diff --git a/src/diffusers/pipelines/cogview4/pipeline_cogview4.py b/src/diffusers/pipelines/cogview4/pipeline_cogview4.py index 546718d57d..22510f5d9d 100644 --- a/src/diffusers/pipelines/cogview4/pipeline_cogview4.py +++ b/src/diffusers/pipelines/cogview4/pipeline_cogview4.py @@ -13,6 +13,7 @@ # See the License for the specific language governing permissions and # limitations under the License. +import inspect from typing import Any, Callable, Dict, List, Optional, Tuple, Union import numpy as np @@ -27,7 +28,6 @@ from ...pipelines.pipeline_utils import DiffusionPipeline from ...schedulers import FlowMatchEulerDiscreteScheduler from ...utils import is_torch_xla_available, logging, replace_example_docstring from ...utils.torch_utils import randn_tensor -from ..pipeline_utils import retrieve_timesteps from .pipeline_output import CogView4PipelineOutput @@ -67,6 +67,73 @@ def calculate_shift( return mu +def retrieve_timesteps( + scheduler, + num_inference_steps: Optional[int] = None, + device: Optional[Union[str, torch.device]] = None, + timesteps: Optional[List[int]] = None, + sigmas: Optional[List[float]] = None, + **kwargs, +): + r""" + Calls the scheduler's `set_timesteps` method and retrieves timesteps from the scheduler after the call. Handles + custom timesteps. Any kwargs will be supplied to `scheduler.set_timesteps`. + + Args: + scheduler (`SchedulerMixin`): + The scheduler to get timesteps from. + num_inference_steps (`int`): + 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*): + The device to which the timesteps should be moved to. If `None`, the timesteps are not moved. + timesteps (`List[int]`, *optional*): + Custom timesteps used to override the timestep spacing strategy of the scheduler. If `timesteps` is passed, + `num_inference_steps` and `sigmas` must be `None`. + sigmas (`List[float]`, *optional*): + Custom sigmas used to override the timestep spacing strategy of the scheduler. If `sigmas` is passed, + `num_inference_steps` and `timesteps` must be `None`. + + Returns: + `Tuple[torch.Tensor, int]`: A tuple where the first element is the timestep schedule from the scheduler and the + second element is the number of inference steps. + """ + accepts_timesteps = "timesteps" in set(inspect.signature(scheduler.set_timesteps).parameters.keys()) + accepts_sigmas = "sigmas" in set(inspect.signature(scheduler.set_timesteps).parameters.keys()) + + if timesteps is not None and sigmas is not None: + if not accepts_timesteps and not accepts_sigmas: + raise ValueError( + f"The current scheduler class {scheduler.__class__}'s `set_timesteps` does not support custom" + f" timestep or sigma schedules. Please check whether you are using the correct scheduler." + ) + scheduler.set_timesteps(timesteps=timesteps, sigmas=sigmas, device=device, **kwargs) + timesteps = scheduler.timesteps + num_inference_steps = len(timesteps) + elif timesteps is not None and sigmas is None: + if not accepts_timesteps: + raise ValueError( + f"The current scheduler class {scheduler.__class__}'s `set_timesteps` does not support custom" + f" timestep schedules. Please check whether you are using the correct scheduler." + ) + scheduler.set_timesteps(timesteps=timesteps, device=device, **kwargs) + timesteps = scheduler.timesteps + num_inference_steps = len(timesteps) + elif timesteps is None and sigmas is not None: + if not accepts_sigmas: + raise ValueError( + f"The current scheduler class {scheduler.__class__}'s `set_timesteps` does not support custom" + f" sigmas schedules. Please check whether you are using the correct scheduler." + ) + scheduler.set_timesteps(sigmas=sigmas, device=device, **kwargs) + timesteps = scheduler.timesteps + num_inference_steps = len(timesteps) + else: + scheduler.set_timesteps(num_inference_steps, device=device, **kwargs) + timesteps = scheduler.timesteps + return timesteps, num_inference_steps + + class CogView4Pipeline(DiffusionPipeline, CogView4LoraLoaderMixin): r""" Pipeline for text-to-image generation using CogView4. diff --git a/src/diffusers/pipelines/cogview4/pipeline_cogview4_control.py b/src/diffusers/pipelines/cogview4/pipeline_cogview4_control.py index 33617b3d17..e26b7ba415 100644 --- a/src/diffusers/pipelines/cogview4/pipeline_cogview4_control.py +++ b/src/diffusers/pipelines/cogview4/pipeline_cogview4_control.py @@ -13,6 +13,7 @@ # See the License for the specific language governing permissions and # limitations under the License. +import inspect from typing import Any, Callable, Dict, List, Optional, Tuple, Union import numpy as np @@ -26,7 +27,6 @@ from ...pipelines.pipeline_utils import DiffusionPipeline from ...schedulers import FlowMatchEulerDiscreteScheduler from ...utils import is_torch_xla_available, logging, replace_example_docstring from ...utils.torch_utils import randn_tensor -from ..pipeline_utils import retrieve_timesteps from .pipeline_output import CogView4PipelineOutput @@ -68,6 +68,74 @@ def calculate_shift( return mu +# Copied from diffusers.pipelines.cogview4.pipeline_cogview4.retrieve_timesteps +def retrieve_timesteps( + scheduler, + num_inference_steps: Optional[int] = None, + device: Optional[Union[str, torch.device]] = None, + timesteps: Optional[List[int]] = None, + sigmas: Optional[List[float]] = None, + **kwargs, +): + r""" + Calls the scheduler's `set_timesteps` method and retrieves timesteps from the scheduler after the call. Handles + custom timesteps. Any kwargs will be supplied to `scheduler.set_timesteps`. + + Args: + scheduler (`SchedulerMixin`): + The scheduler to get timesteps from. + num_inference_steps (`int`): + 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*): + The device to which the timesteps should be moved to. If `None`, the timesteps are not moved. + timesteps (`List[int]`, *optional*): + Custom timesteps used to override the timestep spacing strategy of the scheduler. If `timesteps` is passed, + `num_inference_steps` and `sigmas` must be `None`. + sigmas (`List[float]`, *optional*): + Custom sigmas used to override the timestep spacing strategy of the scheduler. If `sigmas` is passed, + `num_inference_steps` and `timesteps` must be `None`. + + Returns: + `Tuple[torch.Tensor, int]`: A tuple where the first element is the timestep schedule from the scheduler and the + second element is the number of inference steps. + """ + accepts_timesteps = "timesteps" in set(inspect.signature(scheduler.set_timesteps).parameters.keys()) + accepts_sigmas = "sigmas" in set(inspect.signature(scheduler.set_timesteps).parameters.keys()) + + if timesteps is not None and sigmas is not None: + if not accepts_timesteps and not accepts_sigmas: + raise ValueError( + f"The current scheduler class {scheduler.__class__}'s `set_timesteps` does not support custom" + f" timestep or sigma schedules. Please check whether you are using the correct scheduler." + ) + scheduler.set_timesteps(timesteps=timesteps, sigmas=sigmas, device=device, **kwargs) + timesteps = scheduler.timesteps + num_inference_steps = len(timesteps) + elif timesteps is not None and sigmas is None: + if not accepts_timesteps: + raise ValueError( + f"The current scheduler class {scheduler.__class__}'s `set_timesteps` does not support custom" + f" timestep schedules. Please check whether you are using the correct scheduler." + ) + scheduler.set_timesteps(timesteps=timesteps, device=device, **kwargs) + timesteps = scheduler.timesteps + num_inference_steps = len(timesteps) + elif timesteps is None and sigmas is not None: + if not accepts_sigmas: + raise ValueError( + f"The current scheduler class {scheduler.__class__}'s `set_timesteps` does not support custom" + f" sigmas schedules. Please check whether you are using the correct scheduler." + ) + scheduler.set_timesteps(sigmas=sigmas, device=device, **kwargs) + timesteps = scheduler.timesteps + num_inference_steps = len(timesteps) + else: + scheduler.set_timesteps(num_inference_steps, device=device, **kwargs) + timesteps = scheduler.timesteps + return timesteps, num_inference_steps + + class CogView4ControlPipeline(DiffusionPipeline): r""" Pipeline for text-to-image generation using CogView4.