[Script request]: Step1X-Edit: A Practical Framework for General Image Editing

[SpaceAgeHero]

Application Name

Step1X-Edit

Website

https://github.com/stepfun-ai/Step1X-Edit

Description

We introduce a state-of-the-art image editing model, Step1X-Edit, which aims to 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 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. More details please refer to our technical report.

Due Diligence

• I have searched existing scripts and found no duplicates.
• I have searched existing discussions and found no duplicate requests.

[MickLesk]

Do you have a few GPUs and GPU docks to spare? Then we can take a look at it and get it halfway up and running.

---

[tremor021]

I have no clue how we can test this :)

[SpaceAgeHero]

What has happened guys, do you have your Proxmox running on a Potato?
Just kidding. I'm planning to upgrade to a host machine with 128 GB shared memory and thought this would be nice to play with.
Feel free to close the discussion.