ComfyUI Newsletter
Subscribe
Sign in
Home
Engineering
Archive
Latest
Top
Discussions
Higgsfield promised to open source their entire platform. They didn’t, so let’s help them.
For the next two weeks, we’re putting up $25,000 worth of prizes for the best open-source builds made using the Comfy Developer Platform.
Oct 15
•
Allyson Toy
9
1
Krea 3 is now available via Partner Nodes
Krea’s reference-driven image model — multi-reference inputs, targeted edits that hold the details you name, and fast iteration — lands in ComfyUI as a…
Oct 15
•
Rob
1
FLUX 3 Image Klein in ComfyUI: 5.6B Open Weights
5.6B parameters, base and distilled open weights, bounding boxes and multi-reference editing. FLUX 3 Image Klein runs natively in ComfyUI.
Oct 15
•
Rob
5
2
Nvidia VFX Nodes for Video Upscaling, Frame Generation and SDR-to-HDR, for VFX Professionals
Upscale, interpolate, and convert to HDR locally on your RTX GPU, with better EXR support and color management built for VFX pipelines.
Oct 13
•
Rob
and
Alexis Rolland
11
4
How I Generated Live Video with MiniMax H3 on a Single GPU
Can MiniMax H3 keep up with video playback on one GPU while still producing clips worth watching? ComfyStreamerH3 is my attempt to find out.
Oct 8
•
Bryan Wade
12
3
1
Gemini Nano Banana 2.1 is now available via Partner Nodes
1K to 4K output — Minimal, Medium and High thinking — instruction-based editing — Google's Gemini Nano Banana 2.1 lands in ComfyUI as a Partner Node.
Oct 6
•
Rob
3
Creating the story of YUI with 852話 Hakoniwa and Comfy Agent
The behind-the-scenes video that is also part of the story.
Oct 1
•
Jo Zhang
12
Comfy Agent: The First Agent for Craft
Describe what you want right inside ComfyUI. It plans, builds and runs workflows.
Oct 1
•
Jo Zhang
,
Christian Byrne
, and
Kishore Shimikeri
12
7
1
September 2026
Comfy API Is Live: Deploy ComfyUI Workflows as Production APIs
Package your workflow once, deploy it on the GPU you choose, and call it from any app, tool, or service.
Sep 30
•
Jacob Segal
5
1
Introducing Comfy Router: One API for Frontier Media Models
Build once, add models as they launch, and choose where every job runs.
Sep 23
•
Matt Miller
1
Making the MiniMax H3 Video VAE 2x Faster
The MiniMax H3 video VAE now encodes up to ~2.2x faster and decodes ~1.4-2.7x faster on Nvidia GPU.
Sep 22
•
Jukka Seppänen
11
5
Qwen-Image-2.1 in ComfyUI: Open-Weight Image Generation and Editing, Now with Transparency
7B parameters, native 2K output, RGBA transparency, and editing across up to 10 input images — Qwen-Image-2.1 runs natively in ComfyUI.
Sep 20
•
Rob
20
5
1
This site requires JavaScript to run correctly. Please
turn on JavaScript
or unblock scripts
