Jesse Andrews

On the plus side it looks like negative prompts works... NO BLUE! - https://replicate.com/p/ox5orxd3ubb67mdjp5twcgm6tu - https://replicate.com/p/5cpkw66l3fdizjoiirfhceu6mu - https://replicate.com/p/jytb6qszcjczpd3ovhintpp7m4 - https://replicate.com/p/pfm74qiiljdg3kxtvtobfvp24y (although there is some blue in a couple images)

 dreambooth-template  cog-stable-diffusion DDIM scheduler slight differences

The branch is https://github.com/replicate/dreambooth/tree/sd21

Progress by @Pwntus in #34 !

@strickinato / other folks who want to try it out and give feedback: The `trainer_version` in the [dreambooth api](http://replicate.com/blog/dreambooth-api) can be any dreambooth version you have access to. In this...

I think the issue is you changed the `trainer_version` to the dreambooth model you trained already - you need to keep it at `837450bfda6314d2290cc1d0c159843296f981c0b8a7f512d0efbf49970b5229` This prototype doesn't support continuing training...

@ivan-volchenskov thanks for the great writeup & sharing your results! ## 30 minute timeout You are correct about timing out because it is under my personal account. Once we have...

This might be an issue with the recent work adding async support to https://github.com/replicate/cog @achuinard to reproduce, I assume you trained this model recently? (can you provide the an ID...

@achuinard - we have switched over to cog's "async" style: - async api for cog makes the requests look the same as replicate - enabling users to switch between the...

@daanelson did an initial proof of concept with: ``` custom_pipeline="lpw_stable_diffusion", ``` https://github.com/daanelson/cog-stable-diffusion-long-prompt And pushed a version to https://replicate.com/daanelson/stable-diffusion-long-prompts He shares that this pipeline is slower even for short prompts, so...