paper-with-me

Papers

Self-Corrected Flow Distillation for Consistent One-Step and Few-Step Text-to-Image Generation

2024-12-22 · Quan Dao, Hao Phung, Trung Dao, Dimitris Metaxas, Anh Tran

Flow matching has emerged as a promising framework for training generative models, demonstrating impressive empirical performance while offering relative ease of training compared to diffusion-based models. However, this method still requires numerous function evaluations in the sampling process. To address these limitations, we introduce a self-corrected flow distillation method that effectively integrates consistency models and adversarial training within the flow-matching framework. This work is a pioneer in achieving consistent generation quality in both few-step and one-step sampling. Our extensive experiments validate the effectiveness of our method, yielding superior results both quantitatively and qualitatively on CelebA-HQ and zero-shot benchmarks on the COCO dataset. Our implementation is released at https://github.com/VinAIResearch/SCFlow

📄 PDF Abstract BibTeX arXiv:2412.16906

Code (0)

등록된 구현이 없습니다.

Tasks

Image GenerationText to Image GenerationText-to-Image Generation

Methods 이 논문이 사용한 방법론

Consistency Models 설명 없음

Similar Papers 제목 키워드 기반

TraFlow: Trajectory Distillation on Pre-Trained Rectified Flow

2025-02-24 · Zhangkai Wu, Xuhui Fan, Hongyu Wu, Longbing Cao

Majorities of distillation methods on pre-trained diffusion models or on pre-trained rectified flow, focus on either the distillation outputs or the trajectories between random noises and clean images to speed up sample …

Shortcutting Pre-trained Flow Matching Diffusion Models is Almost Free Lunch

2025-10-15 · Xu Cai, Yang Wu, Qianli Chen, Haoran Wu 외 arxiv

We present an ultra-efficient post-training method for shortcutting large-scale pre-trained flow matching diffusion models into efficient few-step samplers, enabled by novel velocity field self-distillation. While shortc…

CAB: Accelerating Flow and Diffusion Sampling via Rectification and Corrected Adams-Bashforth

2026-05-16 · Anuska Roy, Pravin Nair arxiv

Flow and diffusion models achieve high-fidelity, high-resolution image synthesis, but often require many function evaluations (NFEs) at sampling time. Existing acceleration methods either require additional training thro…

FlashRender: Few-Step Generative Rendering via Camera-Controlled Video MeanFlow

2026-09-03 · Byeongjun Park, Byung-Hoon Kim, Hyungjin Chung hf

We present FlashRender, a few-step generative rendering framework that retakes a source video along a target camera trajectory in seconds. We identify sampling-step-dependent camera control as a prominent manifestation o…

Self-conditioned Flow Map Language Models via Fixed-point Flows

2026-07-01 · Jaehoon Yoo, Wonjung Kim, Floor Eijkelboom, Chanhyuk Lee 외 arxiv

Self-conditioning is a core technique that enhances continuous flow-based language models, where the model learns to denoise generated text by conditioning on its own denoising estimate. While empirically successful, its…