Giters

SHI-Labs / Prompt-Free-Diffusion

Prompt-Free Diffusion: Taking "Text" out of Text-to-Image Diffusion Models, arxiv 2023 / CVPR 2024

Home Page:https://arxiv.org/abs/2305.16223

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

text control

pokameng opened this issue · comments

commented

@xingqian2018
Can we take text as a condition?

commented

There are several ways we can include text control. One easiest way is to concatenate CLIP Text Embedding with SeeCoder Image Embedding and condition the diffusion process. You may find such feature in the SDWebUI plugin.