Advancing End-to-End Pixel Space Generative Modeling via Self-supervised Pre-training

• URL: http://arxiv.org/abs/2510.12586v1
• Date: Tue, 14 Oct 2025 14:41:16 GMT
• Title: Advancing End-to-End Pixel Space Generative Modeling via Self-supervised Pre-training
• Authors: Jiachen Lei, Keli Liu, Julius Berner, Haiming Yu, Hongkai Zheng, Jiahong Wu, Xiangxiang Chu,
• Abstract summary: We introduce a novel two-stage training framework for pixel-space diffusion and consistency models.<n>Our training framework demonstrates strong empirical performance on ImageNet dataset.<n>To the best of our knowledge, this marks the first successful training of a consistency model directly on high-resolution images.
• Score: 23.632047555553324
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Pixel-space generative models are often more difficult to train and generally underperform compared to their latent-space counterparts, leaving a persistent performance and efficiency gap. In this paper, we introduce a novel two-stage training framework that closes this gap for pixel-space diffusion and consistency models. In the first stage, we pre-train encoders to capture meaningful semantics from clean images while aligning them with points along the same deterministic sampling trajectory, which evolves points from the prior to the data distribution. In the second stage, we integrate the encoder with a randomly initialized decoder and fine-tune the complete model end-to-end for both diffusion and consistency models. Our training framework demonstrates strong empirical performance on ImageNet dataset. Specifically, our diffusion model reaches an FID of 2.04 on ImageNet-256 and 2.35 on ImageNet-512 with 75 number of function evaluations (NFE), surpassing prior pixel-space methods by a large margin in both generation quality and efficiency while rivaling leading VAE-based models at comparable training cost. Furthermore, on ImageNet-256, our consistency model achieves an impressive FID of 8.82 in a single sampling step, significantly surpassing its latent-space counterpart. To the best of our knowledge, this marks the first successful training of a consistency model directly on high-resolution images without relying on pre-trained VAEs or diffusion models.

Related papers

• Scaling Text-to-Image Diffusion Transformers with Representation Autoencoders [74.72147962028265]
  Representation Autoencoders (RAEs) have shown distinct advantages in diffusion modeling on ImageNet.<n>We investigate whether this framework can scale to large-scale, freeform text-to-image (T2I) generation.
  arXiv  Detail & Related papers  (2026-01-22T18:58:16Z)
• One Layer Is Enough: Adapting Pretrained Visual Encoders for Image Generation [33.56782043207013]
  Feature Auto-Encoder (FAE) adapts pre-trained visual representations into low-dimensional latents suitable for generation using as little as a single attention layer.<n>FAE achieves strong performance across class-conditional and text-to-image benchmarks.
  arXiv  Detail & Related papers  (2025-12-08T18:57:26Z)
• Learning Diffusion Models with Flexible Representation Guidance [49.26046407886349]
  We present a systematic framework for incorporating representation guidance into diffusion models.<n>We introduce two new strategies for enhancing representation alignment in diffusion models.<n>Experiments across image, protein sequence, and molecule generation tasks demonstrate superior performance as well as accelerated training.
  arXiv  Detail & Related papers  (2025-07-11T19:29:02Z)
• D2C: Unlocking the Potential of Continuous Autoregressive Image Generation with Discrete Tokens [80.75893450536577]
  We propose D2C, a novel two-stage method to enhance model generation capacity.<n>In the first stage, the discrete-valued tokens representing coarse-grained image features are sampled by employing a small discrete-valued generator.<n>In the second stage, the continuous-valued tokens representing fine-grained image features are learned conditioned on the discrete token sequence.
  arXiv  Detail & Related papers  (2025-03-21T13:58:49Z)
• Diffusion Models without Classifier-free Guidance [41.59396565229466]
  Model-guidance (MG) is a novel objective for training diffusion model addresses and removes commonly used guidance (CFG)<n>Our innovative approach transcends the standard modeling and incorporates the posterior probability of conditions.<n>Our method significantly accelerates the training process, doubles inference speed, and achieve exceptional quality that parallel surpass even concurrent diffusion models with CFG.
  arXiv  Detail & Related papers  (2025-02-17T18:59:50Z)
• Reconstruction vs. Generation: Taming Optimization Dilemma in Latent Diffusion Models [33.519892081718716]
  We propose aligning the latent space with pre-trained vision foundation models when training the visual tokenizers.<n>Our proposed VA-VAE significantly expands the reconstruction-generation frontier of latent diffusion models.<n>We build an enhanced DiT baseline with improved training strategies and architecture designs, termed LightningDiT.
  arXiv  Detail & Related papers  (2025-01-02T18:59:40Z)
• OFTSR: One-Step Flow for Image Super-Resolution with Tunable Fidelity-Realism Trade-offs [24.046764908874703]
  OFTSR is a flow-based framework for one-step image super-resolution that can produce outputs with tunable levels of fidelity and realism.<n>We demonstrate that OFTSR achieves state-of-the-art performance for one-step image super-resolution, while having the ability to flexibly tune the fidelity-realism trade-off.
  arXiv  Detail & Related papers  (2024-12-12T17:14:58Z)
• Diffusion Models Need Visual Priors for Image Generation [86.92260591389818]
  Diffusion on Diffusion (DoD) is an innovative multi-stage generation framework that first extracts visual priors from previously generated samples, then provides rich guidance for the diffusion model. We evaluate DoD on the popular ImageNet-$256 times 256$ dataset, reducing 7$times$ training cost compared to SiT and DiT. Our largest model DoD-XL achieves an FID-50K score of 1.83 with only 1 million training steps, which surpasses other state-of-the-art methods without bells and whistles during inference.
  arXiv  Detail & Related papers  (2024-10-11T05:03:56Z)
• Masked Diffusion Models Are Fast Distribution Learners [32.485235866596064]
  Diffusion models are commonly trained to learn all fine-grained visual information from scratch. We show that it suffices to train a strong diffusion model by first pre-training the model to learn some primer distribution. Then the pre-trained model can be fine-tuned for various generation tasks efficiently.
  arXiv  Detail & Related papers  (2023-06-20T08:02:59Z)
• Consistency Models [89.68380014789861]
  We propose a new family of models that generate high quality samples by directly mapping noise to data. They support fast one-step generation by design, while still allowing multistep sampling to trade compute for sample quality. They also support zero-shot data editing, such as image inpainting, colorization, and super-resolution, without requiring explicit training.
  arXiv  Detail & Related papers  (2023-03-02T18:30:16Z)
• On Distillation of Guided Diffusion Models [94.95228078141626]
  We propose an approach to distilling classifier-free guided diffusion models into models that are fast to sample from. For standard diffusion models trained on the pixelspace, our approach is able to generate images visually comparable to that of the original model. For diffusion models trained on the latent-space (e.g., Stable Diffusion), our approach is able to generate high-fidelity images using as few as 1 to 4 denoising steps.
  arXiv  Detail & Related papers  (2022-10-06T18:03:56Z)
• P2P: Tuning Pre-trained Image Models for Point Cloud Analysis with Point-to-Pixel Prompting [94.11915008006483]
  We propose a novel Point-to-Pixel prompting for point cloud analysis. Our method attains 89.3% accuracy on the hardest setting of ScanObjectNN. Our framework also exhibits very competitive performance on ModelNet classification and ShapeNet Part Code.
  arXiv  Detail & Related papers  (2022-08-04T17:59:03Z)

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.