From 519f2f0eed10244d2ae4eba54b6d582a6e6beece Mon Sep 17 00:00:00 2001 From: sanchit-gandhi Date: Wed, 26 Apr 2023 11:23:09 +0100 Subject: [PATCH 1/2] [AudioLDM] Update docs to use updated ckpt --- docs/source/en/api/pipelines/audioldm.mdx | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/docs/source/en/api/pipelines/audioldm.mdx b/docs/source/en/api/pipelines/audioldm.mdx index f3987d2263ac..39b8684bb440 100644 --- a/docs/source/en/api/pipelines/audioldm.mdx +++ b/docs/source/en/api/pipelines/audioldm.mdx @@ -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 +68,12 @@ 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 From 9f759396a9c5c229202ca3fffd7db3e87a62b4b8 Mon Sep 17 00:00:00 2001 From: sanchit-gandhi Date: Wed, 26 Apr 2023 11:24:12 +0100 Subject: [PATCH 2/2] make style --- docs/source/en/api/pipelines/audioldm.mdx | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/docs/source/en/api/pipelines/audioldm.mdx b/docs/source/en/api/pipelines/audioldm.mdx index 39b8684bb440..25a5bb8bce13 100644 --- a/docs/source/en/api/pipelines/audioldm.mdx +++ b/docs/source/en/api/pipelines/audioldm.mdx @@ -73,7 +73,9 @@ method, or pass the `scheduler` argument to the `from_pretrained` method of the >>> # or >>> 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) +>>> pipeline = AudioLDMPipeline.from_pretrained( +... "cvssp/audioldm-s-full-v2", scheduler=dpm_scheduler, torch_dtype=torch.float16 +... ) ``` ## AudioLDMPipeline