v0.40.0 v0.41.0

medium risk

Comfy-Org/ComfyUIOct 13, 2026 → Oct 15, 20262 days between releases

What's New

Adds Flux3-image model support, HDR nodes, and geometry tools.

New Features

  • ImageSDRToHDR node for HDR image conversion.
  • ReferenceMultiLatent node for latent referencing.
  • Flux3-image model support.
  • Nodes to retrieve Latent Geometries.

Improvements

  • UX improvements for ReferenceMultiLatent node.
  • Updated workflow templates to v0.11.84.

Bug Fixes

  • Re-enabled LoRA stack loader nodes after temporary disablement.

Upgrade Notes

LoRA stack loader nodes are restored to functionality. The new Flux3-image model is now supported. No configuration changes are required.

The Two Releases

v0.40.0

v0.40.0

Oct 13, 2026· 8 days ago

v0.40.0 introduces a default-on assets system with metadata extraction and EXR preview support, alongside expanded 3D model handling and camera workflow tools. The release also features significant performance optimizations for Qwen 3.5 LLMs, new partner node integrations, and improvements to the Linear model API.

Full release notes
v0.41.0

v0.41.0

Oct 15, 2026· 6 days ago

This release introduces new nodes for HDR processing and latent geometry extraction, alongside support for the Flux3-image model and MiniMax-H3 LightVAE. It also includes updates to workflow templates and a core route for the default workflow.

Full release notes