用连续CRF加速潜在扩散模型，速度提升33%无质量损失
LatentCRF: Continuous CRF for Efficient Latent Diffusion
- 将CRF作为轻量层嵌入潜在扩散模型，建模潜在向量间空间语义关系
- 减少33%推理时间，图像质量与多样性与原模型持平
- 无需修改原模型，可直接添加提升效率，适合部署场景
潜在扩散模型（LDM）能生成高质量、逼真的图像，但多次昂贵的推理迭代导致延迟较高，限制了实际应用。本文提出LatentCRF，一种以神经网络层实现的连续条件随机场（CRF）模型，用于建模LDM中潜在向量的空间与语义关系。通过用轻量级的LatentCRF替代部分计算密集型的推理迭代，实现了质量、速度与多样性的更优平衡。相比完整LDM，推理效率提升33%，且未造成图像质量或多样性损失。LatentCRF为即插即用模块，无需修改原LDM架构。
原文摘要 · Abstract (English)
Latent Diffusion Models (LDMs) produce high-quality, photo-realistic images, however, the latency incurred by multiple costly inference iterations can restrict their applicability. We introduce LatentCRF, a continuous Conditional Random Field (CRF) model, implemented as a neural network layer, that models the spatial and semantic relationships among the latent vectors in the LDM. By replacing some of the computationally-intensive LDM inference iterations with our lightweight LatentCRF, we achieve a superior balance between quality, speed and diversity. We increase inference efficiency by 33% with no loss in image quality or diversity compared to the full LDM. LatentCRF is an easy add-on, which does not require modifying the LDM.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。