David Helen

> ucf101 is a feasible choice thanks!!!

@Youngon I have no idea to solve it. How about you?

@kashif @lucidrains

@JingweiJ Great work! Just wondering when all the related code and dataset of the paper will be released? I just see the tool code on this github.Thanks!

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...

The bug is: 

> if you want to use your own datasets please refer to https://github.com/hpcaitech/ColossalAI/blob/main/examples/images/diffusion/ldm/data/base.py, the data format should be same as your yaml config I know, but the lsun.py you provide...

> But I want to use ldm.data.lsun.LSUNBedroomsTrain to train lsun bedroom dataset. But I want to use ldm.data.lsun.LSUNBedroomsTrain to train lsun bedroom dataset. If i use ldm.data.lsun.LSUNBedroomsTrain, it has a...

> I think the base.py is an good example to train image with text caption Can you give me a example for text? I want to kown the content in...

> I think the base.py is an good example to train image with text caption you mean the cifar10 is the conditional example?