𧨠Diffusers welcomes Stable Diffusion 3.5 Large
β’
43
torch.compile()
them. from_single_file
loading and affected by the Runway SD 1.5 issue.runwayml/stable-diffusion-v1-5
saved locally in your HF cache then loading single file checkpoints in the following way should still work. from diffusers import StableDiffusionPipeline
pipe = StableDiffusionPipeline.from_single_file("<url or path to single file checkpoint>")
runwayml/stable-diffusion-v1-5
doesn't exist anymore. from diffusers import StableDiffusionPipeline
pipe = StableDiffusionPipeline.from_single_file("<url or path to single file checkpoint>", config="Lykon/DreamShaper")
I think you definitely missed out on another big release:
https://huggingface.co/posts/sayakpaul/557387472547604
from_single_file()
method, highlighting our efforts for making our library more amenable to community features π€custom_pipeline
argument πDiffusionPipeline
, no compromise there π€DiffusionPipeline
.
device_map
in Diffusers π€diffusers
library. The post delves deeper into the workflows responsible for:I mean we should be able to make the most out of the GPU by reducing the idle-time as much as possible while also ensuring the throughput is really the highest we can get out of the card.
For example, if we are getting 60 QPS, is that the highest we can get out of the card? Is it the maximum limit?