REVIEW 6 cited by
Steering Rectified Flow Models in the Vector Field for Controlled Image Generation
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
read the original abstract
Diffusion models (DMs) excel in photorealism, image editing, and solving inverse problems, aided by classifier-free guidance and image inversion techniques. However, rectified flow models (RFMs) remain underexplored for these tasks. Existing DM-based methods often require additional training, lack generalization to pretrained latent models, underperform, and demand significant computational resources due to extensive backpropagation through ODE solvers and inversion processes. In this work, we first develop a theoretical and empirical understanding of the vector field dynamics of RFMs in efficiently guiding the denoising trajectory. Our findings reveal that we can navigate the vector field in a deterministic and gradient-free manner. Utilizing this property, we propose FlowChef, which leverages the vector field to steer the denoising trajectory for controlled image generation tasks, facilitated by gradient skipping. FlowChef is a unified framework for controlled image generation that, for the first time, simultaneously addresses classifier guidance, linear inverse problems, and image editing without the need for extra training, inversion, or intensive backpropagation. Finally, we perform extensive evaluations and show that FlowChef significantly outperforms baselines in terms of performance, memory, and time requirements, achieving new state-of-the-art results. Project Page: \url{https://flowchef.github.io}.
Forward citations
Cited by 6 Pith papers
-
Do Unified Multimodal Models Think in One Space? A Lens Through Cross-Branch Steering
Steering vectors from the understanding branch can control image generation, but vectors from the generation branch cannot control understanding, showing UMMs are architecturally unified but representationally asymmetric.
-
MPFlow: Multi-modal Posterior-Guided Flow Matching for Zero-Shot MRI Reconstruction
MPFlow guides flow-matching MRI reconstruction with self-supervised cross-modal feature alignment to an auxiliary scan, reducing hallucinations and using 20% of the sampling steps of diffusion baselines.
-
Solving Inverse Problems with Flow-based Models via Model Predictive Control
MPC-Flow applies model predictive control to guide pretrained flow models through inverse problems, with a single-step variant that avoids backpropagation and scales to 32B-parameter models on consumer hardware.
-
Align & Invert: Solving Inverse Problems with Diffusion and Flow-based Models via Representation Alignment
Adding DINOv2 representation alignment to diffusion/flow inverse-problem solvers, using corrupted measurements as proxies, improves LPIPS/FID and cuts required sampling steps.
-
The Aging Multiverse: Generating Condition-Aware Facial Aging Tree via Training-Free Diffusion
A training-free diffusion framework creates condition-aware facial aging trees from one photo, balancing identity, age, and prompt-controlled attributes.
-
DICT: Data Injection and Contrastive Trajectory Refinement for Conditional Image Generation with Diffusion Models
Noise-perturbed condition injection plus contrastive trajectory refinement improves training-free conditional diffusion sampling across style transfer, super-resolution and deblurring.
Discussion (0). Continue with ORCID to comment.