Pith. sign in

REVIEW 5 cited by

FreeDoM: Training-Free Energy-Guided Conditional Diffusion Model

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2303.09833 v1 pith:MG5EI6XG submitted 2023-03-17 cs.CV

classification cs.CV
keywords conditionsdiffusionfreedomconditionaltraining-freemodelmodelsvarious
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Recently, conditional diffusion models have gained popularity in numerous applications due to their exceptional generation ability. However, many existing methods are training-required. They need to train a time-dependent classifier or a condition-dependent score estimator, which increases the cost of constructing conditional diffusion models and is inconvenient to transfer across different conditions. Some current works aim to overcome this limitation by proposing training-free solutions, but most can only be applied to a specific category of tasks and not to more general conditions. In this work, we propose a training-Free conditional Diffusion Model (FreeDoM) used for various conditions. Specifically, we leverage off-the-shelf pre-trained networks, such as a face detection model, to construct time-independent energy functions, which guide the generation process without requiring training. Furthermore, because the construction of the energy function is very flexible and adaptable to various conditions, our proposed FreeDoM has a broader range of applications than existing training-free methods. FreeDoM is advantageous in its simplicity, effectiveness, and low cost. Experiments demonstrate that FreeDoM is effective for various conditions and suitable for diffusion models of diverse data domains, including image and latent code domains.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Rethinking Diffusion Posterior Sampling: From Conditional Score Estimator to Maximizing a Posterior

    cs.CV 2025-01 conditional novelty 6.0 of 10

    The paper provides evidence that Diffusion Posterior Sampling implicitly maximizes a posterior rather than sampling the posterior, and uses this to build faster, better-performing restoration algorithms.

  2. Seismic Acoustic Impedance Inversion Framework Based on Conditional Latent Generative Diffusion Model

    cs.LG 2025-06 conditional novelty 5.0 of 10

    A conditional latent diffusion model with a wavelet projection module and model-driven sampling performs fast seismic acoustic impedance inversion, with higher well-log correlation than supervised, unsupervised, and t...

  3. Incorporating Inductive Biases to Energy-based Generative Models

    cs.LG 2025-05 conditional novelty 5.0 of 10

    Augmenting a neural energy-based model with a linear statistic term that encodes known data properties improves generation quality on molecules, digits, and point clouds.

  4. Random Sampling for Diffusion-based Adversarial Purification

    cs.CV 2024-11 conditional novelty 5.0 of 10

    A maximally random variant of DDIM sampling, combined with guidance applied to the predicted clean image, yields a diffusion purification defense (DiffAP) that outperforms prior methods on CIFAR-10.

  5. Test-time Conditional Text-to-Image Synthesis Using Diffusion Models

    cs.CV 2024-11 conditional novelty 5.0 of 10

    TINTIN conditions Stable Diffusion outputs at test time on color palettes and edge maps by backpropagating losses between decoded images and the condition through the denoising steps.

Pith tools