ComfyUI Releases
187 releases of Comfy-Org/ComfyUI
- v0.3.52
This release focuses on V3 schema migration for String nodes and implements EasyCache and LazyCache for improved performance. It also adds support for Qwen Diffsynth controlnets.
Aug 23, 2025
- v0.3.51v0.3.51 Qwen Image Edit model
This release marks the implementation of the Qwen Image Edit model and adds support for various new API nodes including Minimax, GPT-5, and Vidu.
Aug 20, 2025
- v0.3.50
This release adds support for the Qwen Image model, introduces async API nodes, and fixes issues with multi-dimensional latents and AMD GPUs.
Aug 13, 2025
- v0.3.49
Focuses on device placement accuracy and introduces initial support for the Qwen Image model alongside a new Veo3 video generation node.
Aug 5, 2025
- v0.3.48
Updates ComfyAPI Core and introduces partial execution support alongside the V3 Node Schema Definition.
Aug 2, 2025
- v0.3.47
Optimizes memory usage for Wan2.2 models, specifically targeting the 5B i2v model and VAE operations.
Jul 30, 2025
- v0.3.46
Adds support for Wan2.2, XPU, and replaces torchaudio with pyav for audio handling.
Jul 28, 2025
- v0.3.45
Enhances training capabilities with async node functions and multi-dataset support, plus introduces the SA-Solver sampler.
Jul 21, 2025
- v0.3.44
Improves custom node management and adds new samplers, including Moonvalley nodes and image manipulation tools.
Jul 8, 2025
- v0.3.43
Adds Flux Kontext and Omnigen 2 models with fixes for memory estimation and controlnet compatibility.
Jun 27, 2025
- v0.3.42
Major release featuring Flux Kontext and Omnigen 2 image editing models, plus Cosmos Predict2 support.
Jun 26, 2025
- v3.0.7
This release refactors prompt handling to support user-defined placeholders such as %RESTRICTED_CORRESPONDENTS% and %RESTRICTED_TAGS% within system messages. It introduces a dedicated RestrictionPromptService to manage these replacements and removes legacy logic from multiple services. Test scripts have also been updated to reflect these changes.
Jun 22, 2025
- v3.0.6v3.0.6 | Critical fix for Custom Providers
This release focuses on a critical bug fix for the Custom Providers, specifically addressing a 400 error encountered with the Gemini API during document analysis.
Jun 18, 2025
- v0.3.41
Introduces Cosmos Predict2 models, fp8 ops for AMD, and a LoRA training node with SQLite database support.
Jun 17, 2025
- v3.0.5v3.0.5 | Introduce fine-grained restrictions for tags and correspondents
This update introduces fine-grained restrictions for creating tags and correspondents, along with enhanced OpenAI service capabilities including external API integration and RAG Chat for Azure OpenAI.
Jun 16, 2025
- v0.3.40
A comprehensive update that adds new nodes for image manipulation (ImageStitch, GetImageSize) and regex operations, alongside various frontend updates and bug fixes.
Jun 5, 2025
- v0.3.39
This release focuses on expanding API support, introducing nodes for BFL Kontext and HiDream SimpleTuner, and refining existing Pika API nodes.
May 29, 2025
- v0.3.38
An update aimed at improving stability and memory estimation, specifically addressing frontend execution logic and GPU memory handling.
May 28, 2025
- v0.3.37
This release improves stability and error handling for AMD/ROCm users while adding new API nodes for various AI generation services.
May 27, 2025
- v0.3.36
A performance and stability focused release optimizing torch.compile compatibility, improving queue handling, and adding various utility nodes.
May 24, 2025