相关论文: FlowAlign: Trajectory-Regularized, Inversion-Free …
Recent advancements in diffusion and flow-matching models have demonstrated remarkable capabilities in high-fidelity image synthesis. A prominent line of research involves reward-guided guidance, which steers the generation process during…
Flow-based latent generative models such as Stable Diffusion 3 are able to generate images with remarkable quality, even enabling photorealistic text-to-image generation. Their impressive performance suggests that these models should also…
Flow matching models have emerged as a strong alternative to diffusion models, but existing inversion and editing methods designed for diffusion are often ineffective or inapplicable to them. The straight-line, non-crossing trajectories of…
Training-free 3D editing aims to modify 3D shapes based on human instructions without model finetuning. It plays a crucial role in 3D content creation. However, existing approaches often struggle to produce strong or geometrically stable…
Text-driven image editing enables users to flexibly modify visual content through natural language instructions, and is widely applied to tasks such as semantic object replacement, insertion, and removal. While recent inversion-based…
With the prosper of video diffusion models, down-stream applications like video editing have been significantly promoted without consuming much computational cost. One particular challenge in this task lies at the motion transfer process…
Fast flow models accelerate the iterative sampling process by learning to directly predict ODE path integrals, enabling one-step or few-step generation. However, we argue that current fast-flow training paradigms suffer from two fundamental…
Drag-based editing allows precise object manipulation through point-based control, offering user convenience. However, current methods often suffer from a geometric inconsistency problem by focusing exclusively on matching user-defined…
This paper focuses on the alignment of flow matching models with human preferences. A promising way is fine-tuning by directly backpropagating reward gradients through the differentiable generation process of flow matching. However,…
Recent advances in image editing with diffusion models have achieved impressive results, offering fine-grained control over the generation process. However, these methods are computationally intensive because of their iterative nature.…
Leveraging the large generative prior of the flow transformer for tuning-free image editing requires authentic inversion to project the image into the model's domain and a flexible invariance control mechanism to preserve non-target…
Text-based semantic image editing assumes the manipulation of an image using a natural language instruction. Although recent works are capable of generating creative and qualitative images, the problem is still mostly approached as a black…
Diffusion models have revolutionized the field of content synthesis and editing. Recent models have replaced the traditional UNet architecture with the Diffusion Transformer (DiT), and employed flow-matching for improved training and…
Though Rectified Flows (ReFlows) with distillation offers a promising way for fast sampling, its fast inversion transforms images back to structured noise for recovery and following editing remains unsolved. This paper introduces FireFlow,…
Existing rectified flow models are based on linear trajectories between data and noise distributions. This linearity enforces zero curvature, which can inadvertently force the image generation process through low-probability regions of the…
Diffusion-based image editing is a composite process of preserving the source image content and generating new content or applying modifications. While current editing approaches have made improvements under text guidance, most of them have…
Instruction-based image editing aims to modify source content according to textual instructions. However, existing methods built upon flow matching often struggle to maintain consistency in non-edited regions due to denoising-induced…
Precise image editing with text-to-image models has attracted increasing interest due to their remarkable generative capabilities and user-friendly nature. However, such attempts face the pivotal challenge of misalignment between the…
Point-based image editing has attracted remarkable attention since the emergence of DragGAN. Recently, DragDiffusion further pushes forward the generative quality via adapting this dragging technique to diffusion models. Despite these great…
Inversion-free image editing using flow-based generative models challenges the prevailing inversion-based pipelines. However, existing approaches rely on fixed Gaussian noise to construct the source trajectory, leading to biased trajectory…