Step1X-Edit: A Practical Framework for General Image Editing
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866909712566452224 |
|---|---|
| author | Liu, Shiyu Han, Yucheng Xing, Peng Yin, Fukun Wang, Rui Cheng, Wei Liao, Jiaqi Wang, Yingming Fu, Honghao Han, Chunrui Li, Guopeng Peng, Yuang Sun, Quan Wu, Jingwei Cai, Yan Ge, Zheng Ming, Ranchen Xia, Lei Zeng, Xianfang Zhu, Yibo Jiao, Binxing Zhang, Xiangyu Yu, Gang Jiang, Daxin |
| author_facet | Liu, Shiyu Han, Yucheng Xing, Peng Yin, Fukun Wang, Rui Cheng, Wei Liao, Jiaqi Wang, Yingming Fu, Honghao Han, Chunrui Li, Guopeng Peng, Yuang Sun, Quan Wu, Jingwei Cai, Yan Ge, Zheng Ming, Ranchen Xia, Lei Zeng, Xianfang Zhu, Yibo Jiao, Binxing Zhang, Xiangyu Yu, Gang Jiang, Daxin |
| contents | In recent years, image editing models have witnessed remarkable and rapid development. The recent unveiling of cutting-edge multimodal models such as GPT-4o and Gemini2 Flash has introduced highly promising image editing capabilities. These models demonstrate an impressive aptitude for fulfilling a vast majority of user-driven editing requirements, marking a significant advancement in the field of image manipulation. However, there is still a large gap between the open-source algorithm with these closed-source models. Thus, in this paper, we aim to release a state-of-the-art image editing model, called Step1X-Edit, which can provide comparable performance against the closed-source models like GPT-4o and Gemini2 Flash. More specifically, we adopt the Multimodal LLM to process the reference image and the user's editing instruction. A latent embedding has been extracted and integrated with a diffusion image decoder to obtain the target image. To train the model, we build a data generation pipeline to produce a high-quality dataset. For evaluation, we develop the GEdit-Bench, a novel benchmark rooted in real-world user instructions. Experimental results on GEdit-Bench demonstrate that Step1X-Edit outperforms existing open-source baselines by a substantial margin and approaches the performance of leading proprietary models, thereby making significant contributions to the field of image editing. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_17761 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Step1X-Edit: A Practical Framework for General Image Editing Liu, Shiyu Han, Yucheng Xing, Peng Yin, Fukun Wang, Rui Cheng, Wei Liao, Jiaqi Wang, Yingming Fu, Honghao Han, Chunrui Li, Guopeng Peng, Yuang Sun, Quan Wu, Jingwei Cai, Yan Ge, Zheng Ming, Ranchen Xia, Lei Zeng, Xianfang Zhu, Yibo Jiao, Binxing Zhang, Xiangyu Yu, Gang Jiang, Daxin Computer Vision and Pattern Recognition In recent years, image editing models have witnessed remarkable and rapid development. The recent unveiling of cutting-edge multimodal models such as GPT-4o and Gemini2 Flash has introduced highly promising image editing capabilities. These models demonstrate an impressive aptitude for fulfilling a vast majority of user-driven editing requirements, marking a significant advancement in the field of image manipulation. However, there is still a large gap between the open-source algorithm with these closed-source models. Thus, in this paper, we aim to release a state-of-the-art image editing model, called Step1X-Edit, which can provide comparable performance against the closed-source models like GPT-4o and Gemini2 Flash. More specifically, we adopt the Multimodal LLM to process the reference image and the user's editing instruction. A latent embedding has been extracted and integrated with a diffusion image decoder to obtain the target image. To train the model, we build a data generation pipeline to produce a high-quality dataset. For evaluation, we develop the GEdit-Bench, a novel benchmark rooted in real-world user instructions. Experimental results on GEdit-Bench demonstrate that Step1X-Edit outperforms existing open-source baselines by a substantial margin and approaches the performance of leading proprietary models, thereby making significant contributions to the field of image editing. |
| title | Step1X-Edit: A Practical Framework for General Image Editing |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2504.17761 |