How to feed the reference image as condition rather than text?

[pokameng]

Hello bro The latent diffusion model make great progress in text-to-image generation ,but how do we take a reference image as the condintion rather than a prompt? I want to use a image to guide image generation. @asanakoy @pesser @crowsonkb @theRealSuperMario @to3i

[WXaaron]

@pokameng Hello, have you solved this problem? Can you please share it? Thank you

[pokameng]

emmm, not tet

繁华落尽 @.***

 

------------------ 原始邮件 ------------------ 发件人: "CompVis/latent-diffusion" @.>; 发送时间: 2023年9月10日(星期天) 中午11:16 @.>; @.@.>; 主题: Re: [CompVis/latent-diffusion] How to feed the reference image as condition rather than text? (Issue #229)

@pokameng Hello, have you solved this problem? Can you please share it? Thank you

— Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you were mentioned.Message ID: @.***>

[zy-charon]

Hello, I also have the same problem. Can you share how to fix it? Thank you.