search

CompVis / stable-diffusion

A latent text-to-image diffusion model
https://ommer-lab.com/research/latent-diffusion-models/
Other
66.51k stars 9.97k forks source link

How to write the data config in v1-inference.yaml by myself? #809

Open liuchangzong opened 7 months ago

liuchangzong commented 7 months ago

It looks like there should have the data config in the v1-inference.yaml.

Because in the main.py of line 663https://github.com/CompVis/stable-diffusion/blob/main/main.py#L663, we need config.data.

Should I write it by myself? or where can I find the source code or tutorial to write it.

Can anyone help me please?

ps: it looks like animatediff code have write the class webVid10M to load a dataset.

CreamyLong commented 6 months ago

maybe you can have a look this repo to imitate the config.