Skip to main content

Discover

Browse workflows, models, LoRAs, nodes, and tools

Personalised recommendations and discovery

Tutorials & Content

Guides, tutorials, videos, and articles

ComfyUI Creators

ComfyUI creators & videos

My Library

Your hardware and environment profile

Favorites, recent views, and collections

Workspace configuration

Report bugs, suggest enhancements, or request features

Documentation and guides

Logout

Krea2_FP8

MODEL

This repository provides an optimized FP8 (float8_e4m3fn) weight-only quantized version of the newly released Krea 2 OSS (Turbo) transformer.

Krea2_FP8