arXiv cs.AI
· Papers
Mage-Flow: An Efficient Native-Resolution Foundation Model for Image Generation and Editing
arXiv:2607.19064v1 Announce Type: cross Abstract: Large-scale visual generators are increasingly capable but costly to train, fine-tune, and deploy. We introduce Mage-Flow, a compact 4B-scale generative stack for efficient text-to-image generation and instruction-based image editing. The stack is built from two co-desi