Updated lora inference instructions #6913
Conversation
examples/dreambooth/README.md
Outdated
| import os | ||
| from diffusers import StableDiffusionPipeline | ||
| pipe = StableDiffusionPipeline.from_pretrained(os.environ["MODEL_NAME"]).to("cuda") |
There was a problem hiding this comment.
Let's not change these things please.
There was a problem hiding this comment.
I can remove os, but I think it's better to switch it to StableDiffusionPipeline
It's a sd pipeline after all. And you don't need this wizardry with DPMSolverMultistepScheduler
There was a problem hiding this comment.
It's okay to use DiffusionPipeline here since it's more generic. I am not sure how that is related to any wizardry.
sayakpaul
left a comment
sayakpaul
left a comment
There was a problem hiding this comment.
Thanks! Left some comments.
|
The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update. |
Co-authored-by: Sayak Paul <[email protected]>
|
@sayakpaul let me know if you want to keep it a Diffusion pipeline instead of StableDiffusion |
examples/dreambooth/README.md
Outdated
| pipe.scheduler = DPMSolverMultistepScheduler.from_config(pipe.scheduler.config) | ||
| pipe.to("cuda") | ||
| from diffusers import StableDiffusionPipeline | ||
| pipe = StableDiffusionPipeline.from_pretrained("base-model-name").to("cuda") |
There was a problem hiding this comment.
| pipe = StableDiffusionPipeline.from_pretrained("base-model-name").to("cuda") | |
| pipe = DiffusionPipeline.from_pretrained("base-model-name").to("cuda") |
sayakpaul
left a comment
sayakpaul
left a comment
There was a problem hiding this comment.
Single suggestion. After that we can merge.
|
Will merge once the CI is green. |
3 participants
What does this PR do?
Fixes #6906
Before submitting
documentation guidelines, and
here are tips on formatting docstrings.
Who can review?
Anyone in the community is free to review the PR once the tests have passed. Feel free to tag
members/contributors who may be interested in your PR.
@sayakpaul