reproduce layout results as in the original stable diffusion paper?

[CreamyLong]

          @CreamyLong, have you reproduce layout results as in the original stable diffusion paper? 

I used your layout config and have trained for 10 epochs （COCO dataset，batch size=16）, but the log images obtained in training phrase are as follows,
which I think are not correct training results. The training loss have awalys keep around 0.27 not decreased during the whole training process.

input bbox

input image

decoded recontruction directly from first-stage embeded latent

sample image from latent diffusion model (ddim_step=200, eta=0.)

Originally posted by @Tonsty in #14 (comment)

[CreamyLong]

What GPU do you use? @Tonsty

[Tonsty]

@CreamyLong I used an L40

[Tonsty]

result after training 100 epochs

gt

sample

I found some results are acceptable, e.g. food