PS可以删了，真电商神器，OminiControl一键P图和AI换衣

Nov 27, 2024#AI47

AI-generated summary

OminiControl is a powerful tool for generating product images and clothing model visuals, outperforming existing models like Lora and IP-Adapter. It offers unified image adjustment capabilities, including theme-driven generation and spatial alignment based on edges and depth. The tool is trained on images generated by DiT, enhancing its effectiveness for theme-driven tasks. Examples include close-up product shots and clothing try-ons in various settings. For more information, visit the project's GitHub page, the research paper on arXiv, or try it out on Hugging Face.

AI 做产品图和衣服模特图，最好的办法还是训练每个产品的 Lora，IP-Adapter 等保持人像和物品一致性的模型都还不能达到满意的效果。而 OminiControl 一出将变成电商神器，分分钟生成各种产品图以及衣服试穿图。应用场景 OminiControl 以统一的方式处理各种图像调节任务，包括：- 主题驱动生成 - 空间对齐条件（如边缘、深度等）特别值得一提的是，这些功能是通过对 DiT 自身生成的图像进行训练来实现的，这对主题驱动生成特别有利。

物品场景变化

Prompt: A close up view of this item. It is placed on a wooden table. The background is a dark room, the TV is on, and the screen is showing a cooking show. With text on the screen that reads 'Omini Control!.'

衣服试穿

Prompt: "On the beach, a lady sits under a beach umbrella with 'Omini' written on it. She's wearing this shirt and has a big smile on her face, with her surfboard hehind her. The sun is setting in the background. The sky is a beautiful shade of orange and purple."

项目页：github.com/Yuanshi9815/OminiControl

论文页：arxiv.org/abs/2411.15098

网页试用：huggingface.co/spaces/Yuanshi/Omini

ControlComfyui 插件：github.com/pzc163/ComfyUI_OminiControl