Large-scale text-to-image diffusion models have been a ground-breaking development in generating convincing images following an input text prompt. The goal of image editing research is to give users control over the generated images by modifying the text prompt. Current image editing techniques are relying on DDIM inversion as a common practice based on the Latent Diffusion Models (LDM). However, the large pretrained T2I models working on the latent space as LDM suffer from losing details due to the first compression stage with an autoencoder mechanism. Instead, another mainstream T2I pipeline working on the pixel level, such as Imagen and DeepFloyd-IF, avoids this problem. They are commonly composed of several stages, normally with a text-to-image stage followed by several super-resolution stages. In this case, the DDIM inversion is unable to find the initial noise to generate the original image given that the super-resolution diffusion models are not compatible with the DDIM technique. According to our experimental findings, iteratively concatenating the noisy image as the condition is the root of this problem. Based on this observation, we develop an iterative inversion (IterInv) technique for this stream of T2I models and verify IterInv with the open-source DeepFloyd-IF model. By combining our method IterInv with a popular image editing method, we prove the application prospects of IterInv. The code will be released at \url{https://github.com/Tchuanm/IterInv.git}.

翻译：大规模文本到图像扩散模型在根据输入文本提示生成逼真图像方面取得了突破性进展。图像编辑研究的目标是通过修改文本提示，赋予用户对生成图像的控制权。当前的图像编辑技术通常依赖基于潜在扩散模型（LDM）的DDIM反演方法。然而，在LDM潜在空间中运行的大规模预训练T2I模型，因其基于自编码器的第一阶段压缩机制，会导致细节丢失问题。相比之下，另一类工作在像素级的主流T2I流水线（如Imagen和DeepFloyd-IF）可以避免该问题。这类模型通常由多个阶段组成，典型结构包含一个文生图阶段和若干超分辨率阶段。在这种情况下，由于超分辨率扩散模型与DDIM技术不兼容，DDIM反演无法找到生成原始图像所需的初始噪声。根据我们的实验发现，将含噪图像迭代拼接作为条件输入是导致该问题的根本原因。基于此观察，我们提出了一种针对该类T2I模型的迭代反演技术（IterInv），并通过开源DeepFloyd-IF模型进行了验证。通过将我们的方法IterInv与流行的图像编辑方法相结合，我们证明了IterInv的应用前景。代码将在\url{https://github.com/Tchuanm/IterInv.git}开源。