Setting-Matched and Semantics-Scaled Benchmarking of One-Step Generative Models Against Multistep Diffusion and Flow Models
State-of-the-art text-to-image models produce high-quality images, but inference remains expensive as generation requires several sequential ODE or denoising steps. Native one-step models aim to reduce this cost by mapping noise to an image in a single step, yet fair comparisons to multi-step systems are difficult because studies use mismatched sampling steps and different classifier-free guidance (CFG) settings, where CFG can shift FID, Inception Score, and CLIP-based alignment in opposing directions. It is also unclear how well one-step models scale to multi-step inference, and there is limited standardized out-of-distribution evaluation for label-ID-conditioned generators beyond ImageNet. To address this, we benchmark eight models spanning one-step flows (MeanFlow, Improved MeanFlow, SoFlow), multi-step baselines (RAE, Scale-RAE), and established systems (SiT, Stable Diffusion 3.5, FLUX.1) under a class-conditional protocol on ImageNet validation, ImageNetV2, and reLAIONet, our new proofread out-of-distribution dataset aligned to ImageNet label IDs. Using FID, Inception Score, CLIP Score, and Pick Score, we show that FID-focused model development and CFG selection can be misleading in few-step regimes, where guidance changes can improve FID while degrading text-image alignment and human preference signals, worsening visual quality. To make these tradeoffs explicit, we introduce CLIP-scaled and PickScore-scaled variants of FID (csFID, psFID) and Inception Score (csIS, psIS) to serve as a diagnostic for semantically aligned image generation.
Code (0)
등록된 구현이 없습니다.
Tasks
Image GenerationSimilar Papers 제목 키워드 기반
Zero-Shot End-to-End Spoken Language Understanding via Cross-Modal Selective Self-Training
End-to-end (E2E) spoken language understanding (SLU) is constrained by the cost of collecting speech-semantics pairs, especially when label domains change. Hence, we explore \textit{zero-shot} E2E SLU, which learns E2E S…
Natural Language UnderstandingSpoken Language UnderstandingBenchmarking down-scaled (not so large) pre-trained language models
Benchmarking down-scaled (not so large) pre-trained language models
Large Transformer-based language models are pre-trained on corpora of varying sizes, for a different number of steps and with different batch sizes. At the same time, more fundamental components, such as the pre-training…
BenchmarkingSolar Multimodal Transformer: Intraday Solar Irradiance Predictor using Public Cameras and Time Series
Accurate intraday solar irradiance forecasting is crucial for optimizing dispatch planning and electricity trading. For this purpose, we introduce a novel and effective approach that includes three distinguishing compone…
BenchmarkingSolar Irradiance ForecastingTime SeriesSAPO: Step-Aligned Policy Optimization for Reasoning-Based Generative Recommendation
Generative recommendation treats next-item prediction as autoregressive item-identifier generation. Specifically, items are encoded as semantic identifiers (SIDs), which are short coarse-to-fine token sequences whose ear…
Reinforcement Learning