Merge branch 'main' into enable-cp-kernels

Remove `*pooled_*` mentions from Chroma as it has just one TE.

docker/diffusers-pytorch-cuda/Dockerfile

@@ -2,7 +2,7 @@ FROM nvidia/cuda:12.1.0-runtime-ubuntu20.04
 LABEL maintainer="Hugging Face"
 LABEL repository="diffusers"
 
-ARG PYTHON_VERSION=3.12
+ARG PYTHON_VERSION=3.11
 ENV DEBIAN_FRONTEND=noninteractive
 
 RUN apt-get -y update \
@@ -32,10 +32,12 @@ RUN uv venv --python ${PYTHON_VERSION} --seed ${VIRTUAL_ENV}
 ENV PATH="$VIRTUAL_ENV/bin:$PATH"
 
 # pre-install the heavy dependencies (these can later be overridden by the deps from setup.py)
+# Install torch, torchvision, and torchaudio together to ensure compatibility
 RUN uv pip install --no-cache-dir \
     torch \
     torchvision \
-    torchaudio
+    torchaudio \
+    --index-url https://download.pytorch.org/whl/cu121
 
 RUN uv pip install --no-cache-dir "git+https://github.com/huggingface/diffusers.git@main#egg=diffusers[test]"
 

docker/diffusers-pytorch-xformers-cuda/Dockerfile

@@ -2,7 +2,7 @@ FROM nvidia/cuda:12.1.0-runtime-ubuntu20.04
 LABEL maintainer="Hugging Face"
 LABEL repository="diffusers"
 
-ARG PYTHON_VERSION=3.12
+ARG PYTHON_VERSION=3.11
 ENV DEBIAN_FRONTEND=noninteractive
 
 RUN apt-get -y update \
@@ -32,10 +32,12 @@ RUN uv venv --python ${PYTHON_VERSION} --seed ${VIRTUAL_ENV}
 ENV PATH="$VIRTUAL_ENV/bin:$PATH"
 
 # pre-install the heavy dependencies (these can later be overridden by the deps from setup.py)
+# Install torch, torchvision, and torchaudio together to ensure compatibility
 RUN uv pip install --no-cache-dir \
     torch \
     torchvision \
-    torchaudio
+    torchaudio \
+    --index-url https://download.pytorch.org/whl/cu121
 
 RUN uv pip install --no-cache-dir "git+https://github.com/huggingface/diffusers.git@main#egg=diffusers[test]"
 

src/diffusers/loaders/peft.py

@@ -478,7 +478,7 @@ class PeftAdapterMixin:
         Args:
             adapter_names (`List[str]` or `str`):
                 The names of the adapters to use.
-            adapter_weights (`Union[List[float], float]`, *optional*):
+            weights (`Union[List[float], float]`, *optional*):
                 The adapter(s) weights to use with the UNet. If `None`, the weights are set to `1.0` for all the
                 adapters.
 
@@ -495,7 +495,7 @@ class PeftAdapterMixin:
             "jbilcke-hf/sdxl-cinematic-1", weight_name="pytorch_lora_weights.safetensors", adapter_name="cinematic"
         )
         pipeline.load_lora_weights("nerijs/pixel-art-xl", weight_name="pixel-art-xl.safetensors", adapter_name="pixel")
-        pipeline.unet.set_adapters(["cinematic", "pixel"], adapter_weights=[0.5, 0.5])
+        pipeline.unet.set_adapters(["cinematic", "pixel"], weights=[0.5, 0.5])
         ```
         """
         if not USE_PEFT_BACKEND:

src/diffusers/models/attention_dispatch.py

@@ -260,6 +260,10 @@ class _HubKernelConfig:
     function_attr: str
     revision: Optional[str] = None
     kernel_fn: Optional[Callable] = None
+    wrapped_forward_attr: Optional[str] = None
+    wrapped_backward_attr: Optional[str] = None
+    wrapped_forward_fn: Optional[Callable] = None
+    wrapped_backward_fn: Optional[Callable] = None
 
 
 # Registry for hub-based attention kernels
@@ -274,7 +278,11 @@ _HUB_KERNELS_REGISTRY: Dict["AttentionBackendName", _HubKernelConfig] = {
         # revision="fake-ops-return-probs",
     ),
     AttentionBackendName.FLASH_HUB: _HubKernelConfig(
-        repo_id="kernels-community/flash-attn2", function_attr="flash_attn_func", revision=None
+        repo_id="kernels-community/flash-attn2",
+        function_attr="flash_attn_func",
+        revision=None,
+        wrapped_forward_attr="flash_attn_interface._wrapped_flash_attn_forward",
+        wrapped_backward_attr="flash_attn_interface._wrapped_flash_attn_backward",
     ),
     AttentionBackendName.FLASH_VARLEN_HUB: _HubKernelConfig(
         repo_id="kernels-community/flash-attn2", function_attr="flash_attn_varlen_func", revision=None
@@ -599,22 +607,39 @@ def _flex_attention_causal_mask_mod(batch_idx, head_idx, q_idx, kv_idx):
 
 
 # ===== Helpers for downloading kernels =====
+def _resolve_kernel_attr(module, attr_path: str):
+    target = module
+    for attr in attr_path.split("."):
+        if not hasattr(target, attr):
+            raise AttributeError(f"Kernel module '{module.__name__}' does not define attribute path '{attr_path}'.")
+        target = getattr(target, attr)
+    return target
+
+
 def _maybe_download_kernel_for_backend(backend: AttentionBackendName) -> None:
     if backend not in _HUB_KERNELS_REGISTRY:
         return
     config = _HUB_KERNELS_REGISTRY[backend]
 
-    if config.kernel_fn is not None:
+    needs_kernel = config.kernel_fn is None
+    needs_wrapped_forward = config.wrapped_forward_attr is not None and config.wrapped_forward_fn is None
+    needs_wrapped_backward = config.wrapped_backward_attr is not None and config.wrapped_backward_fn is None
+
+    if not (needs_kernel or needs_wrapped_forward or needs_wrapped_backward):
         return
 
     try:
         from kernels import get_kernel
 
         kernel_module = get_kernel(config.repo_id, revision=config.revision)
-        kernel_func = getattr(kernel_module, config.function_attr)
+        if needs_kernel:
+            config.kernel_fn = _resolve_kernel_attr(kernel_module, config.function_attr)
 
-        # Cache the downloaded kernel function in the config object
-        config.kernel_fn = kernel_func
+        if needs_wrapped_forward:
+            config.wrapped_forward_fn = _resolve_kernel_attr(kernel_module, config.wrapped_forward_attr)
+
+        if needs_wrapped_backward:
+            config.wrapped_backward_fn = _resolve_kernel_attr(kernel_module, config.wrapped_backward_attr)
 
     except Exception as e:
         logger.error(f"An error occurred while fetching kernel '{config.repo_id}' from the Hub: {e}")
@@ -1065,6 +1090,231 @@ def _flash_attention_backward_op(
     return grad_query, grad_key, grad_value
 
 
+def _flash_attention_hub_forward_op(
+    ctx: torch.autograd.function.FunctionCtx,
+    query: torch.Tensor,
+    key: torch.Tensor,
+    value: torch.Tensor,
+    attn_mask: Optional[torch.Tensor] = None,
+    dropout_p: float = 0.0,
+    is_causal: bool = False,
+    scale: Optional[float] = None,
+    enable_gqa: bool = False,
+    return_lse: bool = False,
+    _save_ctx: bool = True,
+    _parallel_config: Optional["ParallelConfig"] = None,
+):
+    if attn_mask is not None:
+        raise ValueError("`attn_mask` is not yet supported for flash-attn hub kernels.")
+    if enable_gqa:
+        raise ValueError("`enable_gqa` is not yet supported for flash-attn hub kernels.")
+
+    config = _HUB_KERNELS_REGISTRY[AttentionBackendName.FLASH_HUB]
+    wrapped_forward_fn = config.wrapped_forward_fn
+    wrapped_backward_fn = config.wrapped_backward_fn
+    if wrapped_forward_fn is None or wrapped_backward_fn is None:
+        raise RuntimeError(
+            "Flash attention hub kernels must expose `_wrapped_flash_attn_forward` and `_wrapped_flash_attn_backward` "
+            "for context parallel execution."
+        )
+
+    if scale is None:
+        scale = query.shape[-1] ** (-0.5)
+
+    window_size = (-1, -1)
+    softcap = 0.0
+    alibi_slopes = None
+    deterministic = False
+    grad_enabled = any(x.requires_grad for x in (query, key, value))
+
+    if grad_enabled or (_parallel_config is not None and _parallel_config.context_parallel_config._world_size > 1):
+        dropout_p = dropout_p if dropout_p > 0 else 1e-30
+
+    with torch.set_grad_enabled(grad_enabled):
+        out, lse, S_dmask, rng_state = wrapped_forward_fn(
+            query,
+            key,
+            value,
+            dropout_p,
+            scale,
+            is_causal,
+            window_size[0],
+            window_size[1],
+            softcap,
+            alibi_slopes,
+            return_lse,
+        )
+        lse = lse.permute(0, 2, 1).contiguous()
+
+    if _save_ctx:
+        ctx.save_for_backward(query, key, value, out, lse, rng_state)
+        ctx.dropout_p = dropout_p
+        ctx.scale = scale
+        ctx.is_causal = is_causal
+        ctx.window_size = window_size
+        ctx.softcap = softcap
+        ctx.alibi_slopes = alibi_slopes
+        ctx.deterministic = deterministic
+
+    return (out, lse) if return_lse else out
+
+
+def _flash_attention_hub_backward_op(
+    ctx: torch.autograd.function.FunctionCtx,
+    grad_out: torch.Tensor,
+    *args,
+    **kwargs,
+):
+    config = _HUB_KERNELS_REGISTRY[AttentionBackendName.FLASH_HUB]
+    wrapped_backward_fn = config.wrapped_backward_fn
+    if wrapped_backward_fn is None:
+        raise RuntimeError(
+            "Flash attention hub kernels must expose `_wrapped_flash_attn_backward` for context parallel execution."
+        )
+
+    query, key, value, out, lse, rng_state = ctx.saved_tensors
+    grad_query, grad_key, grad_value = torch.empty_like(query), torch.empty_like(key), torch.empty_like(value)
+
+    _ = wrapped_backward_fn(
+        grad_out,
+        query,
+        key,
+        value,
+        out,
+        lse,
+        grad_query,
+        grad_key,
+        grad_value,
+        ctx.dropout_p,
+        ctx.scale,
+        ctx.is_causal,
+        ctx.window_size[0],
+        ctx.window_size[1],
+        ctx.softcap,
+        ctx.alibi_slopes,
+        ctx.deterministic,
+        rng_state,
+    )
+
+    grad_query = grad_query[..., : grad_out.shape[-1]]
+    grad_key = grad_key[..., : grad_out.shape[-1]]
+    grad_value = grad_value[..., : grad_out.shape[-1]]
+
+    return grad_query, grad_key, grad_value
+
+
+def _flash_attention_3_hub_forward_op(
+    ctx: torch.autograd.function.FunctionCtx,
+    query: torch.Tensor,
+    key: torch.Tensor,
+    value: torch.Tensor,
+    attn_mask: Optional[torch.Tensor] = None,
+    dropout_p: float = 0.0,
+    is_causal: bool = False,
+    scale: Optional[float] = None,
+    enable_gqa: bool = False,
+    return_lse: bool = False,
+    _save_ctx: bool = True,
+    _parallel_config: Optional["ParallelConfig"] = None,
+    *,
+    window_size: Tuple[int, int] = (-1, -1),
+    softcap: float = 0.0,
+    num_splits: int = 1,
+    pack_gqa: Optional[bool] = None,
+    deterministic: bool = False,
+    sm_margin: int = 0,
+):
+    if attn_mask is not None:
+        raise ValueError("`attn_mask` is not yet supported for flash-attn 3 hub kernels.")
+    if dropout_p != 0.0:
+        raise ValueError("`dropout_p` is not yet supported for flash-attn 3 hub kernels.")
+    if enable_gqa:
+        raise ValueError("`enable_gqa` is not yet supported for flash-attn 3 hub kernels.")
+
+    func = _HUB_KERNELS_REGISTRY[AttentionBackendName._FLASH_3_HUB].kernel_fn
+    out = func(
+        q=query,
+        k=key,
+        v=value,
+        softmax_scale=scale,
+        causal=is_causal,
+        qv=None,
+        q_descale=None,
+        k_descale=None,
+        v_descale=None,
+        window_size=window_size,
+        softcap=softcap,
+        num_splits=num_splits,
+        pack_gqa=pack_gqa,
+        deterministic=deterministic,
+        sm_margin=sm_margin,
+        return_attn_probs=return_lse,
+    )
+
+    lse = None
+    if return_lse:
+        out, lse = out
+        lse = lse.permute(0, 2, 1).contiguous()
+
+    if _save_ctx:
+        ctx.save_for_backward(query, key, value)
+        ctx.scale = scale
+        ctx.is_causal = is_causal
+        ctx._hub_kernel = func
+
+    return (out, lse) if return_lse else out
+
+
+def _flash_attention_3_hub_backward_op(
+    ctx: torch.autograd.function.FunctionCtx,
+    grad_out: torch.Tensor,
+    *args,
+    window_size: Tuple[int, int] = (-1, -1),
+    softcap: float = 0.0,
+    num_splits: int = 1,
+    pack_gqa: Optional[bool] = None,
+    deterministic: bool = False,
+    sm_margin: int = 0,
+):
+    query, key, value = ctx.saved_tensors
+    kernel_fn = ctx._hub_kernel
+    with torch.enable_grad():
+        query_r = query.detach().requires_grad_(True)
+        key_r = key.detach().requires_grad_(True)
+        value_r = value.detach().requires_grad_(True)
+
+        out = kernel_fn(
+            q=query_r,
+            k=key_r,
+            v=value_r,
+            softmax_scale=ctx.scale,
+            causal=ctx.is_causal,
+            qv=None,
+            q_descale=None,
+            k_descale=None,
+            v_descale=None,
+            window_size=window_size,
+            softcap=softcap,
+            num_splits=num_splits,
+            pack_gqa=pack_gqa,
+            deterministic=deterministic,
+            sm_margin=sm_margin,
+            return_attn_probs=False,
+        )
+        if isinstance(out, tuple):
+            out = out[0]
+
+        grad_query, grad_key, grad_value = torch.autograd.grad(
+            out,
+            (query_r, key_r, value_r),
+            grad_out,
+            retain_graph=False,
+            allow_unused=False,
+        )
+
+    return grad_query, grad_key, grad_value
+
+
 def _sage_attention_forward_op(
     ctx: torch.autograd.function.FunctionCtx,
     query: torch.Tensor,
@@ -1103,6 +1353,46 @@ def _sage_attention_forward_op(
     return (out, lse) if return_lse else out
 
 
+def _sage_attention_hub_forward_op(
+    ctx: torch.autograd.function.FunctionCtx,
+    query: torch.Tensor,
+    key: torch.Tensor,
+    value: torch.Tensor,
+    attn_mask: Optional[torch.Tensor] = None,
+    dropout_p: float = 0.0,
+    is_causal: bool = False,
+    scale: Optional[float] = None,
+    enable_gqa: bool = False,
+    return_lse: bool = False,
+    _save_ctx: bool = True,
+    _parallel_config: Optional["ParallelConfig"] = None,
+):
+    if attn_mask is not None:
+        raise ValueError("`attn_mask` is not yet supported for Sage attention.")
+    if dropout_p > 0.0:
+        raise ValueError("`dropout_p` is not yet supported for Sage attention.")
+    if enable_gqa:
+        raise ValueError("`enable_gqa` is not yet supported for Sage attention.")
+
+    func = _HUB_KERNELS_REGISTRY[AttentionBackendName.SAGE_HUB].kernel_fn
+    out = func(
+        q=query,
+        k=key,
+        v=value,
+        tensor_layout="NHD",
+        is_causal=is_causal,
+        sm_scale=scale,
+        return_lse=return_lse,
+    )
+
+    lse = None
+    if return_lse:
+        out, lse, *_ = out
+        lse = lse.permute(0, 2, 1).contiguous()
+
+    return (out, lse) if return_lse else out
+
+
 def _sage_attention_backward_op(
     ctx: torch.autograd.function.FunctionCtx,
     grad_out: torch.Tensor,
@@ -1695,7 +1985,7 @@ def _flash_attention(
 @_AttentionBackendRegistry.register(
     AttentionBackendName.FLASH_HUB,
     constraints=[_check_device, _check_qkv_dtype_bf16_or_fp16, _check_shape],
-    supports_context_parallel=False,
+    supports_context_parallel=True,
 )
 def _flash_attention_hub(
     query: torch.Tensor,
@@ -1713,17 +2003,35 @@ def _flash_attention_hub(
         raise ValueError("`attn_mask` is not supported for flash-attn 2.")
 
     func = _HUB_KERNELS_REGISTRY[AttentionBackendName.FLASH_HUB].kernel_fn
-    out = func(
-        q=query,
-        k=key,
-        v=value,
-        dropout_p=dropout_p,
-        softmax_scale=scale,
-        causal=is_causal,
-        return_attn_probs=return_lse,
-    )
-    if return_lse:
-        out, lse, *_ = out
+    if _parallel_config is None:
+        out = func(
+            q=query,
+            k=key,
+            v=value,
+            dropout_p=dropout_p,
+            softmax_scale=scale,
+            causal=is_causal,
+            return_attn_probs=return_lse,
+        )
+        if return_lse:
+            out, lse, *_ = out
+    else:
+        out = _templated_context_parallel_attention(
+            query,
+            key,
+            value,
+            None,
+            dropout_p,
+            is_causal,
+            scale,
+            False,
+            return_lse,
+            forward_op=_flash_attention_hub_forward_op,
+            backward_op=_flash_attention_hub_backward_op,
+            _parallel_config=_parallel_config,
+        )
+        if return_lse:
+            out, lse = out
 
     return (out, lse) if return_lse else out
 
@@ -1870,7 +2178,7 @@ def _flash_attention_3(
 @_AttentionBackendRegistry.register(
     AttentionBackendName._FLASH_3_HUB,
     constraints=[_check_device, _check_qkv_dtype_bf16_or_fp16, _check_shape],
-    supports_context_parallel=False,
+    supports_context_parallel=True,
 )
 def _flash_attention_3_hub(
     query: torch.Tensor,
@@ -1885,33 +2193,68 @@ def _flash_attention_3_hub(
     return_attn_probs: bool = False,
     _parallel_config: Optional["ParallelConfig"] = None,
 ) -> torch.Tensor:
-    if _parallel_config:
-        raise NotImplementedError(f"{AttentionBackendName._FLASH_3_HUB.value} is not implemented for parallelism yet.")
     if attn_mask is not None:
         raise ValueError("`attn_mask` is not supported for flash-attn 3.")
 
     func = _HUB_KERNELS_REGISTRY[AttentionBackendName._FLASH_3_HUB].kernel_fn
-    out = func(
-        q=query,
-        k=key,
-        v=value,
-        softmax_scale=scale,
-        causal=is_causal,
-        qv=None,
-        q_descale=None,
-        k_descale=None,
-        v_descale=None,
+    if _parallel_config is None:
+        out = func(
+            q=query,
+            k=key,
+            v=value,
+            softmax_scale=scale,
+            causal=is_causal,
+            qv=None,
+            q_descale=None,
+            k_descale=None,
+            v_descale=None,
+            window_size=window_size,
+            softcap=softcap,
+            num_splits=1,
+            pack_gqa=None,
+            deterministic=deterministic,
+            sm_margin=0,
+            return_attn_probs=return_attn_probs,
+        )
+        return (out[0], out[1]) if return_attn_probs else out
+
+    forward_op = functools.partial(
+        _flash_attention_3_hub_forward_op,
         window_size=window_size,
         softcap=softcap,
         num_splits=1,
         pack_gqa=None,
         deterministic=deterministic,
         sm_margin=0,
-        return_attn_probs=return_attn_probs,
     )
-    # When `return_attn_probs` is True, the above returns a tuple of
-    # actual outputs and lse.
-    return (out[0], out[1]) if return_attn_probs else out
+    backward_op = functools.partial(
+        _flash_attention_3_hub_backward_op,
+        window_size=window_size,
+        softcap=softcap,
+        num_splits=1,
+        pack_gqa=None,
+        deterministic=deterministic,
+        sm_margin=0,
+    )
+    out = _templated_context_parallel_attention(
+        query,
+        key,
+        value,
+        None,
+        0.0,
+        is_causal,
+        scale,
+        False,
+        return_attn_probs,
+        forward_op=forward_op,
+        backward_op=backward_op,
+        _parallel_config=_parallel_config,
+    )
+    if return_attn_probs:
+        out, lse = out
+        return out, lse
+
+    return out
 
 
 @_AttentionBackendRegistry.register(
@@ -2542,7 +2885,7 @@ def _sage_attention(
 @_AttentionBackendRegistry.register(
     AttentionBackendName.SAGE_HUB,
     constraints=[_check_device_cuda, _check_qkv_dtype_bf16_or_fp16, _check_shape],
-    supports_context_parallel=False,
+    supports_context_parallel=True,
 )
 def _sage_attention_hub(
     query: torch.Tensor,
@@ -2570,6 +2913,23 @@ def _sage_attention_hub(
         )
         if return_lse:
             out, lse, *_ = out
+    else:
+        out = _templated_context_parallel_attention(
+            query,
+            key,
+            value,
+            None,
+            0.0,
+            is_causal,
+            scale,
+            False,
+            return_lse,
+            forward_op=_sage_attention_hub_forward_op,
+            backward_op=_sage_attention_backward_op,
+            _parallel_config=_parallel_config,
+        )
+        if return_lse:
+            out, lse = out
 
     return (out, lse) if return_lse else out
 

src/diffusers/models/resnet.py

@@ -366,7 +366,12 @@ class ResnetBlock2D(nn.Module):
         hidden_states = self.conv2(hidden_states)
 
         if self.conv_shortcut is not None:
-            input_tensor = self.conv_shortcut(input_tensor.contiguous())
+            # Only use contiguous() during training to avoid DDP gradient stride mismatch warning.
+            # In inference mode (eval or no_grad), skip contiguous() for better performance, especially on CPU.
+            # Issue: https://github.com/huggingface/diffusers/issues/12975
+            if self.training:
+                input_tensor = input_tensor.contiguous()
+            input_tensor = self.conv_shortcut(input_tensor)
 
         output_tensor = (input_tensor + hidden_states) / self.output_scale_factor
 

src/diffusers/models/transformers/transformer_longcat_image.py

@@ -23,7 +23,7 @@ from ...configuration_utils import ConfigMixin, register_to_config
 from ...loaders import FromOriginalModelMixin, PeftAdapterMixin
 from ...utils import logging
 from ...utils.torch_utils import maybe_allow_in_graph
-from ..attention import AttentionModuleMixin, FeedForward
+from ..attention import AttentionMixin, AttentionModuleMixin, FeedForward
 from ..attention_dispatch import dispatch_attention_fn
 from ..cache_utils import CacheMixin
 from ..embeddings import TimestepEmbedding, Timesteps, apply_rotary_emb, get_1d_rotary_pos_embed
@@ -400,12 +400,14 @@ class LongCatImageTransformer2DModel(
     PeftAdapterMixin,
     FromOriginalModelMixin,
     CacheMixin,
+    AttentionMixin,
 ):
     """
     The Transformer model introduced in Longcat-Image.
     """
 
     _supports_gradient_checkpointing = True
+    _repeated_blocks = ["LongCatImageTransformerBlock", "LongCatImageSingleTransformerBlock"]
 
     @register_to_config
     def __init__(

src/diffusers/pipelines/chroma/pipeline_chroma_inpainting.py

@@ -482,8 +482,6 @@ class ChromaInpaintPipeline(
         negative_prompt=None,
         prompt_embeds=None,
         negative_prompt_embeds=None,
-        pooled_prompt_embeds=None,
-        negative_pooled_prompt_embeds=None,
         callback_on_step_end_tensor_inputs=None,
         padding_mask_crop=None,
         max_sequence_length=None,
@@ -531,15 +529,6 @@ class ChromaInpaintPipeline(
                     f" {negative_prompt_embeds.shape}."
                 )
 
-        if prompt_embeds is not None and pooled_prompt_embeds is None:
-            raise ValueError(
-                "If `prompt_embeds` are provided, `pooled_prompt_embeds` also have to be passed. Make sure to generate `pooled_prompt_embeds` from the same text encoder that was used to generate `prompt_embeds`."
-            )
-        if negative_prompt_embeds is not None and negative_pooled_prompt_embeds is None:
-            raise ValueError(
-                "If `negative_prompt_embeds` are provided, `negative_pooled_prompt_embeds` also have to be passed. Make sure to generate `negative_pooled_prompt_embeds` from the same text encoder that was used to generate `negative_prompt_embeds`."
-            )
-
         if prompt_embeds is not None and prompt_attention_mask is None:
             raise ValueError("Cannot provide `prompt_embeds` without also providing `prompt_attention_mask")
 
@@ -793,13 +782,11 @@ class ChromaInpaintPipeline(
         generator: Optional[Union[torch.Generator, List[torch.Generator]]] = None,
         latents: Optional[torch.FloatTensor] = None,
         prompt_embeds: Optional[torch.FloatTensor] = None,
-        pooled_prompt_embeds: Optional[torch.FloatTensor] = None,
         ip_adapter_image: Optional[PipelineImageInput] = None,
         ip_adapter_image_embeds: Optional[List[torch.Tensor]] = None,
         negative_ip_adapter_image: Optional[PipelineImageInput] = None,
         negative_ip_adapter_image_embeds: Optional[List[torch.Tensor]] = None,
         negative_prompt_embeds: Optional[torch.FloatTensor] = None,
-        negative_pooled_prompt_embeds: Optional[torch.FloatTensor] = None,
         output_type: Optional[str] = "pil",
         return_dict: bool = True,
         joint_attention_kwargs: Optional[Dict[str, Any]] = None,

src/diffusers/schedulers/scheduling_consistency_decoder.py

@@ -14,7 +14,7 @@ from .scheduling_utils import SchedulerMixin
 def betas_for_alpha_bar(
     num_diffusion_timesteps: int,
     max_beta: float = 0.999,
-    alpha_transform_type: Literal["cosine", "exp"] = "cosine",
+    alpha_transform_type: Literal["cosine", "exp", "laplace"] = "cosine",
 ) -> torch.Tensor:
     """
     Create a beta schedule that discretizes the given alpha_t_bar function, which defines the cumulative product of
@@ -28,8 +28,8 @@ def betas_for_alpha_bar(
             The number of betas to produce.
         max_beta (`float`, defaults to `0.999`):
             The maximum beta to use; use values lower than 1 to avoid numerical instability.
-        alpha_transform_type (`"cosine"` or `"exp"`, defaults to `"cosine"`):
-            The type of noise schedule for `alpha_bar`. Choose from `cosine` or `exp`.
+        alpha_transform_type (`str`, defaults to `"cosine"`):
+            The type of noise schedule for `alpha_bar`. Choose from `cosine`, `exp`, or `laplace`.
 
     Returns:
         `torch.Tensor`:

src/diffusers/schedulers/scheduling_ddim.py

@@ -51,7 +51,7 @@ class DDIMSchedulerOutput(BaseOutput):
 def betas_for_alpha_bar(
     num_diffusion_timesteps: int,
     max_beta: float = 0.999,
-    alpha_transform_type: Literal["cosine", "exp"] = "cosine",
+    alpha_transform_type: Literal["cosine", "exp", "laplace"] = "cosine",
 ) -> torch.Tensor:
     """
     Create a beta schedule that discretizes the given alpha_t_bar function, which defines the cumulative product of
@@ -65,8 +65,8 @@ def betas_for_alpha_bar(
             The number of betas to produce.
         max_beta (`float`, defaults to `0.999`):
             The maximum beta to use; use values lower than 1 to avoid numerical instability.
-        alpha_transform_type (`"cosine"` or `"exp"`, defaults to `"cosine"`):
-            The type of noise schedule for `alpha_bar`. Choose from `cosine` or `exp`.
+        alpha_transform_type (`str`, defaults to `"cosine"`):
+            The type of noise schedule for `alpha_bar`. Choose from `cosine`, `exp`, or `laplace`.
 
     Returns:
         `torch.Tensor`:

src/diffusers/schedulers/scheduling_ddim_cogvideox.py

@@ -51,7 +51,7 @@ class DDIMSchedulerOutput(BaseOutput):
 def betas_for_alpha_bar(
     num_diffusion_timesteps: int,
     max_beta: float = 0.999,
-    alpha_transform_type: Literal["cosine", "exp"] = "cosine",
+    alpha_transform_type: Literal["cosine", "exp", "laplace"] = "cosine",
 ) -> torch.Tensor:
     """
     Create a beta schedule that discretizes the given alpha_t_bar function, which defines the cumulative product of
@@ -65,8 +65,8 @@ def betas_for_alpha_bar(
             The number of betas to produce.
         max_beta (`float`, defaults to `0.999`):
             The maximum beta to use; use values lower than 1 to avoid numerical instability.
-        alpha_transform_type (`"cosine"` or `"exp"`, defaults to `"cosine"`):
-            The type of noise schedule for `alpha_bar`. Choose from `cosine` or `exp`.
+        alpha_transform_type (`str`, defaults to `"cosine"`):
+            The type of noise schedule for `alpha_bar`. Choose from `cosine`, `exp`, or `laplace`.
 
     Returns:
         `torch.Tensor`:
@@ -100,14 +100,13 @@ def betas_for_alpha_bar(
     return torch.tensor(betas, dtype=torch.float32)
 
 
-def rescale_zero_terminal_snr(alphas_cumprod):
+def rescale_zero_terminal_snr(alphas_cumprod: torch.Tensor) -> torch.Tensor:
     """
-    Rescales betas to have zero terminal SNR Based on https://huggingface.co/papers/2305.08891 (Algorithm 1)
-
+    Rescales betas to have zero terminal SNR Based on (Algorithm 1)[https://huggingface.co/papers/2305.08891]
 
     Args:
-        betas (`torch.Tensor`):
-            the betas that the scheduler is being initialized with.
+        alphas_cumprod (`torch.Tensor`):
+            The alphas cumulative products that the scheduler is being initialized with.
 
     Returns:
         `torch.Tensor`: rescaled betas with zero terminal SNR
@@ -142,11 +141,11 @@ class CogVideoXDDIMScheduler(SchedulerMixin, ConfigMixin):
     Args:
         num_train_timesteps (`int`, defaults to 1000):
             The number of diffusion steps to train the model.
-        beta_start (`float`, defaults to 0.0001):
+        beta_start (`float`, defaults to 0.00085):
             The starting `beta` value of inference.
-        beta_end (`float`, defaults to 0.02):
+        beta_end (`float`, defaults to 0.0120):
             The final `beta` value.
-        beta_schedule (`str`, defaults to `"linear"`):
+        beta_schedule (`str`, defaults to `"scaled_linear"`):
             The beta schedule, a mapping from a beta range to a sequence of betas for stepping the model. Choose from
             `linear`, `scaled_linear`, or `squaredcos_cap_v2`.
         trained_betas (`np.ndarray`, *optional*):
@@ -179,6 +178,8 @@ class CogVideoXDDIMScheduler(SchedulerMixin, ConfigMixin):
             Whether to rescale the betas to have zero terminal SNR. This enables the model to generate very bright and
             dark samples instead of limiting it to samples with medium brightness. Loosely related to
             [`--offset_noise`](https://github.com/huggingface/diffusers/blob/74fd735eb073eb1d774b1ab4154a0876eb82f055/examples/dreambooth/train_dreambooth.py#L506).
+        snr_shift_scale (`float`, defaults to 3.0):
+            Shift scale for SNR.
     """
 
     _compatibles = [e.name for e in KarrasDiffusionSchedulers]
@@ -190,15 +191,15 @@ class CogVideoXDDIMScheduler(SchedulerMixin, ConfigMixin):
         num_train_timesteps: int = 1000,
         beta_start: float = 0.00085,
         beta_end: float = 0.0120,
-        beta_schedule: str = "scaled_linear",
+        beta_schedule: Literal["linear", "scaled_linear", "squaredcos_cap_v2"] = "scaled_linear",
         trained_betas: Optional[Union[np.ndarray, List[float]]] = None,
         clip_sample: bool = True,
         set_alpha_to_one: bool = True,
         steps_offset: int = 0,
-        prediction_type: str = "epsilon",
+        prediction_type: Literal["epsilon", "sample", "v_prediction"] = "epsilon",
         clip_sample_range: float = 1.0,
         sample_max_value: float = 1.0,
-        timestep_spacing: str = "leading",
+        timestep_spacing: Literal["linspace", "leading", "trailing"] = "leading",
         rescale_betas_zero_snr: bool = False,
         snr_shift_scale: float = 3.0,
     ):
@@ -208,7 +209,15 @@ class CogVideoXDDIMScheduler(SchedulerMixin, ConfigMixin):
             self.betas = torch.linspace(beta_start, beta_end, num_train_timesteps, dtype=torch.float32)
         elif beta_schedule == "scaled_linear":
             # this schedule is very specific to the latent diffusion model.
-            self.betas = torch.linspace(beta_start**0.5, beta_end**0.5, num_train_timesteps, dtype=torch.float64) ** 2
+            self.betas = (
+                torch.linspace(
+                    beta_start**0.5,
+                    beta_end**0.5,
+                    num_train_timesteps,
+                    dtype=torch.float64,
+                )
+                ** 2
+            )
         elif beta_schedule == "squaredcos_cap_v2":
             # Glide cosine schedule
             self.betas = betas_for_alpha_bar(num_train_timesteps)
@@ -238,7 +247,7 @@ class CogVideoXDDIMScheduler(SchedulerMixin, ConfigMixin):
         self.num_inference_steps = None
         self.timesteps = torch.from_numpy(np.arange(0, num_train_timesteps)[::-1].copy().astype(np.int64))
 
-    def _get_variance(self, timestep, prev_timestep):
+    def _get_variance(self, timestep: int, prev_timestep: int) -> torch.Tensor:
         alpha_prod_t = self.alphas_cumprod[timestep]
         alpha_prod_t_prev = self.alphas_cumprod[prev_timestep] if prev_timestep >= 0 else self.final_alpha_cumprod
         beta_prod_t = 1 - alpha_prod_t
@@ -265,7 +274,11 @@ class CogVideoXDDIMScheduler(SchedulerMixin, ConfigMixin):
         """
         return sample
 
-    def set_timesteps(self, num_inference_steps: int, device: Union[str, torch.device] = None):
+    def set_timesteps(
+        self,
+        num_inference_steps: int,
+        device: Optional[Union[str, torch.device]] = None,
+    ) -> None:
         """
         Sets the discrete timesteps used for the diffusion chain (to be run before inference).
 
@@ -317,7 +330,7 @@ class CogVideoXDDIMScheduler(SchedulerMixin, ConfigMixin):
         sample: torch.Tensor,
         eta: float = 0.0,
         use_clipped_model_output: bool = False,
-        generator=None,
+        generator: Optional[torch.Generator] = None,
         variance_noise: Optional[torch.Tensor] = None,
         return_dict: bool = True,
     ) -> Union[DDIMSchedulerOutput, Tuple]:
@@ -328,7 +341,7 @@ class CogVideoXDDIMScheduler(SchedulerMixin, ConfigMixin):
         Args:
             model_output (`torch.Tensor`):
                 The direct output from learned diffusion model.
-            timestep (`float`):
+            timestep (`int`):
                 The current discrete timestep in the diffusion chain.
             sample (`torch.Tensor`):
                 A current instance of a sample created by the diffusion process.
@@ -487,5 +500,5 @@ class CogVideoXDDIMScheduler(SchedulerMixin, ConfigMixin):
         velocity = sqrt_alpha_prod * noise - sqrt_one_minus_alpha_prod * sample
         return velocity
 
-    def __len__(self):
+    def __len__(self) -> int:
         return self.config.num_train_timesteps

src/diffusers/schedulers/scheduling_ddim_flax.py

@@ -22,6 +22,7 @@ import flax
 import jax.numpy as jnp
 
 from ..configuration_utils import ConfigMixin, register_to_config
+from ..utils import logging
 from .scheduling_utils_flax import (
     CommonSchedulerState,
     FlaxKarrasDiffusionSchedulers,
@@ -32,6 +33,9 @@ from .scheduling_utils_flax import (
 )
 
 
+logger = logging.get_logger(__name__)
+
+
 @flax.struct.dataclass
 class DDIMSchedulerState:
     common: CommonSchedulerState
@@ -125,6 +129,10 @@ class FlaxDDIMScheduler(FlaxSchedulerMixin, ConfigMixin):
         prediction_type: str = "epsilon",
         dtype: jnp.dtype = jnp.float32,
     ):
+        logger.warning(
+            "Flax classes are deprecated and will be removed in Diffusers v1.0.0. We "
+            "recommend migrating to PyTorch classes or pinning your version of Diffusers."
+        )
         self.dtype = dtype
 
     def create_state(self, common: Optional[CommonSchedulerState] = None) -> DDIMSchedulerState:
@@ -152,7 +160,10 @@ class FlaxDDIMScheduler(FlaxSchedulerMixin, ConfigMixin):
         )
 
     def scale_model_input(
-        self, state: DDIMSchedulerState, sample: jnp.ndarray, timestep: Optional[int] = None
+        self,
+        state: DDIMSchedulerState,
+        sample: jnp.ndarray,
+        timestep: Optional[int] = None,
     ) -> jnp.ndarray:
         """
         Args:
@@ -190,7 +201,9 @@ class FlaxDDIMScheduler(FlaxSchedulerMixin, ConfigMixin):
     def _get_variance(self, state: DDIMSchedulerState, timestep, prev_timestep):
         alpha_prod_t = state.common.alphas_cumprod[timestep]
         alpha_prod_t_prev = jnp.where(
-            prev_timestep >= 0, state.common.alphas_cumprod[prev_timestep], state.final_alpha_cumprod
+            prev_timestep >= 0,
+            state.common.alphas_cumprod[prev_timestep],
+            state.final_alpha_cumprod,
         )
         beta_prod_t = 1 - alpha_prod_t
         beta_prod_t_prev = 1 - alpha_prod_t_prev

src/diffusers/schedulers/scheduling_ddim_inverse.py

@@ -49,7 +49,7 @@ class DDIMSchedulerOutput(BaseOutput):
 def betas_for_alpha_bar(
     num_diffusion_timesteps: int,
     max_beta: float = 0.999,
-    alpha_transform_type: Literal["cosine", "exp"] = "cosine",
+    alpha_transform_type: Literal["cosine", "exp", "laplace"] = "cosine",
 ) -> torch.Tensor:
     """
     Create a beta schedule that discretizes the given alpha_t_bar function, which defines the cumulative product of
@@ -63,8 +63,8 @@ def betas_for_alpha_bar(
             The number of betas to produce.
         max_beta (`float`, defaults to `0.999`):
             The maximum beta to use; use values lower than 1 to avoid numerical instability.
-        alpha_transform_type (`"cosine"` or `"exp"`, defaults to `"cosine"`):
-            The type of noise schedule for `alpha_bar`. Choose from `cosine` or `exp`.
+        alpha_transform_type (`str`, defaults to `"cosine"`):
+            The type of noise schedule for `alpha_bar`. Choose from `cosine`, `exp`, or `laplace`.
 
     Returns:
         `torch.Tensor`:
@@ -99,7 +99,7 @@ def betas_for_alpha_bar(
 
 
 # Copied from diffusers.schedulers.scheduling_ddim.rescale_zero_terminal_snr
-def rescale_zero_terminal_snr(betas):
+def rescale_zero_terminal_snr(betas: torch.Tensor) -> torch.Tensor:
     """
     Rescales betas to have zero terminal SNR Based on https://huggingface.co/papers/2305.08891 (Algorithm 1)
 
@@ -187,14 +187,14 @@ class DDIMInverseScheduler(SchedulerMixin, ConfigMixin):
         num_train_timesteps: int = 1000,
         beta_start: float = 0.0001,
         beta_end: float = 0.02,
-        beta_schedule: str = "linear",
+        beta_schedule: Literal["linear", "scaled_linear", "squaredcos_cap_v2"] = "linear",
         trained_betas: Optional[Union[np.ndarray, List[float]]] = None,
         clip_sample: bool = True,
         set_alpha_to_one: bool = True,
         steps_offset: int = 0,
-        prediction_type: str = "epsilon",
+        prediction_type: Literal["epsilon", "sample", "v_prediction"] = "epsilon",
         clip_sample_range: float = 1.0,
-        timestep_spacing: str = "leading",
+        timestep_spacing: Literal["leading", "trailing"] = "leading",
         rescale_betas_zero_snr: bool = False,
         **kwargs,
     ):
@@ -210,7 +210,15 @@ class DDIMInverseScheduler(SchedulerMixin, ConfigMixin):
             self.betas = torch.linspace(beta_start, beta_end, num_train_timesteps, dtype=torch.float32)
         elif beta_schedule == "scaled_linear":
             # this schedule is very specific to the latent diffusion model.
-            self.betas = torch.linspace(beta_start**0.5, beta_end**0.5, num_train_timesteps, dtype=torch.float32) ** 2
+            self.betas = (
+                torch.linspace(
+                    beta_start**0.5,
+                    beta_end**0.5,
+                    num_train_timesteps,
+                    dtype=torch.float32,
+                )
+                ** 2
+            )
         elif beta_schedule == "squaredcos_cap_v2":
             # Glide cosine schedule
             self.betas = betas_for_alpha_bar(num_train_timesteps)
@@ -256,7 +264,11 @@ class DDIMInverseScheduler(SchedulerMixin, ConfigMixin):
         """
         return sample
 
-    def set_timesteps(self, num_inference_steps: int, device: Union[str, torch.device] = None):
+    def set_timesteps(
+        self,
+        num_inference_steps: int,
+        device: Optional[Union[str, torch.device]] = None,
+    ) -> None:
         """
         Sets the discrete timesteps used for the diffusion chain (to be run before inference).
 
@@ -308,20 +320,10 @@ class DDIMInverseScheduler(SchedulerMixin, ConfigMixin):
         Args:
             model_output (`torch.Tensor`):
                 The direct output from learned diffusion model.
-            timestep (`float`):
+            timestep (`int`):
                 The current discrete timestep in the diffusion chain.
             sample (`torch.Tensor`):
                 A current instance of a sample created by the diffusion process.
-            eta (`float`):
-                The weight of noise for added noise in diffusion step.
-            use_clipped_model_output (`bool`, defaults to `False`):
-                If `True`, computes "corrected" `model_output` from the clipped predicted original sample. Necessary
-                because predicted original sample is clipped to [-1, 1] when `self.config.clip_sample` is `True`. If no
-                clipping has happened, "corrected" `model_output` would coincide with the one provided as input and
-                `use_clipped_model_output` has no effect.
-            variance_noise (`torch.Tensor`):
-                Alternative to generating noise with `generator` by directly providing the noise for the variance
-                itself. Useful for methods such as [`CycleDiffusion`].
             return_dict (`bool`, *optional*, defaults to `True`):
                 Whether or not to return a [`~schedulers.scheduling_ddim_inverse.DDIMInverseSchedulerOutput`] or
                 `tuple`.
@@ -335,7 +337,8 @@ class DDIMInverseScheduler(SchedulerMixin, ConfigMixin):
         # 1. get previous step value (=t+1)
         prev_timestep = timestep
         timestep = min(
-            timestep - self.config.num_train_timesteps // self.num_inference_steps, self.config.num_train_timesteps - 1
+            timestep - self.config.num_train_timesteps // self.num_inference_steps,
+            self.config.num_train_timesteps - 1,
         )
 
         # 2. compute alphas, betas
@@ -378,5 +381,5 @@ class DDIMInverseScheduler(SchedulerMixin, ConfigMixin):
             return (prev_sample, pred_original_sample)
         return DDIMSchedulerOutput(prev_sample=prev_sample, pred_original_sample=pred_original_sample)
 
-    def __len__(self):
+    def __len__(self) -> int:
         return self.config.num_train_timesteps

src/diffusers/schedulers/scheduling_ddim_parallel.py

@@ -51,7 +51,7 @@ class DDIMParallelSchedulerOutput(BaseOutput):
 def betas_for_alpha_bar(
     num_diffusion_timesteps: int,
     max_beta: float = 0.999,
-    alpha_transform_type: Literal["cosine", "exp"] = "cosine",
+    alpha_transform_type: Literal["cosine", "exp", "laplace"] = "cosine",
 ) -> torch.Tensor:
     """
     Create a beta schedule that discretizes the given alpha_t_bar function, which defines the cumulative product of
@@ -65,8 +65,8 @@ def betas_for_alpha_bar(
             The number of betas to produce.
         max_beta (`float`, defaults to `0.999`):
             The maximum beta to use; use values lower than 1 to avoid numerical instability.
-        alpha_transform_type (`"cosine"` or `"exp"`, defaults to `"cosine"`):
-            The type of noise schedule for `alpha_bar`. Choose from `cosine` or `exp`.
+        alpha_transform_type (`str`, defaults to `"cosine"`):
+            The type of noise schedule for `alpha_bar`. Choose from `cosine`, `exp`, or `laplace`.
 
     Returns:
         `torch.Tensor`:
@@ -101,7 +101,7 @@ def betas_for_alpha_bar(
 
 
 # Copied from diffusers.schedulers.scheduling_ddim.rescale_zero_terminal_snr
-def rescale_zero_terminal_snr(betas):
+def rescale_zero_terminal_snr(betas: torch.Tensor) -> torch.Tensor:
     """
     Rescales betas to have zero terminal SNR Based on https://huggingface.co/papers/2305.08891 (Algorithm 1)
 
@@ -266,7 +266,7 @@ class DDIMParallelScheduler(SchedulerMixin, ConfigMixin):
         """
         return sample
 
-    def _get_variance(self, timestep, prev_timestep=None):
+    def _get_variance(self, timestep: int, prev_timestep: Optional[int] = None) -> torch.Tensor:
         if prev_timestep is None:
             prev_timestep = timestep - self.config.num_train_timesteps // self.num_inference_steps
 
@@ -279,7 +279,7 @@ class DDIMParallelScheduler(SchedulerMixin, ConfigMixin):
 
         return variance
 
-    def _batch_get_variance(self, t, prev_t):
+    def _batch_get_variance(self, t: torch.Tensor, prev_t: torch.Tensor) -> torch.Tensor:
         alpha_prod_t = self.alphas_cumprod[t]
         alpha_prod_t_prev = self.alphas_cumprod[torch.clip(prev_t, min=0)]
         alpha_prod_t_prev[prev_t < 0] = torch.tensor(1.0)
@@ -335,7 +335,7 @@ class DDIMParallelScheduler(SchedulerMixin, ConfigMixin):
         return sample
 
     # Copied from diffusers.schedulers.scheduling_ddim.DDIMScheduler.set_timesteps
-    def set_timesteps(self, num_inference_steps: int, device: Union[str, torch.device] = None):
+    def set_timesteps(self, num_inference_steps: int, device: Union[str, torch.device] = None) -> None:
         """
         Sets the discrete timesteps used for the diffusion chain (to be run before inference).
 
@@ -392,7 +392,7 @@ class DDIMParallelScheduler(SchedulerMixin, ConfigMixin):
         sample: torch.Tensor,
         eta: float = 0.0,
         use_clipped_model_output: bool = False,
-        generator=None,
+        generator: Optional[torch.Generator] = None,
         variance_noise: Optional[torch.Tensor] = None,
         return_dict: bool = True,
     ) -> Union[DDIMParallelSchedulerOutput, Tuple]:
@@ -406,11 +406,13 @@ class DDIMParallelScheduler(SchedulerMixin, ConfigMixin):
             sample (`torch.Tensor`):
                 current instance of sample being created by diffusion process.
             eta (`float`): weight of noise for added noise in diffusion step.
-            use_clipped_model_output (`bool`): if `True`, compute "corrected" `model_output` from the clipped
-                predicted original sample. Necessary because predicted original sample is clipped to [-1, 1] when
-                `self.config.clip_sample` is `True`. If no clipping has happened, "corrected" `model_output` would
-                coincide with the one provided as input and `use_clipped_model_output` will have not effect.
-            generator: random number generator.
+            use_clipped_model_output (`bool`, defaults to `False`):
+                If `True`, compute "corrected" `model_output` from the clipped predicted original sample. This
+                correction is necessary because the predicted original sample is clipped to [-1, 1] when
+                `self.config.clip_sample` is `True`. If no clipping occurred, the "corrected" `model_output` matches
+                the input and `use_clipped_model_output` has no effect.
+            generator (`torch.Generator`, *optional*):
+                Random number generator.
             variance_noise (`torch.Tensor`): instead of generating noise for the variance using `generator`, we
                 can directly provide the noise for the variance itself. This is useful for methods such as
                 CycleDiffusion. (https://huggingface.co/papers/2210.05559)
@@ -496,7 +498,10 @@ class DDIMParallelScheduler(SchedulerMixin, ConfigMixin):
 
             if variance_noise is None:
                 variance_noise = randn_tensor(
-                    model_output.shape, generator=generator, device=model_output.device, dtype=model_output.dtype
+                    model_output.shape,
+                    generator=generator,
+                    device=model_output.device,
+                    dtype=model_output.dtype,
                 )
             variance = std_dev_t * variance_noise
 
@@ -513,7 +518,7 @@ class DDIMParallelScheduler(SchedulerMixin, ConfigMixin):
     def batch_step_no_noise(
         self,
         model_output: torch.Tensor,
-        timesteps: List[int],
+        timesteps: torch.Tensor,
         sample: torch.Tensor,
         eta: float = 0.0,
         use_clipped_model_output: bool = False,
@@ -528,7 +533,7 @@ class DDIMParallelScheduler(SchedulerMixin, ConfigMixin):
 
         Args:
             model_output (`torch.Tensor`): direct output from learned diffusion model.
-            timesteps (`List[int]`):
+            timesteps (`torch.Tensor`):
                 current discrete timesteps in the diffusion chain. This is now a list of integers.
             sample (`torch.Tensor`):
                 current instance of sample being created by diffusion process.
@@ -696,5 +701,5 @@ class DDIMParallelScheduler(SchedulerMixin, ConfigMixin):
         velocity = sqrt_alpha_prod * noise - sqrt_one_minus_alpha_prod * sample
         return velocity
 
-    def __len__(self):
+    def __len__(self) -> int:
         return self.config.num_train_timesteps

src/diffusers/schedulers/scheduling_ddpm.py

@@ -48,7 +48,7 @@ class DDPMSchedulerOutput(BaseOutput):
 def betas_for_alpha_bar(
     num_diffusion_timesteps: int,
     max_beta: float = 0.999,
-    alpha_transform_type: Literal["cosine", "exp"] = "cosine",
+    alpha_transform_type: Literal["cosine", "exp", "laplace"] = "cosine",
 ) -> torch.Tensor:
     """
     Create a beta schedule that discretizes the given alpha_t_bar function, which defines the cumulative product of
@@ -62,8 +62,8 @@ def betas_for_alpha_bar(
             The number of betas to produce.
         max_beta (`float`, defaults to `0.999`):
             The maximum beta to use; use values lower than 1 to avoid numerical instability.
-        alpha_transform_type (`"cosine"` or `"exp"`, defaults to `"cosine"`):
-            The type of noise schedule for `alpha_bar`. Choose from `cosine` or `exp`.
+        alpha_transform_type (`str`, defaults to `"cosine"`):
+            The type of noise schedule for `alpha_bar`. Choose from `cosine`, `exp`, or `laplace`.
 
     Returns:
         `torch.Tensor`:
@@ -192,7 +192,12 @@ class DDPMScheduler(SchedulerMixin, ConfigMixin):
         beta_schedule: Literal["linear", "scaled_linear", "squaredcos_cap_v2", "sigmoid"] = "linear",
         trained_betas: Optional[Union[np.ndarray, List[float]]] = None,
         variance_type: Literal[
-            "fixed_small", "fixed_small_log", "fixed_large", "fixed_large_log", "learned", "learned_range"
+            "fixed_small",
+            "fixed_small_log",
+            "fixed_large",
+            "fixed_large_log",
+            "learned",
+            "learned_range",
         ] = "fixed_small",
         clip_sample: bool = True,
         prediction_type: Literal["epsilon", "sample", "v_prediction"] = "epsilon",
@@ -210,7 +215,15 @@ class DDPMScheduler(SchedulerMixin, ConfigMixin):
             self.betas = torch.linspace(beta_start, beta_end, num_train_timesteps, dtype=torch.float32)
         elif beta_schedule == "scaled_linear":
             # this schedule is very specific to the latent diffusion model.
-            self.betas = torch.linspace(beta_start**0.5, beta_end**0.5, num_train_timesteps, dtype=torch.float32) ** 2
+            self.betas = (
+                torch.linspace(
+                    beta_start**0.5,
+                    beta_end**0.5,
+                    num_train_timesteps,
+                    dtype=torch.float32,
+                )
+                ** 2
+            )
         elif beta_schedule == "squaredcos_cap_v2":
             # Glide cosine schedule
             self.betas = betas_for_alpha_bar(num_train_timesteps)
@@ -268,7 +281,7 @@ class DDPMScheduler(SchedulerMixin, ConfigMixin):
         Sets the discrete timesteps used for the diffusion chain (to be run before inference).
 
         Args:
-            num_inference_steps (`int`):
+            num_inference_steps (`int`, *optional*):
                 The number of diffusion steps used when generating samples with a pre-trained model. If used,
                 `timesteps` must be `None`.
             device (`str` or `torch.device`, *optional*):
@@ -337,7 +350,14 @@ class DDPMScheduler(SchedulerMixin, ConfigMixin):
         t: int,
         predicted_variance: Optional[torch.Tensor] = None,
         variance_type: Optional[
-            Literal["fixed_small", "fixed_small_log", "fixed_large", "fixed_large_log", "learned", "learned_range"]
+            Literal[
+                "fixed_small",
+                "fixed_small_log",
+                "fixed_large",
+                "fixed_large_log",
+                "learned",
+                "learned_range",
+            ]
         ] = None,
     ) -> torch.Tensor:
         """
@@ -472,7 +492,10 @@ class DDPMScheduler(SchedulerMixin, ConfigMixin):
 
         prev_t = self.previous_timestep(t)
 
-        if model_output.shape[1] == sample.shape[1] * 2 and self.variance_type in ["learned", "learned_range"]:
+        if model_output.shape[1] == sample.shape[1] * 2 and self.variance_type in [
+            "learned",
+            "learned_range",
+        ]:
             model_output, predicted_variance = torch.split(model_output, sample.shape[1], dim=1)
         else:
             predicted_variance = None
@@ -521,7 +544,10 @@ class DDPMScheduler(SchedulerMixin, ConfigMixin):
         if t > 0:
             device = model_output.device
             variance_noise = randn_tensor(
-                model_output.shape, generator=generator, device=device, dtype=model_output.dtype
+                model_output.shape,
+                generator=generator,
+                device=device,
+                dtype=model_output.dtype,
             )
             if self.variance_type == "fixed_small_log":
                 variance = self._get_variance(t, predicted_variance=predicted_variance) * variance_noise
@@ -620,7 +646,7 @@ class DDPMScheduler(SchedulerMixin, ConfigMixin):
     def __len__(self) -> int:
         return self.config.num_train_timesteps
 
-    def previous_timestep(self, timestep: int) -> int:
+    def previous_timestep(self, timestep: int) -> Union[int, torch.Tensor]:
         """
         Compute the previous timestep in the diffusion chain.
 
@@ -629,7 +655,7 @@ class DDPMScheduler(SchedulerMixin, ConfigMixin):
                 The current timestep.
 
         Returns:
-            `int`:
+            `int` or `torch.Tensor`:
                 The previous timestep.
         """
         if self.custom_timesteps or self.num_inference_steps:

src/diffusers/schedulers/scheduling_ddpm_flax.py

@@ -22,6 +22,7 @@ import jax
 import jax.numpy as jnp
 
 from ..configuration_utils import ConfigMixin, register_to_config
+from ..utils import logging
 from .scheduling_utils_flax import (
     CommonSchedulerState,
     FlaxKarrasDiffusionSchedulers,
@@ -32,6 +33,9 @@ from .scheduling_utils_flax import (
 )
 
 
+logger = logging.get_logger(__name__)
+
+
 @flax.struct.dataclass
 class DDPMSchedulerState:
     common: CommonSchedulerState
@@ -42,7 +46,12 @@ class DDPMSchedulerState:
     num_inference_steps: Optional[int] = None
 
     @classmethod
-    def create(cls, common: CommonSchedulerState, init_noise_sigma: jnp.ndarray, timesteps: jnp.ndarray):
+    def create(
+        cls,
+        common: CommonSchedulerState,
+        init_noise_sigma: jnp.ndarray,
+        timesteps: jnp.ndarray,
+    ):
         return cls(common=common, init_noise_sigma=init_noise_sigma, timesteps=timesteps)
 
 
@@ -105,6 +114,10 @@ class FlaxDDPMScheduler(FlaxSchedulerMixin, ConfigMixin):
         prediction_type: str = "epsilon",
         dtype: jnp.dtype = jnp.float32,
     ):
+        logger.warning(
+            "Flax classes are deprecated and will be removed in Diffusers v1.0.0. We "
+            "recommend migrating to PyTorch classes or pinning your version of Diffusers."
+        )
         self.dtype = dtype
 
     def create_state(self, common: Optional[CommonSchedulerState] = None) -> DDPMSchedulerState:
@@ -123,7 +136,10 @@ class FlaxDDPMScheduler(FlaxSchedulerMixin, ConfigMixin):
         )
 
     def scale_model_input(
-        self, state: DDPMSchedulerState, sample: jnp.ndarray, timestep: Optional[int] = None
+        self,
+        state: DDPMSchedulerState,
+        sample: jnp.ndarray,
+        timestep: Optional[int] = None,
     ) -> jnp.ndarray:
         """
         Args:

src/diffusers/schedulers/scheduling_ddpm_parallel.py

@@ -50,7 +50,7 @@ class DDPMParallelSchedulerOutput(BaseOutput):
 def betas_for_alpha_bar(
     num_diffusion_timesteps: int,
     max_beta: float = 0.999,
-    alpha_transform_type: Literal["cosine", "exp"] = "cosine",
+    alpha_transform_type: Literal["cosine", "exp", "laplace"] = "cosine",
 ) -> torch.Tensor:
     """
     Create a beta schedule that discretizes the given alpha_t_bar function, which defines the cumulative product of
@@ -64,8 +64,8 @@ def betas_for_alpha_bar(
             The number of betas to produce.
         max_beta (`float`, defaults to `0.999`):
             The maximum beta to use; use values lower than 1 to avoid numerical instability.
-        alpha_transform_type (`"cosine"` or `"exp"`, defaults to `"cosine"`):
-            The type of noise schedule for `alpha_bar`. Choose from `cosine` or `exp`.
+        alpha_transform_type (`str`, defaults to `"cosine"`):
+            The type of noise schedule for `alpha_bar`. Choose from `cosine`, `exp`, or `laplace`.
 
     Returns:
         `torch.Tensor`:
@@ -149,38 +149,41 @@ class DDPMParallelScheduler(SchedulerMixin, ConfigMixin):
     For more details, see the original paper: https://huggingface.co/papers/2006.11239
 
     Args:
-        num_train_timesteps (`int`): number of diffusion steps used to train the model.
-        beta_start (`float`): the starting `beta` value of inference.
-        beta_end (`float`): the final `beta` value.
-        beta_schedule (`str`):
-            the beta schedule, a mapping from a beta range to a sequence of betas for stepping the model. Choose from
+        num_train_timesteps (`int`, defaults to 1000):
+            The number of diffusion steps to train the model.
+        beta_start (`float`, defaults to 0.0001):
+            The starting `beta` value of inference.
+        beta_end (`float`, defaults to 0.02):
+            The final `beta` value.
+        beta_schedule (`str`, defaults to `"linear"`):
+            The beta schedule, a mapping from a beta range to a sequence of betas for stepping the model. Choose from
             `linear`, `scaled_linear`, `squaredcos_cap_v2` or `sigmoid`.
-        trained_betas (`np.ndarray`, optional):
-            option to pass an array of betas directly to the constructor to bypass `beta_start`, `beta_end` etc.
-        variance_type (`str`):
-            options to clip the variance used when adding noise to the denoised sample. Choose from `fixed_small`,
+        trained_betas (`np.ndarray`, *optional*):
+            Option to pass an array of betas directly to the constructor to bypass `beta_start`, `beta_end` etc.
+        variance_type (`str`, defaults to `"fixed_small"`):
+            Options to clip the variance used when adding noise to the denoised sample. Choose from `fixed_small`,
             `fixed_small_log`, `fixed_large`, `fixed_large_log`, `learned` or `learned_range`.
-        clip_sample (`bool`, default `True`):
-            option to clip predicted sample for numerical stability.
-        clip_sample_range (`float`, default `1.0`):
-            the maximum magnitude for sample clipping. Valid only when `clip_sample=True`.
-        prediction_type (`str`, default `epsilon`, optional):
-            prediction type of the scheduler function, one of `epsilon` (predicting the noise of the diffusion
+        clip_sample (`bool`, defaults to `True`):
+            Option to clip predicted sample for numerical stability.
+        prediction_type (`str`, defaults to `"epsilon"`):
+            Prediction type of the scheduler function, one of `epsilon` (predicting the noise of the diffusion
             process), `sample` (directly predicting the noisy sample`) or `v_prediction` (see section 2.4
             https://huggingface.co/papers/2210.02303)
-        thresholding (`bool`, default `False`):
-            whether to use the "dynamic thresholding" method (introduced by Imagen,
+        thresholding (`bool`, defaults to `False`):
+            Whether to use the "dynamic thresholding" method (introduced by Imagen,
             https://huggingface.co/papers/2205.11487). Note that the thresholding method is unsuitable for latent-space
             diffusion models (such as stable-diffusion).
-        dynamic_thresholding_ratio (`float`, default `0.995`):
-            the ratio for the dynamic thresholding method. Default is `0.995`, the same as Imagen
+        dynamic_thresholding_ratio (`float`, defaults to 0.995):
+            The ratio for the dynamic thresholding method. Default is `0.995`, the same as Imagen
             (https://huggingface.co/papers/2205.11487). Valid only when `thresholding=True`.
-        sample_max_value (`float`, default `1.0`):
-            the threshold value for dynamic thresholding. Valid only when `thresholding=True`.
-        timestep_spacing (`str`, default `"leading"`):
+        clip_sample_range (`float`, defaults to 1.0):
+            The maximum magnitude for sample clipping. Valid only when `clip_sample=True`.
+        sample_max_value (`float`, defaults to 1.0):
+            The threshold value for dynamic thresholding. Valid only when `thresholding=True`.
+        timestep_spacing (`str`, defaults to `"leading"`):
             The way the timesteps should be scaled. Refer to Table 2. of [Common Diffusion Noise Schedules and Sample
             Steps are Flawed](https://huggingface.co/papers/2305.08891) for more information.
-        steps_offset (`int`, default `0`):
+        steps_offset (`int`, defaults to 0):
             An offset added to the inference steps, as required by some model families.
         rescale_betas_zero_snr (`bool`, defaults to `False`):
             Whether to rescale the betas to have zero terminal SNR. This enables the model to generate very bright and
@@ -202,7 +205,12 @@ class DDPMParallelScheduler(SchedulerMixin, ConfigMixin):
         beta_schedule: Literal["linear", "scaled_linear", "squaredcos_cap_v2", "sigmoid"] = "linear",
         trained_betas: Optional[Union[np.ndarray, List[float]]] = None,
         variance_type: Literal[
-            "fixed_small", "fixed_small_log", "fixed_large", "fixed_large_log", "learned", "learned_range"
+            "fixed_small",
+            "fixed_small_log",
+            "fixed_large",
+            "fixed_large_log",
+            "learned",
+            "learned_range",
         ] = "fixed_small",
         clip_sample: bool = True,
         prediction_type: Literal["epsilon", "sample", "v_prediction"] = "epsilon",
@@ -220,7 +228,15 @@ class DDPMParallelScheduler(SchedulerMixin, ConfigMixin):
             self.betas = torch.linspace(beta_start, beta_end, num_train_timesteps, dtype=torch.float32)
         elif beta_schedule == "scaled_linear":
             # this schedule is very specific to the latent diffusion model.
-            self.betas = torch.linspace(beta_start**0.5, beta_end**0.5, num_train_timesteps, dtype=torch.float32) ** 2
+            self.betas = (
+                torch.linspace(
+                    beta_start**0.5,
+                    beta_end**0.5,
+                    num_train_timesteps,
+                    dtype=torch.float32,
+                )
+                ** 2
+            )
         elif beta_schedule == "squaredcos_cap_v2":
             # Glide cosine schedule
             self.betas = betas_for_alpha_bar(num_train_timesteps)
@@ -280,7 +296,7 @@ class DDPMParallelScheduler(SchedulerMixin, ConfigMixin):
         Sets the discrete timesteps used for the diffusion chain (to be run before inference).
 
         Args:
-            num_inference_steps (`int`):
+            num_inference_steps (`int`, *optional*):
                 The number of diffusion steps used when generating samples with a pre-trained model. If used,
                 `timesteps` must be `None`.
             device (`str` or `torch.device`, *optional*):
@@ -350,7 +366,14 @@ class DDPMParallelScheduler(SchedulerMixin, ConfigMixin):
         t: int,
         predicted_variance: Optional[torch.Tensor] = None,
         variance_type: Optional[
-            Literal["fixed_small", "fixed_small_log", "fixed_large", "fixed_large_log", "learned", "learned_range"]
+            Literal[
+                "fixed_small",
+                "fixed_small_log",
+                "fixed_large",
+                "fixed_large_log",
+                "learned",
+                "learned_range",
+            ]
         ] = None,
     ) -> torch.Tensor:
         """
@@ -458,7 +481,7 @@ class DDPMParallelScheduler(SchedulerMixin, ConfigMixin):
         model_output: torch.Tensor,
         timestep: int,
         sample: torch.Tensor,
-        generator=None,
+        generator: Optional[torch.Generator] = None,
         return_dict: bool = True,
     ) -> Union[DDPMParallelSchedulerOutput, Tuple]:
         """
@@ -470,7 +493,8 @@ class DDPMParallelScheduler(SchedulerMixin, ConfigMixin):
             timestep (`int`): current discrete timestep in the diffusion chain.
             sample (`torch.Tensor`):
                 current instance of sample being created by diffusion process.
-            generator: random number generator.
+            generator (`torch.Generator`, *optional*):
+                Random number generator.
             return_dict (`bool`): option for returning tuple rather than DDPMParallelSchedulerOutput class
 
         Returns:
@@ -483,7 +507,10 @@ class DDPMParallelScheduler(SchedulerMixin, ConfigMixin):
 
         prev_t = self.previous_timestep(t)
 
-        if model_output.shape[1] == sample.shape[1] * 2 and self.variance_type in ["learned", "learned_range"]:
+        if model_output.shape[1] == sample.shape[1] * 2 and self.variance_type in [
+            "learned",
+            "learned_range",
+        ]:
             model_output, predicted_variance = torch.split(model_output, sample.shape[1], dim=1)
         else:
             predicted_variance = None
@@ -532,7 +559,10 @@ class DDPMParallelScheduler(SchedulerMixin, ConfigMixin):
         if t > 0:
             device = model_output.device
             variance_noise = randn_tensor(
-                model_output.shape, generator=generator, device=device, dtype=model_output.dtype
+                model_output.shape,
+                generator=generator,
+                device=device,
+                dtype=model_output.dtype,
             )
             if self.variance_type == "fixed_small_log":
                 variance = self._get_variance(t, predicted_variance=predicted_variance) * variance_noise
@@ -555,7 +585,7 @@ class DDPMParallelScheduler(SchedulerMixin, ConfigMixin):
     def batch_step_no_noise(
         self,
         model_output: torch.Tensor,
-        timesteps: List[int],
+        timesteps: torch.Tensor,
         sample: torch.Tensor,
     ) -> torch.Tensor:
         """
@@ -568,8 +598,8 @@ class DDPMParallelScheduler(SchedulerMixin, ConfigMixin):
 
         Args:
             model_output (`torch.Tensor`): direct output from learned diffusion model.
-            timesteps (`List[int]`):
-                current discrete timesteps in the diffusion chain. This is now a list of integers.
+            timesteps (`torch.Tensor`):
+                Current discrete timesteps in the diffusion chain. This is a tensor of integers.
             sample (`torch.Tensor`):
                 current instance of sample being created by diffusion process.
 
@@ -583,7 +613,10 @@ class DDPMParallelScheduler(SchedulerMixin, ConfigMixin):
         t = t.view(-1, *([1] * (model_output.ndim - 1)))
         prev_t = prev_t.view(-1, *([1] * (model_output.ndim - 1)))
 
-        if model_output.shape[1] == sample.shape[1] * 2 and self.variance_type in ["learned", "learned_range"]:
+        if model_output.shape[1] == sample.shape[1] * 2 and self.variance_type in [
+            "learned",
+            "learned_range",
+        ]:
             model_output, predicted_variance = torch.split(model_output, sample.shape[1], dim=1)
         else:
             pass
@@ -714,7 +747,7 @@ class DDPMParallelScheduler(SchedulerMixin, ConfigMixin):
         return self.config.num_train_timesteps
 
     # Copied from diffusers.schedulers.scheduling_ddpm.DDPMScheduler.previous_timestep
-    def previous_timestep(self, timestep):
+    def previous_timestep(self, timestep: int) -> Union[int, torch.Tensor]:
         """
         Compute the previous timestep in the diffusion chain.
 
@@ -723,7 +756,7 @@ class DDPMParallelScheduler(SchedulerMixin, ConfigMixin):
                 The current timestep.
 
         Returns:
-            `int`:
+            `int` or `torch.Tensor`:
                 The previous timestep.
         """
         if self.custom_timesteps or self.num_inference_steps:

src/diffusers/schedulers/scheduling_deis_multistep.py

@@ -34,7 +34,7 @@ if is_scipy_available():
 def betas_for_alpha_bar(
     num_diffusion_timesteps: int,
     max_beta: float = 0.999,
-    alpha_transform_type: Literal["cosine", "exp"] = "cosine",
+    alpha_transform_type: Literal["cosine", "exp", "laplace"] = "cosine",
 ) -> torch.Tensor:
     """
     Create a beta schedule that discretizes the given alpha_t_bar function, which defines the cumulative product of
@@ -48,8 +48,8 @@ def betas_for_alpha_bar(
             The number of betas to produce.
         max_beta (`float`, defaults to `0.999`):
             The maximum beta to use; use values lower than 1 to avoid numerical instability.
-        alpha_transform_type (`"cosine"` or `"exp"`, defaults to `"cosine"`):
-            The type of noise schedule for `alpha_bar`. Choose from `cosine` or `exp`.
+        alpha_transform_type (`str`, defaults to `"cosine"`):
+            The type of noise schedule for `alpha_bar`. Choose from `cosine`, `exp`, or `laplace`.
 
     Returns:
         `torch.Tensor`:

src/diffusers/schedulers/scheduling_dpm_cogvideox.py

@@ -52,7 +52,7 @@ class DDIMSchedulerOutput(BaseOutput):
 def betas_for_alpha_bar(
     num_diffusion_timesteps: int,
     max_beta: float = 0.999,
-    alpha_transform_type: Literal["cosine", "exp"] = "cosine",
+    alpha_transform_type: Literal["cosine", "exp", "laplace"] = "cosine",
 ) -> torch.Tensor:
     """
     Create a beta schedule that discretizes the given alpha_t_bar function, which defines the cumulative product of
@@ -66,8 +66,8 @@ def betas_for_alpha_bar(
             The number of betas to produce.
         max_beta (`float`, defaults to `0.999`):
             The maximum beta to use; use values lower than 1 to avoid numerical instability.
-        alpha_transform_type (`"cosine"` or `"exp"`, defaults to `"cosine"`):
-            The type of noise schedule for `alpha_bar`. Choose from `cosine` or `exp`.
+        alpha_transform_type (`str`, defaults to `"cosine"`):
+            The type of noise schedule for `alpha_bar`. Choose from `cosine`, `exp`, or `laplace`.
 
     Returns:
         `torch.Tensor`:

src/diffusers/schedulers/scheduling_dpmsolver_multistep.py

@@ -34,7 +34,7 @@ if is_scipy_available():
 def betas_for_alpha_bar(
     num_diffusion_timesteps: int,
     max_beta: float = 0.999,
-    alpha_transform_type: Literal["cosine", "exp"] = "cosine",
+    alpha_transform_type: Literal["cosine", "exp", "laplace"] = "cosine",
 ) -> torch.Tensor:
     """
     Create a beta schedule that discretizes the given alpha_t_bar function, which defines the cumulative product of
@@ -48,8 +48,8 @@ def betas_for_alpha_bar(
             The number of betas to produce.
         max_beta (`float`, defaults to `0.999`):
             The maximum beta to use; use values lower than 1 to avoid numerical instability.
-        alpha_transform_type (`"cosine"` or `"exp"`, defaults to `"cosine"`):
-            The type of noise schedule for `alpha_bar`. Choose from `cosine` or `exp`.
+        alpha_transform_type (`str`, defaults to `"cosine"`):
+            The type of noise schedule for `alpha_bar`. Choose from `cosine`, `exp`, or `laplace`.
 
     Returns:
         `torch.Tensor`:

src/diffusers/schedulers/scheduling_dpmsolver_multistep_inverse.py

@@ -34,7 +34,7 @@ if is_scipy_available():
 def betas_for_alpha_bar(
     num_diffusion_timesteps: int,
     max_beta: float = 0.999,
-    alpha_transform_type: Literal["cosine", "exp"] = "cosine",
+    alpha_transform_type: Literal["cosine", "exp", "laplace"] = "cosine",
 ) -> torch.Tensor:
     """
     Create a beta schedule that discretizes the given alpha_t_bar function, which defines the cumulative product of
@@ -48,8 +48,8 @@ def betas_for_alpha_bar(
             The number of betas to produce.
         max_beta (`float`, defaults to `0.999`):
             The maximum beta to use; use values lower than 1 to avoid numerical instability.
-        alpha_transform_type (`"cosine"` or `"exp"`, defaults to `"cosine"`):
-            The type of noise schedule for `alpha_bar`. Choose from `cosine` or `exp`.
+        alpha_transform_type (`str`, defaults to `"cosine"`):
+            The type of noise schedule for `alpha_bar`. Choose from `cosine`, `exp`, or `laplace`.
 
     Returns:
         `torch.Tensor`:

src/diffusers/schedulers/scheduling_dpmsolver_sde.py

@@ -117,7 +117,7 @@ class BrownianTreeNoiseSampler:
 def betas_for_alpha_bar(
     num_diffusion_timesteps: int,
     max_beta: float = 0.999,
-    alpha_transform_type: Literal["cosine", "exp"] = "cosine",
+    alpha_transform_type: Literal["cosine", "exp", "laplace"] = "cosine",
 ) -> torch.Tensor:
     """
     Create a beta schedule that discretizes the given alpha_t_bar function, which defines the cumulative product of
@@ -131,8 +131,8 @@ def betas_for_alpha_bar(
             The number of betas to produce.
         max_beta (`float`, defaults to `0.999`):
             The maximum beta to use; use values lower than 1 to avoid numerical instability.
-        alpha_transform_type (`"cosine"` or `"exp"`, defaults to `"cosine"`):
-            The type of noise schedule for `alpha_bar`. Choose from `cosine` or `exp`.
+        alpha_transform_type (`str`, defaults to `"cosine"`):
+            The type of noise schedule for `alpha_bar`. Choose from `cosine`, `exp`, or `laplace`.
 
     Returns:
         `torch.Tensor`:

src/diffusers/schedulers/scheduling_dpmsolver_singlestep.py

@@ -36,7 +36,7 @@ logger = logging.get_logger(__name__)  # pylint: disable=invalid-name
 def betas_for_alpha_bar(
     num_diffusion_timesteps: int,
     max_beta: float = 0.999,
-    alpha_transform_type: Literal["cosine", "exp"] = "cosine",
+    alpha_transform_type: Literal["cosine", "exp", "laplace"] = "cosine",
 ) -> torch.Tensor:
     """
     Create a beta schedule that discretizes the given alpha_t_bar function, which defines the cumulative product of
@@ -50,8 +50,8 @@ def betas_for_alpha_bar(
             The number of betas to produce.
         max_beta (`float`, defaults to `0.999`):
             The maximum beta to use; use values lower than 1 to avoid numerical instability.
-        alpha_transform_type (`"cosine"` or `"exp"`, defaults to `"cosine"`):
-            The type of noise schedule for `alpha_bar`. Choose from `cosine` or `exp`.
+        alpha_transform_type (`str`, defaults to `"cosine"`):
+            The type of noise schedule for `alpha_bar`. Choose from `cosine`, `exp`, or `laplace`.
 
     Returns:
         `torch.Tensor`:

src/diffusers/schedulers/scheduling_euler_ancestral_discrete.py

@@ -51,7 +51,7 @@ class EulerAncestralDiscreteSchedulerOutput(BaseOutput):
 def betas_for_alpha_bar(
     num_diffusion_timesteps: int,
     max_beta: float = 0.999,
-    alpha_transform_type: Literal["cosine", "exp"] = "cosine",
+    alpha_transform_type: Literal["cosine", "exp", "laplace"] = "cosine",
 ) -> torch.Tensor:
     """
     Create a beta schedule that discretizes the given alpha_t_bar function, which defines the cumulative product of
@@ -65,8 +65,8 @@ def betas_for_alpha_bar(
             The number of betas to produce.
         max_beta (`float`, defaults to `0.999`):
             The maximum beta to use; use values lower than 1 to avoid numerical instability.
-        alpha_transform_type (`"cosine"` or `"exp"`, defaults to `"cosine"`):
-            The type of noise schedule for `alpha_bar`. Choose from `cosine` or `exp`.
+        alpha_transform_type (`str`, defaults to `"cosine"`):
+            The type of noise schedule for `alpha_bar`. Choose from `cosine`, `exp`, or `laplace`.
 
     Returns:
         `torch.Tensor`:

src/diffusers/schedulers/scheduling_euler_discrete.py

@@ -54,7 +54,7 @@ class EulerDiscreteSchedulerOutput(BaseOutput):
 def betas_for_alpha_bar(
     num_diffusion_timesteps: int,
     max_beta: float = 0.999,
-    alpha_transform_type: Literal["cosine", "exp"] = "cosine",
+    alpha_transform_type: Literal["cosine", "exp", "laplace"] = "cosine",
 ) -> torch.Tensor:
     """
     Create a beta schedule that discretizes the given alpha_t_bar function, which defines the cumulative product of
@@ -68,8 +68,8 @@ def betas_for_alpha_bar(
             The number of betas to produce.
         max_beta (`float`, defaults to `0.999`):
             The maximum beta to use; use values lower than 1 to avoid numerical instability.
-        alpha_transform_type (`"cosine"` or `"exp"`, defaults to `"cosine"`):
-            The type of noise schedule for `alpha_bar`. Choose from `cosine` or `exp`.
+        alpha_transform_type (`str`, defaults to `"cosine"`):
+            The type of noise schedule for `alpha_bar`. Choose from `cosine`, `exp`, or `laplace`.
 
     Returns:
         `torch.Tensor`:

src/diffusers/schedulers/scheduling_heun_discrete.py

@@ -51,7 +51,7 @@ class HeunDiscreteSchedulerOutput(BaseOutput):
 def betas_for_alpha_bar(
     num_diffusion_timesteps: int,
     max_beta: float = 0.999,
-    alpha_transform_type: Literal["cosine", "exp"] = "cosine",
+    alpha_transform_type: Literal["cosine", "exp", "laplace"] = "cosine",
 ) -> torch.Tensor:
     """
     Create a beta schedule that discretizes the given alpha_t_bar function, which defines the cumulative product of
@@ -65,8 +65,8 @@ def betas_for_alpha_bar(
             The number of betas to produce.
         max_beta (`float`, defaults to `0.999`):
             The maximum beta to use; use values lower than 1 to avoid numerical instability.
-        alpha_transform_type (`"cosine"` or `"exp"`, defaults to `"cosine"`):
-            The type of noise schedule for `alpha_bar`. Choose from `cosine` or `exp`.
+        alpha_transform_type (`str`, defaults to `"cosine"`):
+            The type of noise schedule for `alpha_bar`. Choose from `cosine`, `exp`, or `laplace`.
 
     Returns:
         `torch.Tensor`:

src/diffusers/schedulers/scheduling_k_dpm_2_ancestral_discrete.py

@@ -52,7 +52,7 @@ class KDPM2AncestralDiscreteSchedulerOutput(BaseOutput):
 def betas_for_alpha_bar(
     num_diffusion_timesteps: int,
     max_beta: float = 0.999,
-    alpha_transform_type: Literal["cosine", "exp"] = "cosine",
+    alpha_transform_type: Literal["cosine", "exp", "laplace"] = "cosine",
 ) -> torch.Tensor:
     """
     Create a beta schedule that discretizes the given alpha_t_bar function, which defines the cumulative product of
@@ -66,8 +66,8 @@ def betas_for_alpha_bar(
             The number of betas to produce.
         max_beta (`float`, defaults to `0.999`):
             The maximum beta to use; use values lower than 1 to avoid numerical instability.
-        alpha_transform_type (`"cosine"` or `"exp"`, defaults to `"cosine"`):
-            The type of noise schedule for `alpha_bar`. Choose from `cosine` or `exp`.
+        alpha_transform_type (`str`, defaults to `"cosine"`):
+            The type of noise schedule for `alpha_bar`. Choose from `cosine`, `exp`, or `laplace`.
 
     Returns:
         `torch.Tensor`:

src/diffusers/schedulers/scheduling_k_dpm_2_discrete.py

@@ -51,7 +51,7 @@ class KDPM2DiscreteSchedulerOutput(BaseOutput):
 def betas_for_alpha_bar(
     num_diffusion_timesteps: int,
     max_beta: float = 0.999,
-    alpha_transform_type: Literal["cosine", "exp"] = "cosine",
+    alpha_transform_type: Literal["cosine", "exp", "laplace"] = "cosine",
 ) -> torch.Tensor:
     """
     Create a beta schedule that discretizes the given alpha_t_bar function, which defines the cumulative product of
@@ -65,8 +65,8 @@ def betas_for_alpha_bar(
             The number of betas to produce.
         max_beta (`float`, defaults to `0.999`):
             The maximum beta to use; use values lower than 1 to avoid numerical instability.
-        alpha_transform_type (`"cosine"` or `"exp"`, defaults to `"cosine"`):
-            The type of noise schedule for `alpha_bar`. Choose from `cosine` or `exp`.
+        alpha_transform_type (`str`, defaults to `"cosine"`):
+            The type of noise schedule for `alpha_bar`. Choose from `cosine`, `exp`, or `laplace`.
 
     Returns:
         `torch.Tensor`:

src/diffusers/schedulers/scheduling_lcm.py

@@ -53,7 +53,7 @@ class LCMSchedulerOutput(BaseOutput):
 def betas_for_alpha_bar(
     num_diffusion_timesteps: int,
     max_beta: float = 0.999,
-    alpha_transform_type: Literal["cosine", "exp"] = "cosine",
+    alpha_transform_type: Literal["cosine", "exp", "laplace"] = "cosine",
 ) -> torch.Tensor:
     """
     Create a beta schedule that discretizes the given alpha_t_bar function, which defines the cumulative product of
@@ -67,8 +67,8 @@ def betas_for_alpha_bar(
             The number of betas to produce.
         max_beta (`float`, defaults to `0.999`):
             The maximum beta to use; use values lower than 1 to avoid numerical instability.
-        alpha_transform_type (`"cosine"` or `"exp"`, defaults to `"cosine"`):
-            The type of noise schedule for `alpha_bar`. Choose from `cosine` or `exp`.
+        alpha_transform_type (`str`, defaults to `"cosine"`):
+            The type of noise schedule for `alpha_bar`. Choose from `cosine`, `exp`, or `laplace`.
 
     Returns:
         `torch.Tensor`:
@@ -722,7 +722,7 @@ class LCMScheduler(SchedulerMixin, ConfigMixin):
                 The current timestep.
 
         Returns:
-            `int`:
+            `int` or `torch.Tensor`:
                 The previous timestep.
         """
         if self.custom_timesteps or self.num_inference_steps:

src/diffusers/schedulers/scheduling_lms_discrete.py

@@ -49,7 +49,7 @@ class LMSDiscreteSchedulerOutput(BaseOutput):
 def betas_for_alpha_bar(
     num_diffusion_timesteps: int,
     max_beta: float = 0.999,
-    alpha_transform_type: Literal["cosine", "exp"] = "cosine",
+    alpha_transform_type: Literal["cosine", "exp", "laplace"] = "cosine",
 ) -> torch.Tensor:
     """
     Create a beta schedule that discretizes the given alpha_t_bar function, which defines the cumulative product of
@@ -63,8 +63,8 @@ def betas_for_alpha_bar(
             The number of betas to produce.
         max_beta (`float`, defaults to `0.999`):
             The maximum beta to use; use values lower than 1 to avoid numerical instability.
-        alpha_transform_type (`"cosine"` or `"exp"`, defaults to `"cosine"`):
-            The type of noise schedule for `alpha_bar`. Choose from `cosine` or `exp`.
+        alpha_transform_type (`str`, defaults to `"cosine"`):
+            The type of noise schedule for `alpha_bar`. Choose from `cosine`, `exp`, or `laplace`.
 
     Returns:
         `torch.Tensor`:

src/diffusers/schedulers/scheduling_pndm.py

@@ -28,7 +28,7 @@ from .scheduling_utils import KarrasDiffusionSchedulers, SchedulerMixin, Schedul
 def betas_for_alpha_bar(
     num_diffusion_timesteps: int,
     max_beta: float = 0.999,
-    alpha_transform_type: Literal["cosine", "exp"] = "cosine",
+    alpha_transform_type: Literal["cosine", "exp", "laplace"] = "cosine",
 ) -> torch.Tensor:
     """
     Create a beta schedule that discretizes the given alpha_t_bar function, which defines the cumulative product of
@@ -42,8 +42,8 @@ def betas_for_alpha_bar(
             The number of betas to produce.
         max_beta (`float`, defaults to `0.999`):
             The maximum beta to use; use values lower than 1 to avoid numerical instability.
-        alpha_transform_type (`"cosine"` or `"exp"`, defaults to `"cosine"`):
-            The type of noise schedule for `alpha_bar`. Choose from `cosine` or `exp`.
+        alpha_transform_type (`str`, defaults to `"cosine"`):
+            The type of noise schedule for `alpha_bar`. Choose from `cosine`, `exp`, or `laplace`.
 
     Returns:
         `torch.Tensor`:

src/diffusers/schedulers/scheduling_repaint.py

@@ -47,7 +47,7 @@ class RePaintSchedulerOutput(BaseOutput):
 def betas_for_alpha_bar(
     num_diffusion_timesteps: int,
     max_beta: float = 0.999,
-    alpha_transform_type: Literal["cosine", "exp"] = "cosine",
+    alpha_transform_type: Literal["cosine", "exp", "laplace"] = "cosine",
 ) -> torch.Tensor:
     """
     Create a beta schedule that discretizes the given alpha_t_bar function, which defines the cumulative product of
@@ -61,8 +61,8 @@ def betas_for_alpha_bar(
             The number of betas to produce.
         max_beta (`float`, defaults to `0.999`):
             The maximum beta to use; use values lower than 1 to avoid numerical instability.
-        alpha_transform_type (`"cosine"` or `"exp"`, defaults to `"cosine"`):
-            The type of noise schedule for `alpha_bar`. Choose from `cosine` or `exp`.
+        alpha_transform_type (`str`, defaults to `"cosine"`):
+            The type of noise schedule for `alpha_bar`. Choose from `cosine`, `exp`, or `laplace`.
 
     Returns:
         `torch.Tensor`:

src/diffusers/schedulers/scheduling_sasolver.py

@@ -35,7 +35,7 @@ if is_scipy_available():
 def betas_for_alpha_bar(
     num_diffusion_timesteps: int,
     max_beta: float = 0.999,
-    alpha_transform_type: Literal["cosine", "exp"] = "cosine",
+    alpha_transform_type: Literal["cosine", "exp", "laplace"] = "cosine",
 ) -> torch.Tensor:
     """
     Create a beta schedule that discretizes the given alpha_t_bar function, which defines the cumulative product of
@@ -49,8 +49,8 @@ def betas_for_alpha_bar(
             The number of betas to produce.
         max_beta (`float`, defaults to `0.999`):
             The maximum beta to use; use values lower than 1 to avoid numerical instability.
-        alpha_transform_type (`"cosine"` or `"exp"`, defaults to `"cosine"`):
-            The type of noise schedule for `alpha_bar`. Choose from `cosine` or `exp`.
+        alpha_transform_type (`str`, defaults to `"cosine"`):
+            The type of noise schedule for `alpha_bar`. Choose from `cosine`, `exp`, or `laplace`.
 
     Returns:
         `torch.Tensor`:

src/diffusers/schedulers/scheduling_tcd.py

@@ -52,7 +52,7 @@ class TCDSchedulerOutput(BaseOutput):
 def betas_for_alpha_bar(
     num_diffusion_timesteps: int,
     max_beta: float = 0.999,
-    alpha_transform_type: Literal["cosine", "exp"] = "cosine",
+    alpha_transform_type: Literal["cosine", "exp", "laplace"] = "cosine",
 ) -> torch.Tensor:
     """
     Create a beta schedule that discretizes the given alpha_t_bar function, which defines the cumulative product of
@@ -66,8 +66,8 @@ def betas_for_alpha_bar(
             The number of betas to produce.
         max_beta (`float`, defaults to `0.999`):
             The maximum beta to use; use values lower than 1 to avoid numerical instability.
-        alpha_transform_type (`"cosine"` or `"exp"`, defaults to `"cosine"`):
-            The type of noise schedule for `alpha_bar`. Choose from `cosine` or `exp`.
+        alpha_transform_type (`str`, defaults to `"cosine"`):
+            The type of noise schedule for `alpha_bar`. Choose from `cosine`, `exp`, or `laplace`.
 
     Returns:
         `torch.Tensor`:
@@ -777,7 +777,7 @@ class TCDScheduler(SchedulerMixin, ConfigMixin):
                 The current timestep.
 
         Returns:
-            `int`:
+            `int` or `torch.Tensor`:
                 The previous timestep.
         """
         if self.custom_timesteps or self.num_inference_steps:

src/diffusers/schedulers/scheduling_unclip.py

@@ -48,7 +48,7 @@ class UnCLIPSchedulerOutput(BaseOutput):
 def betas_for_alpha_bar(
     num_diffusion_timesteps: int,
     max_beta: float = 0.999,
-    alpha_transform_type: Literal["cosine", "exp"] = "cosine",
+    alpha_transform_type: Literal["cosine", "exp", "laplace"] = "cosine",
 ) -> torch.Tensor:
     """
     Create a beta schedule that discretizes the given alpha_t_bar function, which defines the cumulative product of
@@ -62,8 +62,8 @@ def betas_for_alpha_bar(
             The number of betas to produce.
         max_beta (`float`, defaults to `0.999`):
             The maximum beta to use; use values lower than 1 to avoid numerical instability.
-        alpha_transform_type (`"cosine"` or `"exp"`, defaults to `"cosine"`):
-            The type of noise schedule for `alpha_bar`. Choose from `cosine` or `exp`.
+        alpha_transform_type (`str`, defaults to `"cosine"`):
+            The type of noise schedule for `alpha_bar`. Choose from `cosine`, `exp`, or `laplace`.
 
     Returns:
         `torch.Tensor`:

src/diffusers/schedulers/scheduling_unipc_multistep.py

@@ -34,7 +34,7 @@ if is_scipy_available():
 def betas_for_alpha_bar(
     num_diffusion_timesteps: int,
     max_beta: float = 0.999,
-    alpha_transform_type: Literal["cosine", "exp"] = "cosine",
+    alpha_transform_type: Literal["cosine", "exp", "laplace"] = "cosine",
 ) -> torch.Tensor:
     """
     Create a beta schedule that discretizes the given alpha_t_bar function, which defines the cumulative product of
@@ -48,8 +48,8 @@ def betas_for_alpha_bar(
             The number of betas to produce.
         max_beta (`float`, defaults to `0.999`):
             The maximum beta to use; use values lower than 1 to avoid numerical instability.
-        alpha_transform_type (`"cosine"` or `"exp"`, defaults to `"cosine"`):
-            The type of noise schedule for `alpha_bar`. Choose from `cosine` or `exp`.
+        alpha_transform_type (`str`, defaults to `"cosine"`):
+            The type of noise schedule for `alpha_bar`. Choose from `cosine`, `exp`, or `laplace`.
 
     Returns:
         `torch.Tensor`:
@@ -226,6 +226,7 @@ class UniPCMultistepScheduler(SchedulerMixin, ConfigMixin):
         time_shift_type: Literal["exponential"] = "exponential",
         sigma_min: Optional[float] = None,
         sigma_max: Optional[float] = None,
+        shift_terminal: Optional[float] = None,
     ) -> None:
         if self.config.use_beta_sigmas and not is_scipy_available():
             raise ImportError("Make sure to install scipy if you want to use beta sigmas.")
@@ -245,6 +246,8 @@ class UniPCMultistepScheduler(SchedulerMixin, ConfigMixin):
             self.betas = betas_for_alpha_bar(num_train_timesteps)
         else:
             raise NotImplementedError(f"{beta_schedule} is not implemented for {self.__class__}")
+        if shift_terminal is not None and not use_flow_sigmas:
+            raise ValueError("`shift_terminal` is only supported when `use_flow_sigmas=True`.")
 
         if rescale_betas_zero_snr:
             self.betas = rescale_zero_terminal_snr(self.betas)
@@ -313,8 +316,12 @@ class UniPCMultistepScheduler(SchedulerMixin, ConfigMixin):
         self._begin_index = begin_index
 
     def set_timesteps(
-        self, num_inference_steps: int, device: Optional[Union[str, torch.device]] = None, mu: Optional[float] = None
-    ) -> None:
+        self,
+        num_inference_steps: Optional[int] = None,
+        device: Union[str, torch.device] = None,
+        sigmas: Optional[List[float]] = None,
+        mu: Optional[float] = None,
+    ):
         """
         Sets the discrete timesteps used for the diffusion chain (to be run before inference).
 
@@ -323,13 +330,24 @@ class UniPCMultistepScheduler(SchedulerMixin, ConfigMixin):
                 The number of diffusion steps used when generating samples with a pre-trained model.
             device (`str` or `torch.device`, *optional*):
                 The device to which the timesteps should be moved to. If `None`, the timesteps are not moved.
+            sigmas (`List[float]`, *optional*):
+                Custom values for sigmas to be used for each diffusion step. If `None`, the sigmas are computed
+                automatically.
             mu (`float`, *optional*):
                 Optional mu parameter for dynamic shifting when using exponential time shift type.
         """
+        if self.config.use_dynamic_shifting and mu is None:
+            raise ValueError("`mu` must be passed when `use_dynamic_shifting` is set to be `True`")
+
+        if sigmas is not None:
+            if not self.config.use_flow_sigmas:
+                raise ValueError(
+                    "Passing `sigmas` is only supported when `use_flow_sigmas=True`. "
+                    "Please set `use_flow_sigmas=True` during scheduler initialization."
+                )
+            num_inference_steps = len(sigmas)
+
         # "linspace", "leading", "trailing" corresponds to annotation of Table 2. of https://huggingface.co/papers/2305.08891
-        if mu is not None:
-            assert self.config.use_dynamic_shifting and self.config.time_shift_type == "exponential"
-            self.config.flow_shift = np.exp(mu)
         if self.config.timestep_spacing == "linspace":
             timesteps = (
                 np.linspace(0, self.config.num_train_timesteps - 1, num_inference_steps + 1)
@@ -354,8 +372,9 @@ class UniPCMultistepScheduler(SchedulerMixin, ConfigMixin):
                 f"{self.config.timestep_spacing} is not supported. Please make sure to choose one of 'linspace', 'leading' or 'trailing'."
             )
 
-        sigmas = np.array(((1 - self.alphas_cumprod) / self.alphas_cumprod) ** 0.5)
         if self.config.use_karras_sigmas:
+            if sigmas is None:
+                sigmas = np.array(((1 - self.alphas_cumprod) / self.alphas_cumprod) ** 0.5)
             log_sigmas = np.log(sigmas)
             sigmas = np.flip(sigmas).copy()
             sigmas = self._convert_to_karras(in_sigmas=sigmas, num_inference_steps=num_inference_steps)
@@ -375,6 +394,8 @@ class UniPCMultistepScheduler(SchedulerMixin, ConfigMixin):
                 )
             sigmas = np.concatenate([sigmas, [sigma_last]]).astype(np.float32)
         elif self.config.use_exponential_sigmas:
+            if sigmas is None:
+                sigmas = np.array(((1 - self.alphas_cumprod) / self.alphas_cumprod) ** 0.5)
             log_sigmas = np.log(sigmas)
             sigmas = np.flip(sigmas).copy()
             sigmas = self._convert_to_exponential(in_sigmas=sigmas, num_inference_steps=num_inference_steps)
@@ -389,6 +410,8 @@ class UniPCMultistepScheduler(SchedulerMixin, ConfigMixin):
                 )
             sigmas = np.concatenate([sigmas, [sigma_last]]).astype(np.float32)
         elif self.config.use_beta_sigmas:
+            if sigmas is None:
+                sigmas = np.array(((1 - self.alphas_cumprod) / self.alphas_cumprod) ** 0.5)
             log_sigmas = np.log(sigmas)
             sigmas = np.flip(sigmas).copy()
             sigmas = self._convert_to_beta(in_sigmas=sigmas, num_inference_steps=num_inference_steps)
@@ -403,9 +426,18 @@ class UniPCMultistepScheduler(SchedulerMixin, ConfigMixin):
                 )
             sigmas = np.concatenate([sigmas, [sigma_last]]).astype(np.float32)
         elif self.config.use_flow_sigmas:
-            alphas = np.linspace(1, 1 / self.config.num_train_timesteps, num_inference_steps + 1)
-            sigmas = 1.0 - alphas
-            sigmas = np.flip(self.config.flow_shift * sigmas / (1 + (self.config.flow_shift - 1) * sigmas))[:-1].copy()
+            if sigmas is None:
+                sigmas = np.linspace(1, 1 / self.config.num_train_timesteps, num_inference_steps + 1)[:-1]
+            if self.config.use_dynamic_shifting:
+                sigmas = self.time_shift(mu, 1.0, sigmas)
+            else:
+                sigmas = self.config.flow_shift * sigmas / (1 + (self.config.flow_shift - 1) * sigmas)
+            if self.config.shift_terminal:
+                sigmas = self.stretch_shift_to_terminal(sigmas)
+            eps = 1e-6
+            if np.fabs(sigmas[0] - 1) < eps:
+                # to avoid inf torch.log(alpha_si) in multistep_uni_p_bh_update during first/second update
+                sigmas[0] -= eps
             timesteps = (sigmas * self.config.num_train_timesteps).copy()
             if self.config.final_sigmas_type == "sigma_min":
                 sigma_last = sigmas[-1]
@@ -417,6 +449,8 @@ class UniPCMultistepScheduler(SchedulerMixin, ConfigMixin):
                 )
             sigmas = np.concatenate([sigmas, [sigma_last]]).astype(np.float32)
         else:
+            if sigmas is None:
+                sigmas = np.array(((1 - self.alphas_cumprod) / self.alphas_cumprod) ** 0.5)
             sigmas = np.interp(timesteps, np.arange(0, len(sigmas)), sigmas)
             if self.config.final_sigmas_type == "sigma_min":
                 sigma_last = ((1 - self.alphas_cumprod[0]) / self.alphas_cumprod[0]) ** 0.5
@@ -446,6 +480,43 @@ class UniPCMultistepScheduler(SchedulerMixin, ConfigMixin):
         self._begin_index = None
         self.sigmas = self.sigmas.to("cpu")  # to avoid too much CPU/GPU communication
 
+    # Copied from diffusers.schedulers.scheduling_flow_match_euler_discrete.FlowMatchEulerDiscreteScheduler.time_shift
+    def time_shift(self, mu: float, sigma: float, t: torch.Tensor):
+        if self.config.time_shift_type == "exponential":
+            return self._time_shift_exponential(mu, sigma, t)
+        elif self.config.time_shift_type == "linear":
+            return self._time_shift_linear(mu, sigma, t)
+
+    # Copied from diffusers.schedulers.scheduling_flow_match_euler_discrete.FlowMatchEulerDiscreteScheduler.stretch_shift_to_terminal
+    def stretch_shift_to_terminal(self, t: torch.Tensor) -> torch.Tensor:
+        r"""
+        Stretches and shifts the timestep schedule to ensure it terminates at the configured `shift_terminal` config
+        value.
+
+        Reference:
+        https://github.com/Lightricks/LTX-Video/blob/a01a171f8fe3d99dce2728d60a73fecf4d4238ae/ltx_video/schedulers/rf.py#L51
+
+        Args:
+            t (`torch.Tensor`):
+                A tensor of timesteps to be stretched and shifted.
+
+        Returns:
+            `torch.Tensor`:
+                A tensor of adjusted timesteps such that the final value equals `self.config.shift_terminal`.
+        """
+        one_minus_z = 1 - t
+        scale_factor = one_minus_z[-1] / (1 - self.config.shift_terminal)
+        stretched_t = 1 - (one_minus_z / scale_factor)
+        return stretched_t
+
+    # Copied from diffusers.schedulers.scheduling_flow_match_euler_discrete.FlowMatchEulerDiscreteScheduler._time_shift_exponential
+    def _time_shift_exponential(self, mu, sigma, t):
+        return math.exp(mu) / (math.exp(mu) + (1 / t - 1) ** sigma)
+
+    # Copied from diffusers.schedulers.scheduling_flow_match_euler_discrete.FlowMatchEulerDiscreteScheduler._time_shift_linear
+    def _time_shift_linear(self, mu, sigma, t):
+        return mu / (mu + (1 / t - 1) ** sigma)
+
     # Copied from diffusers.schedulers.scheduling_ddpm.DDPMScheduler._threshold_sample
     def _threshold_sample(self, sample: torch.Tensor) -> torch.Tensor:
         """

tests/pipelines/kandinsky2_2/test_kandinsky_inpaint.py

@@ -248,6 +248,9 @@ class KandinskyV22InpaintPipelineFastTests(PipelineTesterMixin, unittest.TestCas
     def test_float16_inference(self):
         super().test_float16_inference(expected_max_diff=5e-1)
 
+    def test_save_load_dduf(self):
+        super().test_save_load_dduf(atol=1e-3, rtol=1e-3)
+
     @is_flaky()
     def test_model_cpu_offload_forward_pass(self):
         super().test_inference_batch_single_identical(expected_max_diff=8e-4)

tests/pipelines/kandinsky3/test_kandinsky3_img2img.py

@@ -191,6 +191,9 @@ class Kandinsky3Img2ImgPipelineFastTests(PipelineTesterMixin, unittest.TestCase)
     def test_inference_batch_single_identical(self):
         super().test_inference_batch_single_identical(expected_max_diff=1e-2)
 
+    def test_save_load_dduf(self):
+        super().test_save_load_dduf(atol=1e-3, rtol=1e-3)
+
 
 @slow
 @require_torch_accelerator