AsyncDiff: Asynchronous Timestep Conditioning for Enhanced Text-to-Image Diffusion Inference

• URL: http://arxiv.org/abs/2512.18675v1
• Date: Sun, 21 Dec 2025 10:29:57 GMT
• Title: AsyncDiff: Asynchronous Timestep Conditioning for Enhanced Text-to-Image Diffusion Inference
• Abstract summary: We propose an asynchronous inference mechanism that decouples text-to-image diffusion inference schedules.<n>A lightweight timestep prediction module (TPM) selects a more feasible conditioning timestep based on the current state.<n>To keep the study computationally affordable, we cap the inference at 15 steps for SD3.5 and 10 steps for Flux.
• Score: 12.428201810981149
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Text-to-image diffusion inference typically follows synchronized schedules, where the numerical integrator advances the latent state to the same timestep at which the denoiser is conditioned. We propose an asynchronous inference mechanism that decouples these two, allowing the denoiser to be conditioned at a different, learned timestep while keeping image update schedule unchanged. A lightweight timestep prediction module (TPM), trained with Group Relative Policy Optimization (GRPO), selects a more feasible conditioning timestep based on the current state, effectively choosing a desired noise level to control image detail and textural richness. At deployment, a scaling hyper-parameter can be used to interpolate between the original and de-synchronized timesteps, enabling conservative or aggressive adjustments. To keep the study computationally affordable, we cap the inference at 15 steps for SD3.5 and 10 steps for Flux. Evaluated on Stable Diffusion 3.5 Medium and Flux.1-dev across MS-COCO 2014 and T2I-CompBench datasets, our method optimizes a composite reward that averages Image Reward, HPSv2, CLIP Score and Pick Score, and shows consistent improvement.

Related papers

• AsyncCouple-Flow: Asynchronous Cross-Modal Coupling and Flow Matching for Spatio-Temporal Forecasting [14.101995007248997]
  AsyncCouple-Flow supports weathercasting, traffic prediction, and earth-system modeling by combining heterogeneous sources such as physical fields, satellite sensors, and insitu sensors.<n>AsyncCouple-Flow outperforms state-of-the-art baselines and remains robust with up to two missing modalities.
  arXiv  Detail & Related papers  (2026-09-15T03:15:14Z)
• Efficient Text-to-Image Generation: An Adaptive Step Schedule Controller for Diffusion Models [8.491636802749417]
  Text-to-image diffusion models often use a fixed number of denoising steps, balancing time costs and image quality.<n>We propose an adaptive diffusion controller that dynamically adjusts the number of steps to generate high-quality images efficiently.
  arXiv  Detail & Related papers  (2026-09-15T03:14:52Z)
• GS-STVSR: Ultra-Efficient Continuous Spatio-Temporal Video Super-Resolution via 2D Gaussian Splatting [71.12303582606019]
  Continuous Video Super-Resolution (C-STVSR) aims to simultaneously enhance the spatial and frame rate of videos by arbitrary scale factors.<n>We propose GS-STVSR, an ultra-efficient C-STVSR framework based on 2D Gaussianting (2D-GS)<n>We show that GS-STVSR achieves state-of-the-art quality across all benchmarks.
  arXiv  Detail & Related papers  (2026-04-20T10:11:05Z)
• CIAR: Interval-based Collaborative Decoding for Image Generation Acceleration [47.52310736101766]
  Auto-regressive (AR) models have recently made notable progress in image generation, achieving performance comparable to diffusion-based approaches.<n>We address this via a cloud-device collaboration framework textbfCIAR, which utilizes on-device self-verification to handle two key properties of visual synthesis.<n>Our solution centers on an on-device token uncertainty quantifier, which adopts continuous probability intervals to accelerate processing and make it feasible for large visual vocabularies.
  arXiv  Detail & Related papers  (2026-03-26T14:04:50Z)
• BiFM: Bidirectional Flow Matching for Few-Step Image Editing and Generation [48.679227622825806]
  BiFM (Bidirectional Flow Matching) is a unified framework that jointly learns generation and inversion within a single model.<n>BiFM consistently outperforms existing few-step approaches, achieving superior performance and editability.
  arXiv  Detail & Related papers  (2026-03-26T02:16:54Z)
• Asynchronous Heavy-Tailed Optimization [23.148100548141983]
  We propose two communication schemes that handle stragglers with asynchronous updates in the presence of heavy-tailed gradient noise.<n>Our convergence guarantees under heavy-tailed noise match the rate of the synchronous counterparts and improve delay tolerance compared with existing asynchronous approaches.
  arXiv  Detail & Related papers  (2026-02-20T05:28:48Z)
• TS-DP: Reinforcement Speculative Decoding For Temporal Adaptive Diffusion Policy Acceleration [64.32072516882947]
  Diffusion Policy excels in embodied control but suffers from high inference latency and computational cost.<n>We propose Temporal-aware Reinforcement-based Speculative Diffusion Policy (TS-DP)<n>TS-DP achieves up to 4.17 times faster inference with over 94% accepted drafts, reaching an inference frequency of 25 Hz.
  arXiv  Detail & Related papers  (2025-12-13T07:53:14Z)
• PPMStereo: Pick-and-Play Memory Construction for Consistent Dynamic Stereo Matching [51.98089287914147]
  textbfPick-and-textbflay textbfMemory (PM) construction module for dynamic bfStereo matching, dubbed as bftextPPMStereo.<n>Inspired by the two-stage decision-making process in humans, we propose a textbfPick-and-textbflay textbfMemory (PM) construction module for dynamic bfStereo matching, dubbed as bftextPPMStereo.
  arXiv  Detail & Related papers  (2025-10-23T03:52:39Z)
• ATTS: Asynchronous Test-Time Scaling via Conformal Prediction [112.54016379556073]
  Large language models (LLMs) benefit from test-time scaling but are often hampered by high inference latency.<n>We introduce ATTS (Asynchronous Test-Time Scaling), a statistically guaranteed adaptive scaling framework.<n>We show that ATTS delivers up to 56.7x speedup in test-time scaling and a 4.14x throughput improvement.
  arXiv  Detail & Related papers  (2025-09-18T16:55:09Z)
• TARO: Timestep-Adaptive Representation Alignment with Onset-Aware Conditioning for Synchronized Video-to-Audio Synthesis [39.58643124601554]
  This paper introduces Timestep-Adaptive Representation Alignment with Onset-Aware Conditioning (TARO), a novel framework for high-fidelity and temporally coherent video-to-audio synthesis.
  arXiv  Detail & Related papers  (2025-04-08T04:49:36Z)
• FUSE: Label-Free Image-Event Joint Monocular Depth Estimation via Frequency-Decoupled Alignment and Degradation-Robust Fusion [92.4205087439928]
  Image-event joint depth estimation methods leverage complementary modalities for robust perception, yet face challenges in generalizability.<n>We propose the Self-supervised Transfer (PST) and the FrequencyDe-coupled Fusion module (FreDF)<n>PST establishes cross-modal knowledge transfer through latent space alignment with image foundation models, effectively mitigating data scarcity.<n>FreDF explicitly decouples high-frequency edge features from low-frequency structural components, resolving modality-specific frequency mismatches.<n>This combined approach enables FUSE to construct a universal image-event that only requires lightweight decoder adaptation for target datasets.
  arXiv  Detail & Related papers  (2025-03-25T15:04:53Z)
• LatentSync: Taming Audio-Conditioned Latent Diffusion Models for Lip Sync with SyncNet Supervision [13.447234794835921]
  We introduce StableSyncNet, with an architecture designed for stable convergence.<n>Our method surpasses state-of-the-art lip-sync approaches across various evaluation metrics on the HDTF and VoxCeleb2 datasets.
  arXiv  Detail & Related papers  (2024-12-12T13:20:52Z)
• Hierarchical Temporal Context Learning for Camera-based Semantic Scene Completion [57.232688209606515]
  We present HTCL, a novel Temporal Temporal Context Learning paradigm for improving camera-based semantic scene completion. Our method ranks $1st$ on the Semantic KITTI benchmark and even surpasses LiDAR-based methods in terms of mIoU.
  arXiv  Detail & Related papers  (2024-07-02T09:11:17Z)
• Binarized Diffusion Model for Image Super-Resolution [61.963833405167875]
  Binarization, an ultra-compression algorithm, offers the potential for effectively accelerating advanced diffusion models (DMs) Existing binarization methods result in significant performance degradation. We introduce a novel binarized diffusion model, BI-DiffSR, for image SR.
  arXiv  Detail & Related papers  (2024-06-09T10:30:25Z)
• Match-Stereo-Videos: Bidirectional Alignment for Consistent Dynamic Stereo Matching [17.344430840048094]
  Recent learning-based methods prioritize optimal performance on a single stereo pair, resulting in temporal inconsistencies. We develop a bidirectional alignment mechanism for adjacent frames as a fundamental operation. Unlike the existing methods, we model this task as local matching and global aggregation.
  arXiv  Detail & Related papers  (2024-03-16T01:38:28Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.