DICE: Distilling Classifier-Free Guidance into Text Embeddings
Text-to-image diffusion models are capable of generating high-quality images, but these images often fail to align closely with the given text prompts. Classifier-free guidance (CFG) is a popular and effective technique for improving text-image alignment in the generative process. However, using CFG introduces significant computational overhead and deviates from the established theoretical foundations of diffusion models. In this paper, we present DIstilling CFG by enhancing text Embeddings (DICE), a novel approach that removes the reliance on CFG in the generative process while maintaining the benefits it provides. DICE distills a CFG-based text-to-image diffusion model into a CFG-free version by refining text embeddings to replicate CFG-based directions. In this way, we avoid the computational and theoretical drawbacks of CFG, enabling high-quality, well-aligned image generation at a fast sampling speed. Extensive experiments on multiple Stable Diffusion v1.5 variants, SDXL and PixArt-$\alpha$ demonstrate the effectiveness of our method. Furthermore, DICE supports negative prompts for image editing to improve image quality further. Code will be available soon.
Code (0)
등록된 구현이 없습니다.
Tasks
Image GenerationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Reward Weighted Classifier-Free Guidance as Policy Improvement in Autoregressive Models
Consider an auto-regressive model that produces outputs x (e.g., answers to questions, molecules) each of which can be summarized by an attribute vector y (e.g., helpfulness vs. harmlessness, or bio-availability vs. lipo…
Reinforcement LearningSNOOPI: Supercharged One-step Diffusion Distillation with Proper Guidance
Recent approaches have yielded promising results in distilling multi-step text-to-image diffusion models into one-step ones. The state-of-the-art efficient distillation technique, i.e., SwiftBrushv2 (SBv2), even surpasse…
Image GenerationDMGD: Train-Free Dataset Distillation with Semantic-Distribution Matching in Diffusion Models
Dataset distillation enables efficient training by distilling the information of large-scale datasets into significantly smaller synthetic datasets. Diffusion based paradigms have emerged in recent years, offering novel …
Few-Step Diffusion via Score identity Distillation
Diffusion distillation has emerged as a promising strategy for accelerating text-to-image (T2I) diffusion models by distilling a pretrained score network into a one- or few-step generator. While existing methods have mad…
DiversityStudying Classifier(-Free) Guidance From a Classifier-Centric Perspective
Classifier-free guidance has become a staple for conditional generation with denoising diffusion models. However, a comprehensive understanding of classifier-free guidance is still missing. In this work, we carry out an …
Denoising