Post-Hoc Guidance for Consistency Models by Joint Flow Distribution Learning

• URL: http://arxiv.org/abs/2604.08828v1
• Date: Fri, 10 Apr 2026 00:00:08 GMT
• Title: Post-Hoc Guidance for Consistency Models by Joint Flow Distribution Learning
• Abstract summary: Diffusion-free Guidance (CFG) lets practitioners trade-off fidelity against diversity in Diffusion Models (DMs)<n>Existing guidance methods require knowledge distillation from a separate DM teacher.<n>We propose Joint Flow Distribution Learning (JFDL), a lightweight alignment method enabling guidance in a pre-trained CM.
• Score: 19.252159895953977
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Classifier-free Guidance (CFG) lets practitioners trade-off fidelity against diversity in Diffusion Models (DMs). The practicality of CFG is however hindered by DMs sampling cost. On the other hand, Consistency Models (CMs) generate images in one or a few steps, but existing guidance methods require knowledge distillation from a separate DM teacher, limiting CFG to Consistency Distillation (CD) methods. We propose Joint Flow Distribution Learning (JFDL), a lightweight alignment method enabling guidance in a pre-trained CM. With a pre-trained CM as an ordinary differential equation (ODE) solver, we verify with normality tests that the variance-exploding noise implied by the velocity fields from unconditional and conditional distributions is Gaussian. In practice, JFDL equips CMs with the familiar adjustable guidance knob, yielding guided images with similar characteristics to CFG. Applied to an original Consistency Trained (CT) CM that could only do conditional sampling, JFDL unlocks guided generation and reduces FID on both CIFAR-10 and ImageNet 64x64 datasets. This is the first time that CMs are able to receive effective guidance post-hoc without a DM teacher, thus, bridging a key gap in current methods for CMs.

Related papers

• Decoupled DMD: CFG Augmentation as the Spear, Distribution Matching as the Shield [54.328202401611264]
  Diffusion model distillation has emerged as a powerful technique for creating efficient few-step and single-step generators.<n>We show that the primary driver of few-step distillation is not distribution matching, but a previously overlooked component we identify as CFG Augmentation (CA)<n>We propose principled modifications to the distillation process, such as decoupling the noise schedules for the engine and the regularizer, leading to further performance gains.
  arXiv  Detail & Related papers  (2025-11-27T18:24:28Z)
• Align Your Tangent: Training Better Consistency Models via Manifold-Aligned Tangents [55.43139356528315]
  Consistency Models (CMs) are trained to be consistent on flow ordinary differential equation trajectories.<n>CMs typically require prolonged training with large batch sizes to obtain competitive sample quality.<n>We propose a new loss function, called the manifold feature distance (MFD), which provides manifold-aligned tangents that point toward the data manifold.
  arXiv  Detail & Related papers  (2025-10-01T08:35:18Z)
• Token Perturbation Guidance for Diffusion Models [6.255435016547602]
  Token Perturbation Guidance (TPG) is a novel method that applies matrices directly to intermediate token representations within the diffusion network.<n>TPG is training-free and agnostic to input conditions, making it readily applicable to both conditional and unconditional generation.
  arXiv  Detail & Related papers  (2025-06-10T21:25:46Z)
• Adding Additional Control to One-Step Diffusion with Joint Distribution Matching [58.37264951734603]
  JDM is a novel approach that minimizes the reverse KL divergence between image-condition joint distributions.<n>By deriving a tractable upper bound, JDM decouples fidelity learning from condition learning.<n>This asymmetric distillation scheme enables our one-step student to handle controls unknown to the teacher model.
  arXiv  Detail & Related papers  (2025-03-09T15:06:50Z)
• Beyond and Free from Diffusion: Invertible Guided Consistency Training [12.277762115388187]
  iGCT contributes to fast and guided image generation and editing without requiring the training and distillation of DMs.<n>Our experiments on CIFAR-10 and ImageNet64 show that iGCT significantly improves FID and precision compared to CFG.
  arXiv  Detail & Related papers  (2025-02-08T00:23:40Z)
• Rectified Diffusion Guidance for Conditional Generation [94.83538269086613]
  We revisit the theory behind CFG and rigorously confirm that the improper combination coefficients (textiti.e.) brings about expectation shift the generative distribution.<n>We show that our approach enjoys a textbftextitform solution given the strength.<n> Empirical evidence on real-world data demonstrate the compatibility of our design with existing state-of-the-art diffusion models.
  arXiv  Detail & Related papers  (2024-10-24T13:41:32Z)
• No Training, No Problem: Rethinking Classifier-Free Guidance for Diffusion Models [25.301443993960277]
  We revisit the core principles of CFG and introduce a new method, independent condition guidance (ICG)<n>ICG provides the benefits of CFG without the need for any special training procedures.<n>Our approach streamlines the training process of conditional diffusion models and can also be applied during inference on any pre-trained conditional model.
  arXiv  Detail & Related papers  (2024-07-02T22:04:00Z)
• CCM: Adding Conditional Controls to Text-to-Image Consistency Models [89.75377958996305]
  We consider alternative strategies for adding ControlNet-like conditional control to Consistency Models. A lightweight adapter can be jointly optimized under multiple conditions through Consistency Training. We study these three solutions across various conditional controls, including edge, depth, human pose, low-resolution image and masked image.
  arXiv  Detail & Related papers  (2023-12-12T04:16:03Z)
• On Reinforcement Learning and Distribution Matching for Fine-Tuning Language Models with no Catastrophic Forgetting [5.5302127686575435]
  Two main paradigms have emerged to tackle this challenge: Reward Maximization (RM) and, more recently, Distribution Matching (DM) We show that methods such as KL-control developed for RM can also be construed as belonging to DM. We leverage connections between the two paradigms to import the concept of baseline into DM methods.
  arXiv  Detail & Related papers  (2022-06-01T20:54:41Z)
• MMCGAN: Generative Adversarial Network with Explicit Manifold Prior [78.58159882218378]
  We propose to employ explicit manifold learning as prior to alleviate mode collapse and stabilize training of GAN. Our experiments on both the toy data and real datasets show the effectiveness of MMCGAN in alleviating mode collapse, stabilizing training, and improving the quality of generated samples.
  arXiv  Detail & Related papers  (2020-06-18T07:38:54Z)

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.