Text-guided image editing can have a transformative impact in supporting creative applications. A key challenge is to generate edits that are faithful to input text prompts, while consistent with input images. We present Imagen Editor, a cascaded diffusion model built, by fine-tuning Imagen on text-guided image inpainting. Imagen Editor's edits are faithful to the text prompts, which is accomplished by using object detectors to propose inpainting masks during training. In addition, Imagen Editor captures fine details in the input image by conditioning the cascaded pipeline on the original high resolution image. To improve qualitative and quantitative evaluation, we introduce EditBench, a systematic benchmark for text-guided image inpainting. EditBench evaluates inpainting edits on natural and generated images exploring objects, attributes, and scenes. Through extensive human evaluation on EditBench, we find that object-masking during training leads to across-the-board improvements in text-image alignment -- such that Imagen Editor is preferred over DALL-E 2 and Stable Diffusion -- and, as a cohort, these models are better at object-rendering than text-rendering, and handle material/color/size attributes better than count/shape attributes.

翻译：文本引导的图像编辑可在支持创意应用方面带来变革性影响。其核心挑战在于生成的编辑结果既要忠实于输入文本提示，又要与输入图像保持一致。我们提出Imagen Editor，这是一种通过基于文本引导的图像修复对Imagen进行微调而构建的级联扩散模型。通过训练过程中使用目标检测器生成修复掩码，Imagen Editor的编辑结果能忠实反映文本提示。此外，Imagen Editor通过将级联流水线条件化为原始高分辨率图像，捕获输入图像中的精细细节。为提升定性与定量评估，我们引入EditBench——一个面向文本引导图像修复的系统化基准。该基准针对自然图像与生成图像中的物体、属性及场景维度进行修复编辑评估。基于EditBench的大规模人工评估发现：训练中采用目标掩码能全面改善文本-图像对齐度，使Imagen Editor获得优于DALL-E 2和Stable Diffusion的偏好度；同时，这些模型群体在物体渲染方面优于文本渲染，处理材质/颜色/尺寸属性的表现也优于计数/形状属性。