diff --git a/jobs/process/BaseSDTrainProcess.py b/jobs/process/BaseSDTrainProcess.py
index fff81a75..8a06aa45 100644
--- a/jobs/process/BaseSDTrainProcess.py
+++ b/jobs/process/BaseSDTrainProcess.py
@@ -282,12 +282,34 @@ class BaseSDTrainProcess(BaseTrainProcess):
             items = glob.glob(os.path.join(self.save_root, pattern))
             # Separate files and directories
             safetensors_files = [f for f in items if f.endswith('.safetensors')]
+            pt_files = [f for f in items if f.endswith('.pt')]
             directories = [d for d in items if os.path.isdir(d) and not d.endswith('.safetensors')]
-            # Combine the list and sort by creation time
-            combined_items = safetensors_files + directories
+
+            # Sort the lists by creation time if they are not empty
+            if safetensors_files:
+                safetensors_files.sort(key=os.path.getctime)
+            if pt_files:
+                pt_files.sort(key=os.path.getctime)
+            if directories:
+                directories.sort(key=os.path.getctime)
+
+            # Combine and sort the lists
+            combined_items = safetensors_files + directories + pt_files
             combined_items.sort(key=os.path.getctime)
+
+            # Use slicing with a check to avoid 'NoneType' error
+            safetensors_to_remove = safetensors_files[
+                                    :-self.save_config.max_step_saves_to_keep] if safetensors_files else []
+            pt_files_to_remove = pt_files[:-self.save_config.max_step_saves_to_keep] if pt_files else []
+            directories_to_remove = directories[:-self.save_config.max_step_saves_to_keep] if directories else []
+            combined_items_to_remove = combined_items[
+                                       :-self.save_config.max_step_saves_to_keep] if combined_items else []
+
+            items_to_remove = safetensors_to_remove + pt_files_to_remove + directories_to_remove
+
             # remove all but the latest max_step_saves_to_keep
-            items_to_remove = combined_items[:-self.save_config.max_step_saves_to_keep]
+            # items_to_remove = combined_items[:-self.save_config.max_step_saves_to_keep]
+
             for item in items_to_remove:
                 self.print(f"Removing old save: {item}")
                 if os.path.isdir(item):
@@ -655,14 +677,15 @@ class BaseSDTrainProcess(BaseTrainProcess):
                     do_double = False
 
             with self.timer('prepare_noise'):
+                num_train_timesteps = self.sd.noise_scheduler.config['num_train_timesteps']
 
                 if self.train_config.noise_scheduler == 'lcm':
                     self.sd.noise_scheduler.set_timesteps(
-                        1000, device=self.device_torch, original_inference_steps=1000
+                        num_train_timesteps, device=self.device_torch, original_inference_steps=num_train_timesteps
                     )
                 else:
                     self.sd.noise_scheduler.set_timesteps(
-                        1000, device=self.device_torch
+                        num_train_timesteps, device=self.device_torch
                     )
 
                 # if self.train_config.timestep_sampling == 'style' or self.train_config.timestep_sampling == 'content':
diff --git a/toolkit/sampler.py b/toolkit/sampler.py
index 5e585279..7f014643 100644
--- a/toolkit/sampler.py
+++ b/toolkit/sampler.py
@@ -17,6 +17,8 @@ from diffusers import (
 
 from k_diffusion.external import CompVisDenoiser
 
+from toolkit.samplers.scheduling_ddpm import ADDPMScheduler
+
 # scheduler:
 SCHEDULER_LINEAR_START = 0.00085
 SCHEDULER_LINEAR_END = 0.0120
@@ -76,6 +78,8 @@ def get_sampler(
         scheduler_cls = KDPM2AncestralDiscreteScheduler
     elif sampler == "lcm":
         scheduler_cls = LCMScheduler
+    elif sampler == "addpm":
+        scheduler_cls = ADDPMScheduler
 
     config = copy.deepcopy(sdxl_sampler_config)
     config.update(sched_init_args)
diff --git a/toolkit/samplers/scheduling_ddpm.py b/toolkit/samplers/scheduling_ddpm.py
new file mode 100644
index 00000000..de9ed8de
--- /dev/null
+++ b/toolkit/samplers/scheduling_ddpm.py
@@ -0,0 +1,460 @@
+# Copyright 2023 UC Berkeley Team and The HuggingFace Team. All rights reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+# DISCLAIMER: This file is strongly influenced by https://github.com/ermongroup/ddim
+
+import math
+from dataclasses import dataclass
+from typing import List, Optional, Tuple, Union
+
+import numpy as np
+import torch
+
+from diffusers.configuration_utils import ConfigMixin, register_to_config
+from diffusers.utils import BaseOutput
+from diffusers.utils.torch_utils import randn_tensor
+from diffusers.schedulers.scheduling_utils import KarrasDiffusionSchedulers, SchedulerMixin
+
+
+@dataclass
+class DDPMSchedulerOutput(BaseOutput):
+    """
+    Output class for the scheduler's `step` function output.
+
+    Args:
+        prev_sample (`torch.FloatTensor` of shape `(batch_size, num_channels, height, width)` for images):
+            Computed sample `(x_{t-1})` of previous timestep. `prev_sample` should be used as next model input in the
+            denoising loop.
+        pred_original_sample (`torch.FloatTensor` of shape `(batch_size, num_channels, height, width)` for images):
+            The predicted denoised sample `(x_{0})` based on the model output from the current timestep.
+            `pred_original_sample` can be used to preview progress or for guidance.
+    """
+
+    prev_sample: torch.FloatTensor
+    pred_original_sample: Optional[torch.FloatTensor] = None
+
+
+def betas_for_alpha_bar(
+    num_diffusion_timesteps,
+    max_beta=0.999,
+    alpha_transform_type="cosine",
+):
+    """
+    Create a beta schedule that discretizes the given alpha_t_bar function, which defines the cumulative product of
+    (1-beta) over time from t = [0,1].
+
+    Contains a function alpha_bar that takes an argument t and transforms it to the cumulative product of (1-beta) up
+    to that part of the diffusion process.
+
+
+    Args:
+        num_diffusion_timesteps (`int`): the number of betas to produce.
+        max_beta (`float`): the maximum beta to use; use values lower than 1 to
+                     prevent singularities.
+        alpha_transform_type (`str`, *optional*, default to `cosine`): the type of noise schedule for alpha_bar.
+                     Choose from `cosine` or `exp`
+
+    Returns:
+        betas (`np.ndarray`): the betas used by the scheduler to step the model outputs
+    """
+    if alpha_transform_type == "cosine":
+
+        def alpha_bar_fn(t):
+            return math.cos((t + 0.008) / 1.008 * math.pi / 2) ** 2
+
+    elif alpha_transform_type == "exp":
+
+        def alpha_bar_fn(t):
+            return math.exp(t * -12.0)
+
+    else:
+        raise ValueError(f"Unsupported alpha_tranform_type: {alpha_transform_type}")
+
+    betas = []
+    for i in range(num_diffusion_timesteps):
+        t1 = i / num_diffusion_timesteps
+        t2 = (i + 1) / num_diffusion_timesteps
+        betas.append(min(1 - alpha_bar_fn(t2) / alpha_bar_fn(t1), max_beta))
+    return torch.tensor(betas, dtype=torch.float32)
+
+
+class ADDPMScheduler(SchedulerMixin, ConfigMixin):
+    """
+    `DDPMScheduler` explores the connections between denoising score matching and Langevin dynamics sampling.
+
+    This model inherits from [`SchedulerMixin`] and [`ConfigMixin`]. Check the superclass documentation for the generic
+    methods the library implements for all schedulers such as loading and saving.
+
+    Args:
+        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`, or `squaredcos_cap_v2`.
+        variance_type (`str`, defaults to `"fixed_small"`):
+            Clip the variance 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`, defaults to `True`):
+            Clip the predicted sample for numerical stability.
+        clip_sample_range (`float`, defaults to 1.0):
+            The maximum magnitude for sample clipping. Valid only when `clip_sample=True`.
+        prediction_type (`str`, defaults to `epsilon`, *optional*):
+            Prediction type of the scheduler function; can be `epsilon` (predicts the noise of the diffusion process),
+            `sample` (directly predicts the noisy sample`) or `v_prediction` (see section 2.4 of [Imagen
+            Video](https://imagen.research.google/video/paper.pdf) paper).
+        thresholding (`bool`, defaults to `False`):
+            Whether to use the "dynamic thresholding" method. This is unsuitable for latent-space diffusion models such
+            as Stable Diffusion.
+        dynamic_thresholding_ratio (`float`, defaults to 0.995):
+            The ratio for the dynamic thresholding method. Valid only when `thresholding=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 the [Common Diffusion Noise Schedules and
+            Sample Steps are Flawed](https://huggingface.co/papers/2305.08891) for more information.
+        steps_offset (`int`, defaults to 0):
+            An offset added to the inference steps. You can use a combination of `offset=1` and
+            `set_alpha_to_one=False` to make the last step use step 0 for the previous alpha product like in Stable
+            Diffusion.
+    """
+
+    _compatibles = [e.name for e in KarrasDiffusionSchedulers]
+    order = 1
+
+    @register_to_config
+    def __init__(
+        self,
+        num_train_timesteps: int = 1000,
+        beta_start: float = 0.0001,
+        beta_end: float = 0.02,
+        beta_schedule: str = "linear",
+        trained_betas: Optional[Union[np.ndarray, List[float]]] = None,
+        variance_type: str = "fixed_small",
+        clip_sample: bool = True,
+        prediction_type: str = "epsilon",
+        thresholding: bool = False,
+        dynamic_thresholding_ratio: float = 0.995,
+        clip_sample_range: float = 1.0,
+        sample_max_value: float = 1.0,
+        timestep_spacing: str = "leading",
+        steps_offset: int = 0,
+    ):
+        if trained_betas is not None:
+            self.betas = torch.tensor(trained_betas, dtype=torch.float32)
+        elif beta_schedule == "linear":
+            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
+            )
+        elif beta_schedule == "squaredcos_cap_v2":
+            # Glide cosine schedule
+            self.betas = betas_for_alpha_bar(num_train_timesteps)
+        elif beta_schedule == "sigmoid":
+            # GeoDiff sigmoid schedule
+            betas = torch.linspace(-6, 6, num_train_timesteps)
+            self.betas = torch.sigmoid(betas) * (beta_end - beta_start) + beta_start
+        else:
+            raise NotImplementedError(f"{beta_schedule} does is not implemented for {self.__class__}")
+
+        self.alphas = 1.0 - self.betas
+        self.alphas_cumprod = torch.cumprod(self.alphas, dim=0)
+        self.one = torch.tensor(1.0)
+
+        # standard deviation of the initial noise distribution
+        self.init_noise_sigma = 1.0
+        self.is_training = False
+
+        # setable values
+        self.custom_timesteps = False
+        self.num_inference_steps = None
+        self.timesteps = torch.from_numpy(np.arange(0, num_train_timesteps)[::-1].copy())
+
+        self.variance_type = variance_type
+
+    def scale_model_input(self, sample: torch.FloatTensor, timestep: Optional[int] = None) -> torch.FloatTensor:
+        """
+        Ensures interchangeability with schedulers that need to scale the denoising model input depending on the
+        current timestep.
+
+        Args:
+            sample (`torch.FloatTensor`):
+                The input sample.
+            timestep (`int`, *optional*):
+                The current timestep in the diffusion chain.
+
+        Returns:
+            `torch.FloatTensor`:
+                A scaled input sample.
+        """
+        return sample
+
+    def set_timesteps(
+        self,
+        num_inference_steps: Optional[int] = None,
+        device: Union[str, torch.device] = None,
+        timesteps: Optional[List[int]] = None,
+    ):
+        original_steps = 50 if num_inference_steps != 1000 else 1000
+        train_timesteps = self.config['num_train_timesteps']
+        strength = 1.0
+        c = train_timesteps // original_steps
+        # LCM Training Steps Schedule
+        lcm_origin_timesteps = np.asarray(list(range(1, int(original_steps * strength) + 1))) * c - 1
+        skipping_step = len(lcm_origin_timesteps) // num_inference_steps
+        # LCM Inference Steps Schedule
+        timesteps = lcm_origin_timesteps[::-skipping_step][:num_inference_steps]
+
+        self._step_index = None
+
+        self.timesteps = torch.from_numpy(timesteps.copy()).to(device)
+
+    def _get_variance(self, t, predicted_variance=None, variance_type=None):
+        prev_t = self.previous_timestep(t)
+
+        alpha_prod_t = self.alphas_cumprod[t]
+        alpha_prod_t_prev = self.alphas_cumprod[prev_t] if prev_t >= 0 else self.one
+        current_beta_t = 1 - alpha_prod_t / alpha_prod_t_prev
+
+        # For t > 0, compute predicted variance βt (see formula (6) and (7) from https://arxiv.org/pdf/2006.11239.pdf)
+        # and sample from it to get previous sample
+        # x_{t-1} ~ N(pred_prev_sample, variance) == add variance to pred_sample
+        variance = (1 - alpha_prod_t_prev) / (1 - alpha_prod_t) * current_beta_t
+
+        # we always take the log of variance, so clamp it to ensure it's not 0
+        variance = torch.clamp(variance, min=1e-20)
+
+        if variance_type is None:
+            variance_type = self.config.variance_type
+
+        # hacks - were probably added for training stability
+        if variance_type == "fixed_small":
+            variance = variance
+        # for rl-diffuser https://arxiv.org/abs/2205.09991
+        elif variance_type == "fixed_small_log":
+            variance = torch.log(variance)
+            variance = torch.exp(0.5 * variance)
+        elif variance_type == "fixed_large":
+            variance = current_beta_t
+        elif variance_type == "fixed_large_log":
+            # Glide max_log
+            variance = torch.log(current_beta_t)
+        elif variance_type == "learned":
+            return predicted_variance
+        elif variance_type == "learned_range":
+            min_log = torch.log(variance)
+            max_log = torch.log(current_beta_t)
+            frac = (predicted_variance + 1) / 2
+            variance = frac * max_log + (1 - frac) * min_log
+
+        return variance
+
+    def _threshold_sample(self, sample: torch.FloatTensor) -> torch.FloatTensor:
+        """
+        "Dynamic thresholding: At each sampling step we set s to a certain percentile absolute pixel value in xt0 (the
+        prediction of x_0 at timestep t), and if s > 1, then we threshold xt0 to the range [-s, s] and then divide by
+        s. Dynamic thresholding pushes saturated pixels (those near -1 and 1) inwards, thereby actively preventing
+        pixels from saturation at each step. We find that dynamic thresholding results in significantly better
+        photorealism as well as better image-text alignment, especially when using very large guidance weights."
+
+        https://arxiv.org/abs/2205.11487
+        """
+        dtype = sample.dtype
+        batch_size, channels, *remaining_dims = sample.shape
+
+        if dtype not in (torch.float32, torch.float64):
+            sample = sample.float()  # upcast for quantile calculation, and clamp not implemented for cpu half
+
+        # Flatten sample for doing quantile calculation along each image
+        sample = sample.reshape(batch_size, channels * np.prod(remaining_dims))
+
+        abs_sample = sample.abs()  # "a certain percentile absolute pixel value"
+
+        s = torch.quantile(abs_sample, self.config.dynamic_thresholding_ratio, dim=1)
+        s = torch.clamp(
+            s, min=1, max=self.config.sample_max_value
+        )  # When clamped to min=1, equivalent to standard clipping to [-1, 1]
+        s = s.unsqueeze(1)  # (batch_size, 1) because clamp will broadcast along dim=0
+        sample = torch.clamp(sample, -s, s) / s  # "we threshold xt0 to the range [-s, s] and then divide by s"
+
+        sample = sample.reshape(batch_size, channels, *remaining_dims)
+        sample = sample.to(dtype)
+
+        return sample
+
+    def step(
+        self,
+        model_output: torch.FloatTensor,
+        timestep: int,
+        sample: torch.FloatTensor,
+        generator=None,
+        return_dict: bool = True,
+    ) -> Union[DDPMSchedulerOutput, Tuple]:
+        """
+        Predict the sample from the previous timestep by reversing the SDE. This function propagates the diffusion
+        process from the learned model outputs (most often the predicted noise).
+
+        Args:
+            model_output (`torch.FloatTensor`):
+                The direct output from learned diffusion model.
+            timestep (`float`):
+                The current discrete timestep in the diffusion chain.
+            sample (`torch.FloatTensor`):
+                A current instance of a sample created by the diffusion process.
+            generator (`torch.Generator`, *optional*):
+                A random number generator.
+            return_dict (`bool`, *optional*, defaults to `True`):
+                Whether or not to return a [`~schedulers.scheduling_ddpm.DDPMSchedulerOutput`] or `tuple`.
+
+        Returns:
+            [`~schedulers.scheduling_ddpm.DDPMSchedulerOutput`] or `tuple`:
+                If return_dict is `True`, [`~schedulers.scheduling_ddpm.DDPMSchedulerOutput`] is returned, otherwise a
+                tuple is returned where the first element is the sample tensor.
+
+        """
+        t = timestep
+
+        prev_t = self.previous_timestep(t)
+
+        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
+
+        # 1. compute alphas, betas
+        alpha_prod_t = self.alphas_cumprod[t]
+        alpha_prod_t_prev = self.alphas_cumprod[prev_t] if prev_t >= 0 else self.one
+        beta_prod_t = 1 - alpha_prod_t
+        beta_prod_t_prev = 1 - alpha_prod_t_prev
+        current_alpha_t = alpha_prod_t / alpha_prod_t_prev
+        current_beta_t = 1 - current_alpha_t
+
+        # 2. compute predicted original sample from predicted noise also called
+        # "predicted x_0" of formula (15) from https://arxiv.org/pdf/2006.11239.pdf
+        if self.config.prediction_type == "epsilon":
+            pred_original_sample = (sample - beta_prod_t ** (0.5) * model_output) / alpha_prod_t ** (0.5)
+        elif self.config.prediction_type == "sample":
+            pred_original_sample = model_output
+        elif self.config.prediction_type == "v_prediction":
+            pred_original_sample = (alpha_prod_t**0.5) * sample - (beta_prod_t**0.5) * model_output
+        else:
+            raise ValueError(
+                f"prediction_type given as {self.config.prediction_type} must be one of `epsilon`, `sample` or"
+                " `v_prediction`  for the DDPMScheduler."
+            )
+
+        # 3. Clip or threshold "predicted x_0"
+        if self.config.thresholding:
+            pred_original_sample = self._threshold_sample(pred_original_sample)
+        elif self.config.clip_sample:
+            pred_original_sample = pred_original_sample.clamp(
+                -self.config.clip_sample_range, self.config.clip_sample_range
+            )
+
+        # 4. Compute coefficients for pred_original_sample x_0 and current sample x_t
+        # See formula (7) from https://arxiv.org/pdf/2006.11239.pdf
+        pred_original_sample_coeff = (alpha_prod_t_prev ** (0.5) * current_beta_t) / beta_prod_t
+        current_sample_coeff = current_alpha_t ** (0.5) * beta_prod_t_prev / beta_prod_t
+
+        # 5. Compute predicted previous sample µ_t
+        # See formula (7) from https://arxiv.org/pdf/2006.11239.pdf
+        pred_prev_sample = pred_original_sample_coeff * pred_original_sample + current_sample_coeff * sample
+
+        # 6. Add noise
+        variance = 0
+        if t > 0:
+            device = model_output.device
+            variance_noise = randn_tensor(
+                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
+            elif self.variance_type == "learned_range":
+                variance = self._get_variance(t, predicted_variance=predicted_variance)
+                variance = torch.exp(0.5 * variance) * variance_noise
+            else:
+                variance = (self._get_variance(t, predicted_variance=predicted_variance) ** 0.5) * variance_noise
+
+        pred_prev_sample = pred_prev_sample + variance
+
+        if not return_dict:
+            return (pred_prev_sample,)
+
+        return DDPMSchedulerOutput(prev_sample=pred_prev_sample, pred_original_sample=pred_original_sample)
+
+    def add_noise(
+        self,
+        original_samples: torch.FloatTensor,
+        noise: torch.FloatTensor,
+        timesteps: torch.IntTensor,
+    ) -> torch.FloatTensor:
+        # Make sure alphas_cumprod and timestep have same device and dtype as original_samples
+        alphas_cumprod = self.alphas_cumprod.to(device=original_samples.device, dtype=original_samples.dtype)
+        timesteps = timesteps.to(original_samples.device)
+
+        sqrt_alpha_prod = alphas_cumprod[timesteps] ** 0.5
+        sqrt_alpha_prod = sqrt_alpha_prod.flatten()
+        while len(sqrt_alpha_prod.shape) < len(original_samples.shape):
+            sqrt_alpha_prod = sqrt_alpha_prod.unsqueeze(-1)
+
+        sqrt_one_minus_alpha_prod = (1 - alphas_cumprod[timesteps]) ** 0.5
+        sqrt_one_minus_alpha_prod = sqrt_one_minus_alpha_prod.flatten()
+        while len(sqrt_one_minus_alpha_prod.shape) < len(original_samples.shape):
+            sqrt_one_minus_alpha_prod = sqrt_one_minus_alpha_prod.unsqueeze(-1)
+
+        noisy_samples = sqrt_alpha_prod * original_samples + sqrt_one_minus_alpha_prod * noise
+        return noisy_samples
+
+    def get_velocity(
+        self, sample: torch.FloatTensor, noise: torch.FloatTensor, timesteps: torch.IntTensor
+    ) -> torch.FloatTensor:
+        # Make sure alphas_cumprod and timestep have same device and dtype as sample
+        alphas_cumprod = self.alphas_cumprod.to(device=sample.device, dtype=sample.dtype)
+        timesteps = timesteps.to(sample.device)
+
+        sqrt_alpha_prod = alphas_cumprod[timesteps] ** 0.5
+        sqrt_alpha_prod = sqrt_alpha_prod.flatten()
+        while len(sqrt_alpha_prod.shape) < len(sample.shape):
+            sqrt_alpha_prod = sqrt_alpha_prod.unsqueeze(-1)
+
+        sqrt_one_minus_alpha_prod = (1 - alphas_cumprod[timesteps]) ** 0.5
+        sqrt_one_minus_alpha_prod = sqrt_one_minus_alpha_prod.flatten()
+        while len(sqrt_one_minus_alpha_prod.shape) < len(sample.shape):
+            sqrt_one_minus_alpha_prod = sqrt_one_minus_alpha_prod.unsqueeze(-1)
+
+        velocity = sqrt_alpha_prod * noise - sqrt_one_minus_alpha_prod * sample
+        return velocity
+
+    def __len__(self):
+        return self.config.num_train_timesteps
+
+    def previous_timestep(self, timestep):
+        if self.custom_timesteps:
+            index = (self.timesteps == timestep).nonzero(as_tuple=True)[0][0]
+            if index == self.timesteps.shape[0] - 1:
+                prev_t = torch.tensor(-1)
+            else:
+                prev_t = self.timesteps[index + 1]
+        else:
+            num_inference_steps = (
+                self.num_inference_steps if self.num_inference_steps else self.config.num_train_timesteps
+            )
+            prev_t = timestep - self.config.num_train_timesteps // num_inference_steps
+
+        return prev_t
diff --git a/toolkit/stable_diffusion_model.py b/toolkit/stable_diffusion_model.py
index 0b1e9a5b..c688cc9b 100644
--- a/toolkit/stable_diffusion_model.py
+++ b/toolkit/stable_diffusion_model.py
@@ -675,6 +675,9 @@ class StableDiffusion:
                 do_classifier_free_guidance = False
             elif latents.shape[0] * 2 != text_embeddings.text_embeds.shape[0]:
                 raise ValueError("Batch size of latents must be the same or half the batch size of text embeddings")
+        latents = latents.to(self.device_torch)
+        text_embeddings = text_embeddings.to(self.device_torch)
+        timestep = timestep.to(self.device_torch)
 
         if self.is_xl:
             with torch.no_grad():