ComfyUI Blog

ComfyUI Blog

Home
Notes
Archive
About
FLUX.1 Krea [dev] Lands on ComfyUI on Day-1
This is currently the best open-source FLUX model, specifically designed for text-to-image generation.
 • 
Jo Zhang
 and 
ComfyUI Wiki
2
Wan2.2 Memory Optimization
Update and try!
 • 
Jo Zhang
6
Wan2.2 Day-0 Support in ComfyUI
Wan2.2 is a brand new multimodal video generation model that adopts an innovative MoE (Mixture of Experts) architecture
 • 
ComfyUI Wiki
 and 
Jo Zhang
9
ComfyUI HiDream E1.1 Native Support
HiDream-E1.1, an iteration of HiDream E1, outperforms its predecessor and other mainstream models in various image editing aspects (e.g., color…
 • 
ComfyUI Wiki
Marey Realism v1.5 in ComfyUI – Built on 100% Licensed Content
Commercially safe, native 1080P output.
 • 
Jo Zhang
2
Intel OpenVINO Joins Forces with ComfyUI to Enhance AI Creation Efficiency
Intel OpenVINO toolkits (https://openvino.ai/), renowned for its ability to optimize and deploy AI models on Intel hardware, has recently partnered with…
 • 
ComfyUI Wiki
4

June 2025

OmniGen2 Native Support in ComfyUI!
OmniGen2 is a 7B parameter unified multimodal model that combines text-to-image generation, image editing, and multi-image composition in one powerful…
 • 
ComfyUI Wiki
4
Flux.1 Kontext [dev] Day-0 Support in ComfyUI
Generate. Edit. Repeat. All locally!
 • 
ComfyUI Wiki
 and 
Jo Zhang
17
Cosmos-Predict2 Now Supported in ComfyUI!
A family of world foundation models by Nvidia
 • 
Jo Zhang
1
Subgraph Update: Easier Testing
Greatly simplified testing process, and improvements to links, inputs, and outputs.
 • 
webfiltered
Dependency Resolution and Custom Node Standards
Making ComfyUI more comfy.
 • 
Jedrzej Kosinski
 and 
Jacob Segal
6
Subgraphs Are Coming to ComfyUI! 🎉
Subgraphs let you encapsulate complex workflows into neat, reusable nodes with inputs, outputs, and widget controls.
 • 
webfiltered
 and 
ComfyUI Wiki
14
© 2025 Comfy Org
Privacy ∙ Terms ∙ Collection notice
Start writingGet the app
Substack is the home for great culture