search

YangLing0818 / RealCompo

RealCompo: Balancing Realism and Compositionality Improves Text-to-Image Diffusion Models
https://arxiv.org/abs/2402.12908
103 stars 3 forks source link

Is api_key necessary in option 1? #4

Open ustczhouyu opened 1 month ago

ustczhouyu commented 1 month ago

Is api_key necessary in option 1?

Cominclip commented 1 month ago

If you want to generate images only based on a text prompt, you should follow Option 1 and provide an api_key. This is because the layout is generated from GPT-4 using an api_key, which is used to guide the L2I models during generation. If you don't have an api_key, you can consider setting up the layout to meet the format in Option2.