David Helen

@justinpinkney hello can i ask you some questions?

@justinpinkney Do i need to use this ckpt? sd-clip-vit-l14-img-embed_ema_only.ckpt? like this: model: base_learning_rate: 1.0e-04 ckpt_path:sd-clip-vit-l14-img-embed_ema_only.ckpt target: ldm.models.diffusion.ddpm.LatentDiffusion

But why the reconstruction is not work ？I want to train a new model @justinpinkney

I have no solution for it. when i load the weight ckpt the reconstruction is also not work @justinpinkney

可以 我加你 繁华落尽 ***@***.***   ------------------ 原始邮件 ------------------ 发件人: "justinpinkney/stable-diffusion" ***@***.***>; 发送时间: 2023年4月3日(星期一) 下午5:04 ***@***.***>; ***@***.******@***.***>; 主题: Re: [justinpinkney/stable-diffusion] How to train a image-condition model with my custom dataset? (Issue #49) nt to main.py...

@justinpinkney

There is something wrong: No checkpoint found at ./checkpoints/ffhq_256_ncsnpp_continuous/checkpoint_48.pth. Returned the same state as input Error: Ran out of input when I load ./checkpoints/ffhq_256_ncsnpp_continuous/checkpoint_48.pt

> @pokameng How is your training process, and the rendered image? My training and rendered are from the old code version, but my mesh is from the latest. My training...

@wzr1201 Hi,I have encount this problem, did you solved this issue? 

@wzr1201 I have solved!