Improving Controllable Generation: Faster Training and Better Performance via $x_0$-Supervision

• URL: http://arxiv.org/abs/2604.05761v1
• Date: Tue, 07 Apr 2026 12:04:43 GMT
• Title: Improving Controllable Generation: Faster Training and Better Performance via $x_0$-Supervision
• Abstract summary: Controllable generation methods augment the initial T2I model with additional conditions that more easily describe the scene.<n>We show that direct supervision on the clean target image, dubbed $x_0$-supervision, or an equivalent re-weighting of the diffusion loss, yields faster convergence.
• Score: 27.540734730362725
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Text-to-Image (T2I) diffusion/flow models have recently achieved remarkable progress in visual fidelity and text alignment. However, they remain limited when users need to precisely control image layouts, something that natural language alone cannot reliably express. Controllable generation methods augment the initial T2I model with additional conditions that more easily describe the scene. Prior works straightforwardly train the augmented network with the same loss as the initial network. Although natural at first glance, this can lead to very long training times in some cases before convergence. In this work, we revisit the training objective of controllable diffusion models through a detailed analysis of their denoising dynamics. We show that direct supervision on the clean target image, dubbed $x_0$-supervision, or an equivalent re-weighting of the diffusion loss, yields faster convergence. Experiments on multiple control settings demonstrate that our formulation accelerates convergence by up to 2$\times$ according to our novel metric (mean Area Under the Convergence Curve - mAUCC), while also improving both visual quality and conditioning accuracy. Our code is available at https://github.com/CEA-LIST/x0-supervision

Related papers

• Optimal Control Meets Flow Matching: A Principled Route to Multi-Subject Fidelity [35.95129874095729]
  Text-to-image (T2I) models excel on single-entity prompts but struggle with multi-subject descriptions.<n>We introduce the first theoretical framework with principled optimizable objective for steering sampling dynamics toward multi-subject fidelity.
  arXiv  Detail & Related papers  (2025-10-02T17:59:58Z)
• DivControl: Knowledge Diversion for Controllable Image Generation [38.166949036830886]
  DivControl is a decomposable pretraining framework for unified controllable generation.<n>It achieves state-of-the-art controllability with 36.4$times$ less training cost.<n>It also delivers strong zero-shot and few-shot performance on unseen conditions.
  arXiv  Detail & Related papers  (2025-07-31T15:00:15Z)
• Representation Entanglement for Generation: Training Diffusion Transformers Is Much Easier Than You Think [63.25744258438214]
  REPA and its variants effectively mitigate training challenges in diffusion models by incorporating external visual representations from pretrained models.<n>We argue that the external alignment, which is absent during the entire denoising inference process, falls short of fully harnessing the potential of discriminative representations.<n>We propose Representation Entanglement for Generation (REG), which entangles low-level image latents with a single high-level class token from pretrained foundation models for denoising.
  arXiv  Detail & Related papers  (2025-07-02T08:29:18Z)
• REPA Works Until It Doesn't: Early-Stopped, Holistic Alignment Supercharges Diffusion Training [58.33728862521732]
  Diffusion Transformers (DiTs) deliver state-of-the-art image quality, yet their training remains notoriously slow.<n>A recent remedy -- representation alignment (REPA) that matches DiT hidden features to those of a non-generative teacher (e.g. DINO) -- dramatically accelerates the early epochs but plateaus or even degrades performance later.<n>We trace this failure to a capacity mismatch: once the generative student begins modelling the joint data distribution, the teacher's lower-dimensional embeddings and attention patterns become a straitjacket rather than a guide.<n>We introduce HASTE
  arXiv  Detail & Related papers  (2025-05-22T15:34:33Z)
• Fast constrained sampling in pre-trained diffusion models [80.99262780028015]
  We propose an algorithm that enables fast, high-quality generation under arbitrary constraints.<n>Our approach produces results that rival or surpass the state-of-the-art training-free inference methods.
  arXiv  Detail & Related papers  (2024-10-24T14:52:38Z)
• Truncated Consistency Models [57.50243901368328]
  Training consistency models requires learning to map all intermediate points along PF ODE trajectories to their corresponding endpoints.<n>We empirically find that this training paradigm limits the one-step generation performance of consistency models.<n>We propose a new parameterization of the consistency function and a two-stage training procedure that prevents the truncated-time training from collapsing to a trivial solution.
  arXiv  Detail & Related papers  (2024-10-18T22:38:08Z)
• Rectified Diffusion: Straightness Is Not Your Need in Rectified Flow [65.51671121528858]
  Diffusion models have greatly improved visual generation but are hindered by slow generation speed due to the computationally intensive nature of solving generative ODEs. Rectified flow, a widely recognized solution, improves generation speed by straightening the ODE path. We propose Rectified Diffusion, which generalizes the design space and application scope of rectification to encompass the broader category of diffusion models.
  arXiv  Detail & Related papers  (2024-10-09T17:43:38Z)
• Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think [72.48325960659822]
  One main bottleneck in training large-scale diffusion models for generation lies in effectively learning these representations.<n>We study this by introducing a straightforward regularization called REPresentation Alignment (REPA), which aligns the projections of noisy input hidden states in denoising networks with clean image representations obtained from external, pretrained visual encoders.<n>The results are striking: our simple strategy yields significant improvements in both training efficiency and generation quality when applied to popular diffusion and flow-based transformers, such as DiTs and SiTs.
  arXiv  Detail & Related papers  (2024-10-09T14:34:53Z)
• Identifying and Solving Conditional Image Leakage in Image-to-Video Diffusion Model [31.70050311326183]
  Diffusion models tend to generate videos with less motion than expected. We address this issue from both inference and training aspects. Our methods outperform baselines by producing higher motion scores with lower errors.
  arXiv  Detail & Related papers  (2024-06-22T04:56:16Z)
• One-Step Image Translation with Text-to-Image Models [35.0987002313882]
  We introduce a general method for adapting a single-step diffusion model to new tasks and domains through adversarial learning objectives. We consolidate various modules of the vanilla latent diffusion model into a single end-to-end generator network with small trainable weights. Our model CycleGAN-Turbo outperforms existing GAN-based and diffusion-based methods for various scene translation tasks.
  arXiv  Detail & Related papers  (2024-03-18T17:59:40Z)
• Direct Consistency Optimization for Robust Customization of Text-to-Image Diffusion Models [67.68871360210208]
  Text-to-image (T2I) diffusion models, when fine-tuned on a few personal images, can generate visuals with a high degree of consistency.<n>We propose a novel fine-tuning objective, dubbed Direct Consistency Optimization, which controls the deviation between fine-tuning and pretrained models.<n>We show that our approach achieves better prompt fidelity and subject fidelity than those post-optimized for merging regular fine-tuned models.
  arXiv  Detail & Related papers  (2024-02-19T09:52:41Z)
• DiffBIR: Towards Blind Image Restoration with Generative Diffusion Prior [70.46245698746874]
  We present DiffBIR, a general restoration pipeline that could handle different blind image restoration tasks. DiffBIR decouples blind image restoration problem into two stages: 1) degradation removal: removing image-independent content; 2) information regeneration: generating the lost image content. In the first stage, we use restoration modules to remove degradations and obtain high-fidelity restored results. For the second stage, we propose IRControlNet that leverages the generative ability of latent diffusion models to generate realistic details.
  arXiv  Detail & Related papers  (2023-08-29T07:11:52Z)
• Unleashing Text-to-Image Diffusion Models for Visual Perception [84.41514649568094]
  VPD (Visual Perception with a pre-trained diffusion model) is a new framework that exploits the semantic information of a pre-trained text-to-image diffusion model in visual perception tasks. We show that VPD can be faster adapted to downstream visual perception tasks using the proposed VPD.
  arXiv  Detail & Related papers  (2023-03-03T18:59:47Z)

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.