Wan2.2 Fun Camera and Qwen Image Edit templates
- Context Windows Support: Enhanced sampling code to support longer sequence generation tasks
- SDPA Backend Optimization: Improved Scaled Dot Product Attention backend settings for better performance
- Audio Recording Node: New native audio recording node, now you can record audio directly in ComfyUI
- Audio Video Integration: Complete audio-video dependency integration
- GPT-5 Series Models: Support for the latest GPT-5 models
- Kling V2-1 and V2-1-Master: Updated video generation model functionality
- Minimax Hailuo Video Node: New video generation node
- Vidu Video Node: Vidu API node support
- Google Model Updates: Added new Google Gemini models
- OpenAI API Fix: Fixed MIME type errors in OpenAI API node input images
- Intel GPU Compatibility: Fixed Intel integrated GPU compatibility issues
- PyTorch Compatibility: Enhanced compatibility with older PyTorch versions
- Torch Compile Optimization: Improved torch compile behavior
- Memory Management: Optimized installation size and memory efficiency
- Subgraph Support: Subgraph functionality support
- Shortcut Panel: Added bottom shortcut panel
- UI Layout Modifications: Modified terminal entry layout, added template, log panel and other entries
- Standard Canvas Mode: Added standard canvas mode, can be switched in
Lite Graph>Canvas>Canvas Navigation Mode - Mini Map: Added workflow mini map
- Tab Preview: Added workflow tab preview
- Top Tab Menu Layout Adjustments
Model Integration & Performance EnhancementsThis 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
- 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
- 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
- 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
- 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
UI Experience & Model SupportThis 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
- Workflow Navigation: Enhanced user experience with better organization of commonly accessed elements
- 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
- 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
- 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
- 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
- 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
- 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
API Enhancement & Performance OptimizationsThis release introduces backend improvements and performance optimizations that enhance workflow execution and node development: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
- 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
- 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
- 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
- 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
Memory Optimization & Large Model PerformanceThis 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, reducing memory usage
- 5B I2V Model Support: Memory optimization for WAN 2.2 5B image-to-video models, making these models more accessible
- 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
- 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 ProcessingThis release expands hardware support and enhances audio processing capabilities: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
- 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
- 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
- Training Nodes: Added algorithm support, gradient accumulation, and optional gradient checkpointing
- Training Flexibility: Better memory management and performance optimization for custom model training
- 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
- 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
- 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
Sampling & Training ImprovementsThis release introduces enhancements to sampling algorithms, training capabilities, and node functionality: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
- 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
- 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
- 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
- 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
- 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
Sampling & Model Control EnhancementsThis release delivers improvements to sampling algorithms and model control systems: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
- Custom Node Management: New
--whitelist-custom-nodesargument 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
- 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
- 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
- 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
- Moonvalley Nodes: Added native support for Moonvalley model workflows
- Scheduler Reordering: Simple scheduler now defaults first
- Template Updates: Multiple template version updates (0.1.31-0.1.35)
- Safe Loading: Added warnings when loading files unsafely
- File Validation: Enhanced checkpoint loading safety measures
Model Support & Workflow ReliabilityThis release brings improvements to model compatibility and workflow stability: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
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
- 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
- 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
- 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
- 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
Workflow Tools & Performance OptimizationsThis release brings new workflow utilities and performance optimizations: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
- 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
- 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 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
- Pillow Compatibility: Updated deprecated API calls
- ROCm Support: Improved version detection for AMD GPU users
- Template Updates: Enhanced project templates for custom node development