Merge branch 'main' into lora/improve-docs

Author: sayakpaul

docs/source/en/_toctree.yml

@@ -105,6 +105,8 @@
     title: MPS
   - local: optimization/habana
     title: Habana Gaudi
+  - local: optimization/tome
+    title: Token Merging
   title: Optimization/Special Hardware
 - sections:
   - local: conceptual/philosophy
@@ -152,6 +154,8 @@
       title: DDPM
     - local: api/pipelines/dit
       title: DiT
+    - local: api/pipelines/if
+      title: IF
     - local: api/pipelines/latent_diffusion
       title: Latent Diffusion
     - local: api/pipelines/paint_by_example
@@ -262,6 +266,8 @@
       title: VP-SDE
     - local: api/schedulers/vq_diffusion
       title: VQDiffusionScheduler
+    - local: api/schedulers/dpm_sde
+      title: DPMSolverSDEScheduler
     title: Schedulers
   - sections:
     - local: api/experimental/rl

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 +68,14 @@ 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