In this technical report, we introduce SEED-Data-Edit: a unique hybrid
dataset for instruction-guided image editing, which aims to facilitate image
manipulation using open-form language. SEED-Data-Edit is composed of three
distinct types of data: (1) High-quality editing data produced by an automated
pipeline, ensuring a substantial volume of diverse image editing pairs. (2)
Real-world scenario data collected from the internet, which captures the
intricacies of user intentions for promoting the practical application of image
editing in the real world. (3) High-precision multi-turn editing data annotated
by humans, which involves multiple rounds of edits for simulating iterative
editing processes. The combination of these diverse data sources makes
SEED-Data-Edit a comprehensive and versatile dataset for training
language-guided image editing model. We fine-tune a pretrained Multimodal Large
Language Model (MLLM) that unifies comprehension and generation with
SEED-Data-Edit. The instruction tuned model demonstrates promising results,
indicating the potential and effectiveness of SEED-Data-Edit in advancing the
field of instructional image editing. The datasets are released in
this https URL

SEED-Data-Edit 是一个用于指导图像编辑的独特混合数据集，包括高质量编辑数据、实际场景数据、和多轮编辑数据；使用该数据集对预训练的多模态大型语言模型进行微调，显示了其在指导图像编辑方面的潜力和有效性。

SEED-Data-Edit 技术报告：用于教学图像编辑的混合数据集

SEED-Data-Edit Technical Report: A Hybrid Dataset for Instructional  Image Editing

The combination of language processing and image processing keeps attracting
increased interest given recent impressive advances that leverage the combined
strengths of both domains of research. Among these advances, the task of
editing an image on the basis solely of a natural language instruction stands
out as a most challenging endeavour. While recent approaches for this task
resort, in one way or other, to some form of preliminary preparation, training
or fine-tuning, this paper explores a novel approach: We propose a
preparation-free method that permits instruction-guided image editing on the
fly. This approach is organized along three steps properly orchestrated that
resort to image captioning and DDIM inversion, followed by obtaining the edit
direction embedding, followed by image editing proper. While dispensing with
preliminary preparation, our approach demonstrates to be effective and
competitive, outperforming recent, state of the art models for this task when
evaluated on the MAGICBRUSH dataset.

该研究论文通过语言处理和图像处理的组合吸引了越来越多的关注，其中一项最具挑战性的任务是仅基于自然语言指令对图像进行编辑。本论文提出了一种无需准备的方法，通过图像字幕和 DDIM 反演、获取编辑方向嵌入以及图像编辑等三个步骤有效地进行指令引导的图像编辑，该方法在 MAGICBRUSH 数据集上表现出色，优于最新的先进模型。