MultiModal Diffusion Transformer (MMDiT) for Stable Diffusion 3

The RBLNSD3Transformer2DModel is the RBLN-optimized version of the core transformer block used in the Stable Diffusion 3 model.

This model replaces the UNet architecture used in previous Stable Diffusion versions. It processes latent image representations along with pooled embeddings from multiple text encoders and timestep information to perform the diffusion process.

Usage within Pipelines

Typically, you don't interact with RBLNSD3Transformer2DModel directly. Instead, it's automatically loaded and managed as part of an RBLN Stable Diffusion 3 pipeline, such as RBLNStableDiffusion3Pipeline.

When configuring an RBLN SD3 pipeline, you can pass specific settings for the transformer via the transformer argument in the pipeline's configuration object:

from optimum.rbln import RBLNStableDiffusion3PipelineConfig

# Example: Configure pipeline with specific batch size for the transformer
config = RBLNStableDiffusion3PipelineConfig(
    batch_size=1, # Pipeline inference batch size
    height=1024,
    width=1024,
    transformer=dict(
        batch_size=2 # Transformer batch size (e.g., doubled for CFG)
    )
)

# ... load pipeline using this config ...

Refer to the Stable Diffusion 3 Pipeline Documentation for details on pipeline usage and configuration, including handling guidance scale effects on the transformer's batch size.

API Reference

Classes

RBLNSD3Transformer2DModel

Bases: RBLNModel

RBLN implementation of SD3Transformer2DModel for diffusion models like Stable Diffusion 3.

The SD3Transformer2DModel takes text and/or image embeddings from encoders (like CLIP) and maps them to a shared latent space that guides the diffusion process to generate the desired image.

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

Functions

from_model(model, config=None, rbln_config=None, model_save_dir=None, subfolder='', **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
config	Optional[PretrainedConfig]	The configuration object associated with the model.	None
rbln_config	Optional[Union[RBLNModelConfig, Dict]]	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	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
RBLNModel	A RBLN model instance ready for inference on RBLN NPU devices.

from_pretrained(model_id, export=None, 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	Optional[bool]	A boolean flag to indicate whether the model should be compiled. If None, it will be determined based on the existence of the compiled model files in the model_id.	None
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	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
RBLNModel	A RBLN model instance ready for inference on RBLN NPU devices.

save_pretrained(save_directory, push_to_hub=False, **kwargs)

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

Parameters:

Name	Type	Description	Default
save_directory	Union[str, Path]	Directory where to save the model file.	required
push_to_hub	bool	Whether or not to push your model to the HuggingFace model hub after saving it.	False

Functions

Classes

RBLNSD3Transformer2DModelConfig

Bases: RBLNModelConfig

Configuration class for RBLN Stable Diffusion 3 Transformer models.

This class inherits from RBLNModelConfig and provides specific configuration options for Transformer models used in diffusion models like Stable Diffusion 3.

Functions

__init__(batch_size=None, sample_size=None, prompt_embed_length=None, **kwargs)

Parameters:

Name	Type	Description	Default
batch_size	Optional[int]	The batch size for inference. Defaults to 1.	None
sample_size	Optional[Union[int, 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
prompt_embed_length	Optional[int]	The length of the embedded prompt vectors that will be used to condition the transformer model.	None
kwargs	Any	Additional arguments passed to the parent RBLNModelConfig.	{}

Raises:

Type	Description
ValueError	If batch_size is not a positive integer.

load(path, **kwargs) classmethod

Load a RBLNModelConfig from a path.

Parameters:

Name	Type	Description	Default
path	str	Path to the RBLNModelConfig file or directory containing the config file.	required
kwargs	Any	Additional keyword arguments to override configuration values. Keys starting with 'rbln_' will have the prefix removed and be used to update the configuration.	{}

Returns:

Name	Type	Description
RBLNModelConfig	RBLNModelConfig	The loaded configuration instance.

Note

This method loads the configuration from the specified path and applies any provided overrides. If the loaded configuration class doesn't match the expected class, a warning will be logged.