A PyTorch-native inference engine with hybrid cache acceleration and massive parallelism for DiTs.
-
Updated
Mar 13, 2026 - Python
A PyTorch-native inference engine with hybrid cache acceleration and massive parallelism for DiTs.
Generate 3D assets from text or images directly in Unity Editor via Flux2/GPT-Image and Trellis.2 in real-time
Multi-model Ai platform for image generation.
Add a description, image, and links to the flux2-klein topic page so that developers can more easily learn about it.
To associate your repository with the flux2-klein topic, visit your repo's landing page and select "manage topics."