Mage-Flow is a compact 4B generative stack for text-to-image generation and instruction-based image editing, built from two co-designed components: Mage-VAE (a lightweight, high-fidelity latent tokenizer) and a Native-Resolution Multimodal Diffusion Transformer trained with rectified flow matching. Each task ships in Base, RL-aligned, and 4-step Turbo variants.

Highlights

• Compact & competitive. A single 4B family for generation and editing that matches or beats much larger open systems (Qwen-Image 20B, Z-Image 6B, FLUX.2 32B, FireRed-Image-Edit 20B).
• Efficient tokenizer. Mage-VAE matches FLUX.2-VAE reconstruction fidelity using ~12× / ~22× fewer encode / decode MACs per pixel, removing the VAE high-resolution bottleneck.
• Native resolution. One checkpoint generates from 512 to 2048 on any aspect ratio, including extreme 4:1 (e.g. 512×2048, 2048×512).
• System-level speed. Native-resolution packing + fused CUDA kernels cut per-step training time from ~1.93 s → ~0.78 s (~2.5× faster training); at 1024² on a single A100, Mage-Flow-Turbo 0.59 s/image and Mage-Flow-Edit-Turbo 1.02 s/edit.
• Versatile editing. Mage-Flow-Edit supports semantic content editing, appearance transformation, image restoration, and structure-aware outputs within a unified image-and-text-conditioned model.