做出相对严谨的量化和解释，比如attribution methods中的Shapley value，和Harsanyi interaction都属于这一类算...
二、 Diffusion for Video Generation Diffusion模型在Image Generation上的成功也促使其被应用于Video Generation上。近年来,一些工作试图使用现有的Image Diffusion模型生成视频。具有代表性的工作是Text2Video-Zero。该工作试图直接使用已训练好的Image Diffusion模型生成视频,无需额外的训练过程。
ReCo: Region-Controlled Text-to-Image Generation GLIGEN: Open-Set Grounded Text-to-Image Generation Adding Conditional Control to Text-to-Image Diffusion Models T2I-Adapter: Learning Adapters to Dig out More Controllable Ability for Text-to-Image Diffusion Models Composer: Creative and Controllable ...
“Cascaded Diffusion Models for High Fidelity Image Generation” Ho et al., Google, 2021 降噪扩散...
More Control for Free! Image Synthesis with Semantic Diffusion Guidance Classifier-Free Diffusion Guidance Zero-Shot Text-to-Image Generation On Fast Sampling of Diffusion Probabilistic Models Vector Quantized Diffusion Model for Text-to-Image Synthesis...
28、CosmicMan: A Text-to-Image Foundation Model for Humans 提出CosmicMan,一种用于生成高保真人体图像的文本到图像基础模型。与当前困在人体图像质量和文本-图像不对齐困境中的通用基础模型不同,CosmicMan能够生成具有细致外貌、合理结构和精确文本-图像对齐的逼真人体图像,同时还提供详细的密集描述。CosmicMan关键在于...
1、DEADiff: An Efficient Stylization Diffusion Model with Disentangled Representations 基于文本到图像扩散模型在迁移参考风格方面具有巨大潜力。然而,当前基于编码器的方法在迁移风格时显著损害了文本到图像模型的文本可控性。本文提出DEADiff来解决这个问题,采用以下两种策略:1)一种解耦参考图像的风格和语义的机制。解耦...
In this work, we propose a native skeleton-guided diffusion model for controllable HIG called HumanSD. Instead of performing image editing with dual-branch diffusion, we fine-tune the original SD model using a novel heatmap-guided denoising loss. This strategy effectively and efficiently strengthens...
1、DEADiff: An Efficient Stylization Diffusion Model with Disentangled Representations 基于文本到图像扩散模型在迁移参考风格方面具有巨大潜力。然而,当前基于编码器的方法在迁移风格时显著损害了文本到图像模型的文本可控性。本文提出DEADiff来解决这个问题,采用以下两种策略:1)一种解耦参考图像的风格和语义的机制。解耦...
The User Interface for Image Generation With a working model, we can now experiment with various prompts producing different visual styles (e.g., “me as an animated character” or “me as an impressionist painting”). However, using GPT for character prompts is optimal, as it yields added ...