Pith. sign in

REVIEW 6 cited by

Diffusion Models without Classifier-free Guidance

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

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 2502.12154 v1 pith:P6XL4SEV submitted 2025-02-17 cs.CV cs.AIcs.LG

Zhicong Tang , Jianmin Bao , Dong Chen , Baining Guo This is my paper
classification cs.CVcs.AIcs.LG
keywords modelsdiffusionclassifier-freeguidancetrainingacceleratesachieveaddresses
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

This paper presents Model-guidance (MG), a novel objective for training diffusion model that addresses and removes of the commonly used Classifier-free guidance (CFG). Our innovative approach transcends the standard modeling of solely data distribution to incorporating the posterior probability of conditions. The proposed technique originates from the idea of CFG and is easy yet effective, making it a plug-and-play module for existing models. Our method significantly accelerates the training process, doubles the inference speed, and achieve exceptional quality that parallel and even surpass concurrent diffusion models with CFG. Extensive experiments demonstrate the effectiveness, efficiency, scalability on different models and datasets. Finally, we establish state-of-the-art performance on ImageNet 256 benchmarks with an FID of 1.34. Our code is available at https://github.com/tzco/Diffusion-wo-CFG.

Discussion (0). Sign in to comment.

Forward citations

Cited by 6 Pith papers

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

  1. Coupled Continuous-Discrete Generation for Scene Text Image Super-Resolution

    cs.CV 2026-08 conditional novelty 6.0 of 10

    A shared transformer trained with continuous flow matching for images and discrete diffusion for text jointly restores scene text images and reads out their characters, removing the external OCR prior.

  2. Transition Models: Rethinking the Generative Learning Objective

    cs.LG 2025-09 conditional novelty 6.0 of 10

    TiM trains a single diffusion-type model on arbitrary time-interval transitions, achieving strong one-step and multi-step text-to-image generation with 865M parameters.

  3. TeEFusion: Blending Text Embeddings to Distill Classifier-Free Guidance

    cs.CV 2025-07 conditional novelty 6.0 of 10

    TeEFusion distills classifier-free guidance into text embeddings via linear fusion, enabling a student model to generate images in one forward pass instead of two.

  4. A Minimalist Method for Fine-tuning Text-to-Image Diffusion Models

    cs.LG 2025-05 conditional novelty 6.0 of 10

    A one-step RL method learns a prompt-conditioned initial noise distribution for a frozen diffusion model, improving scores on the training reward models, with the largest gains at low inference steps.

  5. CMuon: Accelerating and Stabilizing Diffusion Transformer Training via Chunked Momentum Orthogonalization

    cs.AI 2026-08 conditional novelty 5.0 of 10

    Chunked Muon, which orthogonalizes fused DiT weight matrices per functional block instead of jointly, reaches FID 1.18 on ImageNet 256 in 200 epochs, about 2× faster than AdamW.

  6. DiffTopo: Solver in the Loop for Inverse Topography via Condition Diffusion Generation

    physics.ao-ph 2025-08 conditional novelty 5.0 of 10

    DiffTopo reconstructs seabed topography from synthetic wave fields using conditional diffusion with classifier-free guidance and a solver-based residual filter.

Pith tools