Mage-Flow：一種高效原生解析度的基礎模型，用於影像生成與編輯

摘要

大規模視覺生成模型的能力日益增強，但其訓練、微調與部署成本高昂。我們提出Mage-Flow，一個緊湊的4B規模生成堆疊，用於高效文字到影像生成與基於指令的影像編輯。該堆疊由兩個協同設計的元件構成：Mage-VAE（輕量高保真潛在分詞器），以及使用整流流匹配訓練的原生解析度多模態擴散變壓器。Mage-VAE採用一步擴散式編碼/解碼與錨點潛在正則化，在維持強大公共VAE重建品質的同時，將分詞成本降低一個數量級以上。結合原生解析度打包與堆疊級CUDA核心融合，該堆疊支援彈性解析度訓練，並將端到端訓練吞吐量提升約2.5倍。在此基礎上，我們開發了完整的模型系列，包含用於生成與編輯的Base、RL對齊與Turbo變體。擴散NFT改善了提示跟隨、文字渲染、美學品質與編輯保真度，而結合對抗性感知引導的少步蒸餾則產生了適用於低延遲推論的4步Turbo模型。儘管規模緊湊，Mage-Flow與Mage-Flow-Edit在標準生成與編輯基準測試中仍展現出競爭力。更重要的是，Turbo變體使高解析度生成與編輯可用於互動場景：在單張NVIDIA A100 GPU上，以1024²解析度，Mage-Flow-Turbo可在0.59秒內生成影像，Mage-Flow-Edit-Turbo可在1.02秒內編輯影像，同時維持較小的記憶體佔用。這些結果表明，精心的分詞器－骨幹網路－系統協同設計，能在高效的4B模型家族中實現強大的高解析度生成與編輯。

English

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-designed components: Mage-VAE, a lightweight high-fidelity latent tokenizer, and a Native-Resolution Multimodal Diffusion Transformer trained with rectified flow matching. Mage-VAE uses one-step diffusion-style encoding and decoding with anchor-latent regularization, preserving the reconstruction quality of strong public VAEs while reducing tokenization cost by more than an order of magnitude. Together with native-resolution packing and stack-level CUDA kernel fusion, the stack supports flexible-resolution training and improves end-to-end training throughput by about 2.5times. Built on this foundation, we develop a complete model family with Base, RL-aligned, and Turbo variants for both generation and editing. Diffusion-NFT improves prompt following, text rendering, aesthetic quality, and editing fidelity, while few-step distillation with adversarial perceptual guidance produces 4-step Turbo models for low-latency inference. Despite its compact scale, Mage-Flow and Mage-Flow-Edit achieves competitive performance across standard generation and editing benchmarks. More importantly, the Turbo variants make high-resolution generation and editing practical for interactive use: at 1024^2 resolution on a single NVIDIA A100 GPU, Mage-Flow-Turbo generates an image in 0.59s, and Mage-Flow-Edit-Turbo edits an image in 1.02s, while maintaining a small memory footprint. These results show that careful tokenizer--backbone--system co-design can deliver strong high-resolution generation and editing within an efficient 4B model family.