REVIEW 12 cited by
CFG-Zero*: Improved Classifier-Free Guidance for Flow Matching Models
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
CFG-Zero*: Improved Classifier-Free Guidance for Flow Matching Models
read the original abstract
Classifier-Free Guidance (CFG) is a widely adopted technique in diffusion/flow models to improve image fidelity and controllability. In this work, we first analytically study the effect of CFG on flow matching models trained on Gaussian mixtures where the ground-truth flow can be derived. We observe that in the early stages of training, when the flow estimation is inaccurate, CFG directs samples toward incorrect trajectories. Building on this observation, we propose CFG-Zero*, an improved CFG with two contributions: (a) optimized scale, where a scalar is optimized to correct for the inaccuracies in the estimated velocity, hence the * in the name; and (b) zero-init, which involves zeroing out the first few steps of the ODE solver. Experiments on both text-to-image (Lumina-Next, Stable Diffusion 3, and Flux) and text-to-video (Wan-2.1) generation demonstrate that CFG-Zero* consistently outperforms CFG, highlighting its effectiveness in guiding Flow Matching models. (Code is available at github.com/WeichenFan/CFG-Zero-star)
Forward citations
Cited by 12 Pith papers
-
Guidance Breaks the Fitted Operator: A Terminal-Fitted Repair for Classifier-Free Guidance
Replacing CFG's w(r-1) coefficient with r^(1+w)-r removes a sigma_min-divergent residual blow-up on a Gaussian calibration model and stabilizes high-guidance diffusion sampling at zero extra NFE.
-
Reflective Flow Sampling Enhancement
RF-Sampling enhances flow matching models by implicitly performing gradient ascent on text-image alignment scores via linear textual combinations and flow inversion.
-
Probabilistic Inversion with Flow Matching
Adapts Flow Matching from generative AI to probabilistic inversion, evaluated on a simple 2D velocity model and the OpenFWI seismic dataset.
-
SpecLoR: Spectral Lookahead Rectification for Motion-Coherent Text-to-Video Generation
SpecLoR rectifies the amplitude spectrum of lookahead-estimated clean latents to natural-video priors during early ODE sampling steps, cutting physical artifacts with only four extra NFEs.
-
VAGS: Velocity Adaptive Guidance Scale for Image Editing and Generation
VAGS adapts the CFG scale at each ODE step using velocity alignment signals to raise structural fidelity in editing and sample quality in generation over fixed-scale baselines.
-
GenMed: A Pairwise Generative Reformulation of Medical Diagnostic Tasks
GenMed uses diffusion models to capture P(X,Y) for medical tasks and performs inference via gradient-based test-time optimization, supporting arbitrary observation combinations without retraining.
-
Self-Refining Video Sampling
Self-refining video sampling treats a pre-trained generator as a denoising autoencoder for iterative inference-time refinement guided by self-consistency uncertainty to improve motion coherence and physics alignment.
-
ModaFlow: Modality-Aware Flow Matching for High-Fidelity Virtual Try-On
ModaFlow is a modality-aware flow matching framework for virtual try-on that uses visual embeddings for structural guidance, text embeddings with adaptive CFG, regularization losses, and stochastic mask sampling to ac...
-
VoxCPM2 Technical Report
VoxCPM2 scales hierarchical continuous-latent speech modeling to 2B parameters and over 2M hours of multilingual data, unifying voice cloning, style control, and continuation in one backbone with open release.
-
AssetGen: Deployable 3D Asset Generation at Interactive Speed
AssetGen is a system that produces deployable 3D assets including meshes, baked normals, and textures from a single reference image in under 30 seconds via a coarse-to-refine VecSet pipeline and co-designed optimizations.
-
Exploring Motion-Language Alignment for Text-driven Motion Generation
MLA-Gen advances text-driven motion synthesis by aligning global motion patterns with fine-grained text semantics and mitigating attention sink effects via new masking techniques.
-
Text-to-Image Generative AI for Modeling and Simulation: Methods, Opportunities, and Applications
A tutorial on applying text-to-image generative AI to support conceptual model communication, simulation visualization, education, and multi-scale model interfacing in modeling and simulation.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.