Skip to content

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.

Key Class

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:

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
from optimum.rbln import RBLNStableDiffusion3PipelineConfig

# Example: Configure pipeline with specific batch size for the transformer
config = RBLNStableDiffusion3PipelineConfig(
    batch_size=1, # Pipeline inference batch size
    img_height=1024,
    img_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 wrapper for the Stable Diffusion 3 MMDiT Transformer model.

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

RBLNSD3Transformer2DModelConfig

Bases: RBLNModelConfig

Configuration class for RBLN Stable Diffusion 3 Transformer models.

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 input latent 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 Dict[str, Any]

Additional arguments passed to the parent RBLNModelConfig.

 {}