Skip to content

UNet2DCondition

The UNet2DCondition model is a key component in diffusion-based image generation models like Stable Diffusion. It predicts the noise that should be removed from a noisy image at each denoising step. RBLN NPUs can accelerate UNet2DCondition model inference using Optimum RBLN.

Key Classes

API Reference

Classes

RBLNUNet2DConditionModel

Bases: RBLNModel

RBLN implementation of UNet2DConditionModel for diffusion models.

This model is used to accelerate UNet2DCondition models from diffusers library on RBLN NPUs. It is a key component in diffusion-based image generation models like Stable Diffusion.

This class inherits from [RBLNModel]. Check the superclass documentation for the generic methods the library implements for all its models.

Functions

from_pretrained(model_id, export=False, rbln_config=None, **kwargs) classmethod

The from_pretrained() function is utilized in its standard form as in the HuggingFace transformers library. User can use this function to load a pre-trained model from the HuggingFace library and convert it to a RBLN model to be run on RBLN NPUs.

Parameters:

Name Type Description Default
model_id Union[str, Path]

The model id of the pre-trained model to be loaded. It can be downloaded from the HuggingFace model hub or a local path, or a model id of a compiled model using the RBLN Compiler.

required
export bool

A boolean flag to indicate whether the model should be compiled.

False
rbln_config Optional[Union[Dict, RBLNModelConfig]]

Configuration for RBLN model compilation and runtime. This can be provided as a dictionary or an instance of the model's configuration class (e.g., RBLNLlamaForCausalLMConfig for Llama models). For detailed configuration options, see the specific model's configuration class documentation.

None
kwargs Dict[str, Any]

Additional keyword arguments. Arguments with the prefix 'rbln_' are passed to rbln_config, while the remaining arguments are passed to the HuggingFace library.

{}

Returns:

Type Description
Self

A RBLN model instance ready for inference on RBLN NPU devices.

from_model(model, *, rbln_config=None, **kwargs) classmethod

Converts and compiles a pre-trained HuggingFace library model into a RBLN model. This method performs the actual model conversion and compilation process.

Parameters:

Name Type Description Default
model PreTrainedModel

The PyTorch model to be compiled. The object must be an instance of the HuggingFace transformers PreTrainedModel class.

required
rbln_config Optional[Union[Dict, RBLNModelConfig]]

Configuration for RBLN model compilation and runtime. This can be provided as a dictionary or an instance of the model's configuration class (e.g., RBLNLlamaForCausalLMConfig for Llama models). For detailed configuration options, see the specific model's configuration class documentation.

None
kwargs Dict[str, Any]

Additional keyword arguments. Arguments with the prefix 'rbln_' are passed to rbln_config, while the remaining arguments are passed to the HuggingFace library.

{}

The method performs the following steps:

  1. Compiles the PyTorch model into an optimized RBLN graph
  2. Configures the model for the specified NPU device
  3. Creates the necessary runtime objects if requested
  4. Saves the compiled model and configurations

Returns:

Type Description
Self

A RBLN model instance ready for inference on RBLN NPU devices.

save_pretrained(save_directory)

Saves a model and its configuration file to a directory, so that it can be re-loaded using the [from_pretrained] class method.

Parameters:

Name Type Description Default
save_directory Union[str, PathLike]

The directory to save the model and its configuration files. Will be created if it doesn't exist.

required

Classes

RBLNUNet2DConditionModelConfig

Bases: RBLNModelConfig

Configuration class for RBLN UNet2DCondition models.

This class inherits from RBLNModelConfig and provides specific configuration options for UNet2DCondition models used in diffusion-based image generation.

Functions

__init__(batch_size=None, sample_size=None, in_channels=None, cross_attention_dim=None, use_additional_residuals=None, max_seq_len=None, in_features=None, text_model_hidden_size=None, image_model_hidden_size=None, **kwargs)

Parameters:

Name Type Description Default
batch_size Optional[int]

The batch size for inference. Defaults to 1.

None
sample_size Optional[Tuple[int, int]]

The spatial dimensions (height, width) of the generated samples. If an integer is provided, it's used for both height and width.

None
in_channels Optional[int]

Number of input channels for the UNet.

None
cross_attention_dim Optional[int]

Dimension of the cross-attention features.

None
use_additional_residuals Optional[bool]

Whether to use additional residual connections in the model.

None
max_seq_len Optional[int]

Maximum sequence length for text inputs when used with cross-attention.

None
in_features Optional[int]

Number of input features for the model.

None
text_model_hidden_size Optional[int]

Hidden size of the text encoder model.

None
image_model_hidden_size Optional[int]

Hidden size of the image encoder model.

None
**kwargs Dict[str, Any]

Additional arguments passed to the parent RBLNModelConfig.

{}