AI/diffusers
1
0
Fork 0
mirror of https://github.com/huggingface/diffusers.git synced 2026-01-27 17:22:53 +03:00
Code Activity

[AudioLDM] Update docs to use updated ckpt (#3240)

Browse Source 
* [AudioLDM] Update docs to use updated ckpt

* make style
This commit is contained in:
Sanchit Gandhi
2023-04-26 11:33:08 +00:00
committed by GitHub
parent 977162c02b
commit 46ceba5b35
1 changed files with 8 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

14
docs/source/en/api/pipelines/audioldm.mdx
View File

@@ -25,14 +25,14 @@ This pipeline was contributed by [sanchit-gandhi](https://huggingface.co/sanchit
## Text-to-Audio
The [`AudioLDMPipeline`] can be used to load pre-trained weights from [cvssp/audioldm](https://huggingface.co/cvssp/audioldm) and generate text-conditional audio outputs:
The [`AudioLDMPipeline`] can be used to load pre-trained weights from [cvssp/audioldm-s-full-v2](https://huggingface.co/cvssp/audioldm-s-full-v2) and generate text-conditional audio outputs:
```python
from diffusers import AudioLDMPipeline
import torch
import scipy
repo_id = "cvssp/audioldm"
repo_id = "cvssp/audioldm-s-full-v2"
pipe = AudioLDMPipeline.from_pretrained(repo_id, torch_dtype=torch.float16)
pipe = pipe.to("cuda")
@@ -56,7 +56,7 @@ Inference:
### How to load and use different schedulers
The AudioLDM pipeline uses [`DDIMScheduler`] scheduler by default. But `diffusers` provides many other schedulers
that can be used with the AudioLDM pipeline such as [`PNDMScheduler`], [`LMSDiscreteScheduler`], [`EulerDiscreteScheduler`],
that can be used with the AudioLDM pipeline such as [`PNDMScheduler`], [`LMSDiscreteScheduler`], [`EulerDiscreteScheduler`],
[`EulerAncestralDiscreteScheduler`] etc. We recommend using the [`DPMSolverMultistepScheduler`] as it's currently the fastest
scheduler there is.
@@ -68,12 +68,14 @@ method, or pass the `scheduler` argument to the `from_pretrained` method of the
>>> from diffusers import AudioLDMPipeline, DPMSolverMultistepScheduler
>>> import torch
>>> pipeline = AudioLDMPipeline.from_pretrained("cvssp/audioldm", torch_dtype=torch.float16)
>>> pipeline = AudioLDMPipeline.from_pretrained("cvssp/audioldm-s-full-v2", torch_dtype=torch.float16)
>>> pipeline.scheduler = DPMSolverMultistepScheduler.from_config(pipeline.scheduler.config)
>>> # or
>>> dpm_scheduler = DPMSolverMultistepScheduler.from_pretrained("cvssp/audioldm", subfolder="scheduler")
>>> pipeline = AudioLDMPipeline.from_pretrained("cvssp/audioldm", scheduler=dpm_scheduler, torch_dtype=torch.float16)
>>> dpm_scheduler = DPMSolverMultistepScheduler.from_pretrained("cvssp/audioldm-s-full-v2", subfolder="scheduler")
>>> pipeline = AudioLDMPipeline.from_pretrained(
... "cvssp/audioldm-s-full-v2", scheduler=dpm_scheduler, torch_dtype=torch.float16
... )
```
## AudioLDMPipeline