IB-Flow: Information Bottleneck-Guided CFG Distillation for Few-Step Text-to-Image Generation

arXiv:2607.09133 · cs.CV, cs.AI · Submitted 2026-07-10 · Read on arXiv

cs.CV, cs.AI

Submitted: 2026-07-10

Updated: 2026-09-23

Code: https://github.com/zhjy2016/IBFlow

Terminology

• Distillation — 48× in this paper · explained in 2 episodes
• Fidelity — 28× in this paper · explained in 2 episodes
• Information Bottleneck — 14× in this paper
• Alignment — 13× in this paper · explained in 1 episode
• Diffusion Model — 13× in this paper · explained in 8 episodes
• Diffusion Models — 13× in this paper · explained in 6 episodes
• Flow Matching — 10× in this paper · explained in 8 episodes
• Distribution Matching — 7× in this paper · explained in 2 episodes
• Classifier-Free Guidance — 6× in this paper
• Generative Model — 5× in this paper · explained in 2 episodes
• Generative Models — 5× in this paper · explained in 2 episodes
• Semantic Alignment — 5× in this paper · explained in 3 episodes
• Benchmark — 4× in this paper · explained in 2 episodes
• CFG Augmentation — 4× in this paper
• Consistency — 4× in this paper · explained in 3 episodes
• Normalizing Flow — 4× in this paper · explained in 3 episodes
• Normalizing Flows — 4× in this paper · explained in 4 episodes
• Rectified Flow — 4× in this paper · explained in 3 episodes
• Distribution Matching Distillation — 3× in this paper
• Fisher Information — 3× in this paper · explained in 3 episodes
• Generative Modeling — 3× in this paper · explained in 3 episodes
• Semantic Gap — 3× in this paper · explained in 2 episodes
• Core — 2× in this paper · explained in 2 episodes
• Failure Modes — 2× in this paper · explained in 3 episodes
• Pointwise Mutual Information — 2× in this paper
• Unified Framework — 2× in this paper · explained in 5 episodes
• Ablation — 1× in this paper · explained in 1 episode
• Ablation Studies — 1× in this paper · explained in 1 episode
• Adaptive Mechanism — 1× in this paper · explained in 1 episode
• Aggregation — 1× in this paper · explained in 1 episode
• Computational overhead — 1× in this paper · explained in 2 episodes
• Consistency Distillation — 1× in this paper · explained in 2 episodes
• Diffusion Process — 1× in this paper · explained in 2 episodes
• Edge Devices — 1× in this paper · explained in 2 episodes
• Entanglement — 1× in this paper · explained in 3 episodes
• Flow Matching Model — 1× in this paper · explained in 2 episodes
• Information Gain — 1× in this paper · explained in 2 episodes
• Knowledge Distillation — 1× in this paper · explained in 11 episodes
• Latent Diffusion Model — 1× in this paper · explained in 2 episodes
• Latent Diffusion Models — 1× in this paper · explained in 2 episodes
• Optimal Transport — 1× in this paper · explained in 5 episodes
• Pointwise Mutual Information (PMI) — 1× in this paper · explained in 3 episodes
• Provenance — 1× in this paper · explained in 3 episodes
• Signal-to-noise ratio (SNR) — 1× in this paper · explained in 2 episodes
• Signalto-Noise Ratio — 1× in this paper
• Symmetry Breaking — 1× in this paper · explained in 3 episodes

Sources

• Mean Flows for One-step Generative Modeling
• STARFlow: Scaling Latent Normalizing Flows for High-resolution Image Synthesis
• Classifier-Free Diffusion Guidance
• ELLA: Equip Diffusion Models with LLM for Enhanced Semantic Alignment
• Simple ReFlow: Improved Techniques for Fast Flow Models
• SenseFlow: Scaling Distribution Matching for Flow-based Text-to-Image Distillation
• SDXL-Lightning: Progressive Adversarial Diffusion Distillation
• Decoupled DMD: CFG Augmentation as the Spear, Distribution Matching as the Shield
• Self-Adversarial One Step Generation via Condition Shifting
• Knowledge Distillation in Iterative Generative Models for Improved Sampling Speed
• Progressive Distillation for Fast Sampling of Diffusion Models
• TwinFlow: Realizing One-step Generation on Large Models with Self-adversarial Flows
• Qwen-Image Technical Report
• OpenUni: A Simple Baseline for Unified Multimodal Understanding and Generation
• ArcFlow: Unleashing 2-Step Text-to-Image Generation via High-Precision Non-Linear Flow Distillation
• Large Scale Diffusion Distillation via Score-Regularized Continuous-Time Consistency

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models