Text-to-Image
Can Pre-Trained Text-to-Image Models Generate Visual Goals for Reinforcement Learning
概述 Learning form the Void (LfVoid) 根据给定的language instruction对observation进行appearance-based and structure-based修改得到goal images，为RL提供奖励信号。提升了example-bas ......
Adding Conditional Control to Text-to-Image Diffusion Models
https://mp.weixin.qq.com/s/iL6YitT7EGP6DnrBehb9MQ 1.Adding Conditional Control to Text-to-Image Diffusion Models 论文地址：https://arxiv.org/pdf/2302.05543 ......
论文阅读（二）—— Text2Video-Zero: Text-to-Image Diffusion Models are Zero-Shot Video Generators
  ![image](https://img2023.cnblogs.com/blog/3279428/20... ......
DreamBooth Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation
[TOC] > [Ruiz N., Li Y., Jampani V., Pritch Y., Rubinstein M. and Aberman K. DreamBooth: Fine tuning text-to-image diffusion models for subject-driven ......
Generative AI 新世界 | 走进文生图（Text-to-Image）领域
在之前的四篇 “Generative AI 新世界” 中，我们带领大家一起探索了生成式 AI（Generative AI），以及大型语言模型（LLMs）的全新世界概览。并在文本生成（Text Generation）领域做了一些概述、相关论文解读、以及在亚马逊云科技的落地实践和动手实验。 亚马逊云科技 ......