Swift-Image: Exploring the Performance Frontier of Compact Unified Image Generation Models

2026-08-20

AI Summary

研究通过系统训练工程和优化方法，探讨了在有限计算资源下小型图像生成模型的性能极限，提出了Swift-Image模型。

Abstract

We present Swift-Image, a compact unified model for text-to-image generation, single-image editing, and multi-image editing. Our goal is to explore how far a relatively small visual generator can be pushed through systematic training engineering under a constrained computational budget. Swift-Image adopts an efficient 6B single-stream DiT and a progressive training pipeline that evolves from broad semantic coverage to higher resolution, stronger visual quality, and unified generation-editing supervision. For post-training, we employ parallel expert reinforcement learning followed by multi-teacher on-policy distillation to alleviate interference among heterogeneous objectives. We further decouple high-level reasoning from pixel-level rendering with a Prompt Enhancer that translates user requests into generator-aligned visual specifications. For efficient deployment, structural pruning and few-step distillation produce 3B and accelerated variants. Swift-Image achieves leading aggregate performance among evaluated open-source models with only 6B parameters and 243K GPU training hours; the compressed 3B model incurs nearly no loss, while few-step distillation further improves aggregate editing performance with substantially fewer sampling steps. Our study also summarizes practical lessons for architecture, data curriculum, post-training, prompt enhancement, and model compression.

Problem

• Compact Unified Model
• Text-to-Image Generation
• Single-Image Editing
• Multi-Image Editing
• Constrained Computational Budget

Innovation

• compact unified model
• progressive training pipeline
• parallel expert reinforcement learning
• multi-teacher on-policy distillation
• prompt enhancer