Pith. sign in

REVIEW 19 cited by

CFG++: Manifold-constrained Classifier Free Guidance for Diffusion 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

arxiv 2406.08070 v2 pith:EU4SD4MM submitted 2024-06-12 cs.CV cs.AIcs.LG

CFG++: Manifold-constrained Classifier Free Guidance for Diffusion Models

classification cs.CV cs.AIcs.LG
keywords diffusionguidancemodelsscalesgenerationinversecollapseddim
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Classifier-free guidance (CFG) is a fundamental tool in modern diffusion models for text-guided generation. Although effective, CFG has notable drawbacks. For instance, DDIM with CFG lacks invertibility, complicating image editing; furthermore, high guidance scales, essential for high-quality outputs, frequently result in issues like mode collapse. Contrary to the widespread belief that these are inherent limitations of diffusion models, this paper reveals that the problems actually stem from the off-manifold phenomenon associated with CFG, rather than the diffusion models themselves. More specifically, inspired by the recent advancements of diffusion model-based inverse problem solvers (DIS), we reformulate text-guidance as an inverse problem with a text-conditioned score matching loss and develop CFG++, a novel approach that tackles the off-manifold challenges inherent in traditional CFG. CFG++ features a surprisingly simple fix to CFG, yet it offers significant improvements, including better sample quality for text-to-image generation, invertibility, smaller guidance scales, reduced mode collapse, etc. Furthermore, CFG++ enables seamless interpolation between unconditional and conditional sampling at lower guidance scales, consistently outperforming traditional CFG at all scales. Moreover, CFG++ can be easily integrated into high-order diffusion solvers and naturally extends to distilled diffusion models. Experimental results confirm that our method significantly enhances performance in text-to-image generation, DDIM inversion, editing, and solving inverse problems, suggesting a wide-ranging impact and potential applications in various fields that utilize text guidance. Project Page: https://cfgpp-diffusion.github.io/.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 19 Pith papers

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

  1. Guidance Breaks the Fitted Operator: A Terminal-Fitted Repair for Classifier-Free Guidance

    cs.LG 2026-07 conditional novelty 7.0

    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.

  2. Live Music Diffusion Models: Efficient Fine-Tuning and Post-Training of Interactive Diffusion Music Generators

    cs.SD 2026-05 unverdicted novelty 7.0

    Live Music Diffusion Models adapt bidirectional diffusion for interactive music generation via KV caching and ARC-Forcing, recovering and exceeding discrete autoregressive efficiency while enabling post-training align...

  3. Probability-Conserving Flow Guidance

    cs.CV 2026-05 unverdicted novelty 7.0

    AdaMaG is a guidance rule for generative models derived from decomposing continuity-equation effects into divergence and score-parallel terms, with a proof that divergence diverges near the manifold and a time-depende...

  4. DCR: Counterfactual Attractor Guidance for Rare Compositional Generation

    cs.CV 2026-05 unverdicted novelty 7.0

    DCR uses a counterfactual attractor and projection-based repulsion to suppress default completion bias in diffusion models, improving fidelity for rare compositional prompts while preserving quality.

  5. GeoEdit: Local Frames for Fast, Training-Free On-Manifold Editing in Diffusion Models

    cs.LG 2026-04 unverdicted novelty 7.0

    GeoEdit constructs local tangent frames from small perturbations to initial noise, enabling Jacobian-free on-manifold edits in diffusion models via alternating tangent steps and diffusion projections.

  6. $Z^2$-Sampling: Zero-Cost Zigzag Trajectories for Semantic Alignment in Diffusion Models

    cs.CV 2026-04 unverdicted novelty 7.0

    Z²-Sampling implicitly realizes zero-cost zigzag trajectories for curvature-aware semantic alignment in diffusion models by reducing multi-step paths via operator dualities and temporal caching while synthesizing a di...

  7. Reflective Flow Sampling Enhancement

    cs.CV 2026-03 unverdicted novelty 7.0

    RF-Sampling enhances flow matching models by implicitly performing gradient ascent on text-image alignment scores via linear textual combinations and flow inversion.

  8. It's Never Too Late: Noise Optimization for Collapse Recovery in Trained Diffusion Models

    cs.CV 2025-12 unverdicted novelty 7.0

    Noise optimization during sampling recovers diversity in mode-collapsed diffusion models while preserving output fidelity.

  9. Factored Classifier-Free Guidance

    cs.CV 2025-06 unverdicted novelty 7.0

    Factored Classifier-Free Guidance enables per-attribute control in classifier-free guidance for diffusion models to produce more sound counterfactuals.

  10. TPD: Temporal Prior Decoupling for Text-to-Video Diffusion Models

    cs.CV 2026-07 conditional novelty 6.5

    TPD restores suppressed late-segment events in text-to-video diffusion by projecting classifier-free guidance onto a frame- and timestep-selective lower bound along a temporal-counterfactual direction.

  11. Frequency-Guided Action Diffusion via Sub-Frequency Manifold Traversal

    cs.RO 2026-05 unverdicted novelty 6.0

    FGO guides diffusion policy generation via expanding spectral bands on sub-frequency manifolds to improve action smoothness on 15 robotic manipulation tasks.

  12. P-Guide: Parameter-Efficient Prior Steering for Single-Pass CFG Inference

    cs.AI 2026-05 unverdicted novelty 6.0

    P-Guide achieves single-pass classifier-free guidance in flow matching by modulating the initial latent state and is equivalent to standard CFG under a first-order approximation while cutting latency by half.

  13. Delta Score Matters! Spatial Adaptive Multi Guidance in Diffusion Models

    cs.CV 2026-04 unverdicted novelty 6.0

    SAMG uses spatially adaptive guidance scales derived from a geometric analysis of classifier-free guidance to resolve the detail-artifact dilemma in diffusion-based image and video generation.

  14. Synthesis of discrete-continuous quantum circuits with multimodal diffusion models

    quant-ph 2025-06 unverdicted novelty 6.0

    Multimodal diffusion model generates discrete gate selections and continuous parameters for quantum circuit compilation, claiming better gate counts and noise resilience than prior methods.

  15. Awakening Diffusion Transformers: Eliciting Stronger Generation and Understanding via Massive Activation Modulation

    cs.CV 2026-07 conditional novelty 5.0

    Massive activations in DiTs are timestep-driven detail channels; suppressing them guides finer sampling and AdaLN-modulating them yields more discriminative dense features.

  16. Embedding-perturbed Exploration Preference Optimization for Flow Models

    cs.CV 2026-05 unverdicted novelty 5.0

    E²PO uses embedding-level perturbations to maintain intra-group variance and discriminative signal in RL-based preference optimization for generative flow models.

  17. Exploring Time Conditioning in Diffusion Generative Models from Disjoint Noisy Data Manifolds

    cs.LG 2026-04 unverdicted novelty 5.0

    Aligning the DDIM forward diffusion process with flow-matching manifold evolution enables high-quality generation without time conditioning, and class-conditional synthesis is possible with an unconditional denoiser b...

  18. Exploring Motion-Language Alignment for Text-driven Motion Generation

    cs.CV 2026-04 unverdicted novelty 5.0

    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.

  19. PureCC: Pure Learning for Text-to-Image Concept Customization

    cs.CV 2026-03 unverdicted novelty 5.0

    PureCC introduces a decoupled learning objective, dual-branch training pipeline with frozen extractor, and adaptive guidance scale λ* for high-fidelity concept customization while preserving original model behavior in...