Related papers: In-situ Autoguidance: Eliciting Self-Correction in…
Diffusion models are emerging expressive generative models, in which a large number of time steps (inference steps) are required for a single image generation. To accelerate such tedious process, reducing steps uniformly is considered as an…
Diffusion models have achieved remarkable progress in image and audio generation, largely due to Classifier-Free Guidance. However, the choice of guidance scale remains underexplored: a fixed scale often fails to generalize across prompts…
Typical diffusion models are trained to accept a particular form of conditioning, most commonly text, and cannot be conditioned on other modalities without retraining. In this work, we propose a universal guidance algorithm that enables…
Flow-based generative models have become a strong framework for high-quality generative modeling, yet pretrained models are rarely used in their vanilla conditional form: conditional samples without guidance often appear diffuse and lack…
Classifier-free guidance (CFG) is the de facto standard for conditional sampling in diffusion models, yet it often reduces sample diversity. Using tools from statistical physics, we analyze the emergence of generative distortions induced by…
Diffusion models have demonstrated strong generative performance when using guidance methods such as classifier-free guidance (CFG), which enhance output quality by modifying the sampling trajectory. These methods typically improve a target…
Classifier-Free Guidance (CFG) enhances the quality and condition adherence of text-to-image diffusion models. It operates by combining the conditional and unconditional predictions using a fixed weight. However, recent works vary the…
Diffusion models have emerged as a powerful tool for generating high-quality images, videos, and 3D content. While sampling guidance techniques like CFG improve quality, they reduce diversity and motion. Autoguidance mitigates these issues…
Diffusion models are among the most effective methods for image generation. This is in particular because, unlike GANs, they can be easily conditioned during training to produce elements with desired class or properties. However, guiding a…
We present a simple but effective training-free approach for text-driven image-to-image translation based on a pretrained text-to-image diffusion model. Our goal is to generate an image that aligns with the target task while preserving the…
Despite recent advances, diffusion-based text-to-image models still struggle with accurate text rendering. Several studies have proposed fine-tuning or training-free refinement methods for accurate text rendering. However, the critical…
Classifier-guided diffusion models have emerged as a powerful approach for conditional image generation, but they suffer from overconfident predictions during early denoising steps, causing the guidance gradient to vanish. This paper…
Text-to-image diffusion models produce impressive results but are frustrating tools for artists who desire fine-grained control. For example, a common use case is to create images of a specific instance in novel contexts, i.e.,…
Guiding unconditional diffusion models typically requires either retraining with conditional inputs or per-step gradient computations (e.g., classifier-based guidance), both of which incur substantial computational overhead. We present a…
Classifier-free guidance (CFG) succeeds in condition diffusion models that use a guidance scale to balance the influence of conditional and unconditional terms. A high guidance scale is used to enhance the performance of the conditional…
As Classifier-Free Guidance (CFG) has proven effective in conditional diffusion model sampling for improved condition alignment, many applications use a negated CFG term to filter out unwanted features from samples. However, simply negating…
In generative modeling, we often wish to produce samples that maximize a user-specified reward such as aesthetic quality or alignment with human preferences, a problem known as \textit{guidance}. Despite their widespread use, existing…
Given an unconditional generative model and a predictor for a target property (e.g., a classifier), the goal of training-free guidance is to generate samples with desirable target properties without additional training. As a highly…
Text-guided image inpainting endeavors to generate new content within specified regions of images using textual prompts from users. The primary challenge is to accurately align the inpainted areas with the user-provided prompts while…
Diffusion-based editing models have emerged as a powerful tool for semantic image and video manipulation. However, existing models lack a mechanism for smoothly controlling the intensity of text-guided edits. In standard text-conditioned…