ComfyUI Releases

A minor maintenance release that addresses a regression in comment processing within code fences and updates the package.json repository field format.

Oct 31, 2025

Introduces a new endpoint for custom node subgraphs and a major overhaul of the API nodes with async capabilities and V3 schema support.

Oct 28, 2025

This release prioritizes performance improvements, including faster cache handling and reduced overhead for object assignment, alongside stability fixes for tags and categories.

Oct 26, 2025

Addresses critical stability issues preventing Transformer models from loading and ensures proper state updates when selecting models.

Oct 25, 2025

Improves reliability by fixing timeout issues with SearxNG requests and ensuring model selection persists using local storage.

Oct 23, 2025

This release focuses on performance optimizations, including faster workflow cancellation and memory management improvements for AMD and NVIDIA hardware. It includes updates for Python 3.14 and the frontend, along with continued V3 schema conversions and fixes for API nodes.

Oct 21, 2025

This release heavily prioritizes the migration to the V3 schema, converting core nodes like Flux, SD3, and LoRA extractors. It also includes updates to API nodes (Gemini, Pika) and performance enhancements for AMD hardware.

Oct 14, 2025

This release adds the Sora2 API node and continues the conversion of API nodes and nodes to the V3 schema. It also introduces Gemma 3 as a text encoder.

Oct 8, 2025

This release is characterized by extensive V3 schema conversions for various node types and a shift from soundfile to torchaudio for audio handling. It also introduces linter support for API nodes.

Oct 6, 2025

This release focuses on workflow permissions, new portable installation links, and support for the Rodin3D Gen-2 model in API nodes.

Sep 30, 2025

This release introduces the Rodin3D Gen-2 API node, adds new audio nodes, and extends V3 schema support to many other nodes. It also adds support for Ascend NPU.

Sep 30, 2025

This release introduces extensive support for the Hunyuan image model, including distilled and refiner variants, along with V3 schema conversions for various API nodes like Kling, Wan, and Cosmos. It also adds fp8 ops support for specific hardware and updates the frontend.

Sep 23, 2025

Drops support for older Node.js versions (16 and 18) and introduces new features for URL validation, permalink variables, and code blocks.

Sep 15, 2025

A minor release focused on adding new API integrations, specifically introducing the ByteDanceSeedream (4.0) node, along with a template update for the wiki.

Sep 10, 2025

This release adds support for Hunyuan 3D 2.1 and addresses several AMD-specific optimizations, including bf16 VAE support. It also introduces StabilityAI Audio API nodes.

Sep 10, 2025

A major refactoring release focused on converting various node types to the V3 schema, including Stable Cascade, Video, and Primitive nodes. It also adds USO/UXO style reference support.

Sep 4, 2025

A performance-oriented release aimed at reducing RAM usage on Windows systems through internal optimizations.

Aug 30, 2025

This release expands support for Wan 2.2 models, adding specific support for the 5B fun control and inpaint models. It also introduces utility nodes for extending videos and cutting latents.

Aug 29, 2025

A maintenance release that updates the nodes_model_patch.py file, likely to ensure compatibility or fix issues with model handling.

Aug 28, 2025

This release introduces audio encoding capabilities with wav2vec2 and fixes critical crashes in EasyCache and LazyCache. It also adds preliminary support for Wan 2.2 S2V (Sound to Video) model.

Aug 28, 2025