From d4be95a87e44cd356fd339337727f783d119d5f7 Mon Sep 17 00:00:00 2001 From: coderfromthenorth93 <213232275+coderfromthenorth93@users.noreply.github.com> Date: Thu, 4 Sep 2025 03:33:05 -0400 Subject: [PATCH 1/3] Add/update changelog/index.mdx --- changelog/index.mdx | 27 ++++++++++++++++++++++++++- 1 file changed, 26 insertions(+), 1 deletion(-) diff --git a/changelog/index.mdx b/changelog/index.mdx index 2958a2ef8..429b61f90 100644 --- a/changelog/index.mdx +++ b/changelog/index.mdx @@ -4,6 +4,32 @@ description: "Track ComfyUI's latest features, improvements, and bug fixes" icon: "clock-rotate-left" --- + + +**API Integration Expansion & Node Schema Modernization** + +This release significantly expands ComfyUI's API integration capabilities and modernizes the node architecture for improved workflow reliability. + +**New API Service Integration** +- **ByteDance Image Nodes**: Added comprehensive support for ByteDance image generation services, expanding creative options for AI artists working with enterprise-grade image models. +- **Ideogram Character Node**: New integration with Ideogram's character generation API, enabling specialized character creation workflows directly within ComfyUI. +- **Enhanced Prompt Control**: API interrupt handler now accepts prompt_id parameters, providing better control over API-driven generation processes and enabling more sophisticated workflow automation. + +**Next-Generation UXO/UNO Model Support** +- **UXO Subject Identity LoRA**: Implemented support for UXO (formerly USO) subject identity LoRA models, enabling consistent character and subject preservation across generated images. +- **UXO Style Reference**: Added UXO style reference functionality for maintaining visual consistency in multi-image workflows. + +**Workflow Utility Enhancements** +- **ImageScaleToMaxDimension Node**: New utility node for intelligent image scaling based on maximum dimension constraints, simplifying image preprocessing in complex workflows. +- **SEEDS Noise System**: Updated noise decomposition with improved algorithms and refactored architecture for more predictable and controllable generation results. + +**Performance & Architecture Improvements** +- **V3 Schema Migration**: Extensive conversion of core nodes (Stable Cascade, Video, Stability, Primitive, Runway API, and AlignYourStepsScheduler) to the modern V3 schema, improving node reliability and future compatibility. +- **Convolution AutoTuning**: Enabled automatic convolution optimization for better GPU utilization and faster inference across supported hardware configurations. +- **RoPE Issue Resolution**: Fixed potential issues with Rotary Position Embedding that could affect transformer-based model performance. + + + **Performance Enhancement** @@ -47,7 +73,6 @@ This focused update improves the core node model patching system that underpins - **Enhanced Stability**: Core model patching improvements contribute to more reliable node execution and model handling across different workflow configurations - **Audio Workflow Integration & Enhanced Performance Optimizations** From 1cd659a7df2d4603a4db371fc053c2525be25feb Mon Sep 17 00:00:00 2001 From: coderfromthenorth93 <213232275+coderfromthenorth93@users.noreply.github.com> Date: Thu, 4 Sep 2025 03:33:06 -0400 Subject: [PATCH 2/3] Add/update zh-CN/changelog/index.mdx --- zh-CN/changelog/index.mdx | 25 +++++++++++++++++++++++++ 1 file changed, 25 insertions(+) diff --git a/zh-CN/changelog/index.mdx b/zh-CN/changelog/index.mdx index 1cc826c67..f7e07f5ec 100644 --- a/zh-CN/changelog/index.mdx +++ b/zh-CN/changelog/index.mdx @@ -4,6 +4,31 @@ description: "追踪ComfyUI的最新功能、改进和错误修复" icon: "clock-rotate-left" --- + + +**API集成扩展与节点架构现代化** + +此版本显著扩展了ComfyUI的API集成能力，并现代化了节点架构以提高工作流可靠性。 + +**新增API服务集成** +- **字节跳动图像节点**：新增对字节跳动图像生成服务的全面支持，为使用企业级图像模型的AI艺术家扩展创作选择。 +- **Ideogram角色节点**：新集成Ideogram角色生成API，支持在ComfyUI内直接进行专业的角色创建工作流。 +- **增强提示控制**：API中断处理器现在接受prompt_id参数，为API驱动的生成过程提供更好的控制，并支持更复杂的工作流自动化。 + +**下一代UXO/UNO模型支持** +- **UXO主体身份LoRA**：实现对UXO（原USO）主体身份LoRA模型的支持，在生成图像中保持角色和主体的一致性。 +- **UXO风格参考**：新增UXO风格参考功能，在多图像工作流中保持视觉一致性。 + +**工作流实用功能增强** +- **ImageScaleToMaxDimension节点**：新增智能图像缩放实用节点，基于最大尺寸约束进行缩放，简化复杂工作流中的图像预处理。 +- **SEEDS噪声系统**：更新噪声分解算法并重构架构，实现更可预测和可控的生成结果。 + +**性能与架构改进** +- **V3架构迁移**：大规模转换核心节点（Stable Cascade、Video、Stability、Primitive、Runway API和AlignYourStepsScheduler）到现代V3架构，提高节点可靠性和未来兼容性。 +- **卷积自动调优**：启用自动卷积优化，在支持的硬件配置上实现更好的GPU利用率和更快的推理速度。 +- **RoPE问题解决**：修复可能影响基于transformer模型性能的旋转位置嵌入潜在问题。 + + **Windows内存优化** From e1bddedea5bc6bd5d1a225bc8cd6fd2a9238517f Mon Sep 17 00:00:00 2001 From: ComfyUI Wiki Date: Thu, 4 Sep 2025 16:23:01 +0800 Subject: [PATCH 3/3] Update Changelog --- changelog/index.mdx | 42 +++++++++++++++------------------------ zh-CN/changelog/index.mdx | 32 +++++++++++++---------------- 2 files changed, 30 insertions(+), 44 deletions(-) diff --git a/changelog/index.mdx b/changelog/index.mdx index 429b61f90..569578f3b 100644 --- a/changelog/index.mdx +++ b/changelog/index.mdx @@ -6,28 +6,22 @@ icon: "clock-rotate-left" -**API Integration Expansion & Node Schema Modernization** - -This release significantly expands ComfyUI's API integration capabilities and modernizes the node architecture for improved workflow reliability. - -**New API Service Integration** -- **ByteDance Image Nodes**: Added comprehensive support for ByteDance image generation services, expanding creative options for AI artists working with enterprise-grade image models. -- **Ideogram Character Node**: New integration with Ideogram's character generation API, enabling specialized character creation workflows directly within ComfyUI. -- **Enhanced Prompt Control**: API interrupt handler now accepts prompt_id parameters, providing better control over API-driven generation processes and enabling more sophisticated workflow automation. - -**Next-Generation UXO/UNO Model Support** -- **UXO Subject Identity LoRA**: Implemented support for UXO (formerly USO) subject identity LoRA models, enabling consistent character and subject preservation across generated images. -- **UXO Style Reference**: Added UXO style reference functionality for maintaining visual consistency in multi-image workflows. - -**Workflow Utility Enhancements** -- **ImageScaleToMaxDimension Node**: New utility node for intelligent image scaling based on maximum dimension constraints, simplifying image preprocessing in complex workflows. -- **SEEDS Noise System**: Updated noise decomposition with improved algorithms and refactored architecture for more predictable and controllable generation results. - -**Performance & Architecture Improvements** -- **V3 Schema Migration**: Extensive conversion of core nodes (Stable Cascade, Video, Stability, Primitive, Runway API, and AlignYourStepsScheduler) to the modern V3 schema, improving node reliability and future compatibility. -- **Convolution AutoTuning**: Enabled automatic convolution optimization for better GPU utilization and faster inference across supported hardware configurations. -- **RoPE Issue Resolution**: Fixed potential issues with Rotary Position Embedding that could affect transformer-based model performance. - +**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` + +**Workflow Utilities** +- **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 + +**Performance & Architecture** +- **V3 Schema Migration**: Converted some core nodes to V3 schema +- **Convolution AutoTuning**: Enabled automatic convolution optimization + +**New API Integration** +- **ByteDance Image Nodes**: Added support for ByteDance image generation services +- **Ideogram Character Reference**: Ideogram v3 API now supports character reference @@ -54,10 +48,6 @@ This release focuses on Wan2.2 S2V related video workflow capabilities and model - **Fun Control Model Support**: Added support for Wan2.2 5B fun control model. - **Fun Inpaint Model Support**: Integrated Wan2.2 5B fun inpaint model. -**Workflow Templates** -- **Template v0.1.70**: Added initial version of Wan2.2 S2V workflows - - diff --git a/zh-CN/changelog/index.mdx b/zh-CN/changelog/index.mdx index f7e07f5ec..40b3a8b23 100644 --- a/zh-CN/changelog/index.mdx +++ b/zh-CN/changelog/index.mdx @@ -6,29 +6,25 @@ icon: "clock-rotate-left" -**API集成扩展与节点架构现代化** +**ByteDance USO 模型支持** +- **UXO主体身份LoRA**：支持USO主体身份驱动的图像生成 LoRA 模型，基于 FLUX 架构 +- **相关工作流，请在模板 `Flux` -> `Flux.1 Dev USO Reference Image Generation` 查找 -此版本显著扩展了ComfyUI的API集成能力，并现代化了节点架构以提高工作流可靠性。 +**工作流实用功能** +- **ImageScaleToMaxDimension节点**：新增智能图像缩放实用节点 +- **SEEDS噪声系统**：更新噪声分解算法 +- **增强提示控制**：中断处理器现在接受prompt_id参数 -**新增API服务集成** -- **字节跳动图像节点**：新增对字节跳动图像生成服务的全面支持，为使用企业级图像模型的AI艺术家扩展创作选择。 -- **Ideogram角色节点**：新集成Ideogram角色生成API，支持在ComfyUI内直接进行专业的角色创建工作流。 -- **增强提示控制**：API中断处理器现在接受prompt_id参数，为API驱动的生成过程提供更好的控制，并支持更复杂的工作流自动化。 +**性能与架构** +- **V3架构迁移**：转换部分核心节点到V3架构 +- **卷积自动调优**：启用自动卷积优化 -**下一代UXO/UNO模型支持** -- **UXO主体身份LoRA**：实现对UXO（原USO）主体身份LoRA模型的支持，在生成图像中保持角色和主体的一致性。 -- **UXO风格参考**：新增UXO风格参考功能，在多图像工作流中保持视觉一致性。 - -**工作流实用功能增强** -- **ImageScaleToMaxDimension节点**：新增智能图像缩放实用节点，基于最大尺寸约束进行缩放，简化复杂工作流中的图像预处理。 -- **SEEDS噪声系统**：更新噪声分解算法并重构架构，实现更可预测和可控的生成结果。 - -**性能与架构改进** -- **V3架构迁移**：大规模转换核心节点（Stable Cascade、Video、Stability、Primitive、Runway API和AlignYourStepsScheduler）到现代V3架构，提高节点可靠性和未来兼容性。 -- **卷积自动调优**：启用自动卷积优化，在支持的硬件配置上实现更好的GPU利用率和更快的推理速度。 -- **RoPE问题解决**：修复可能影响基于transformer模型性能的旋转位置嵌入潜在问题。 +**新增API集成** +- **字节跳动图像节点**：新增对字节跳动图像生成服务的支持 +- **Ideogram角色参考**：Ideogram v3 API现在支持角色参考 + **Windows内存优化**