Skip to content

Prior Transformer

The Prior Transformer model is a key component in the Kandinsky V2.2 architecture. RBLN NPUs can accelerate Prior Transformer inference using RBLN Optimum.

Supported NPU

Diffusers pipelines run on ATOM™ only. Rebel100™ does not support them yet.

API Reference

RBLNPriorTransformer

Bases: RBLNModel

RBLN implementation of PriorTransformer for diffusion models like Kandinsky V2.2.

The PriorTransformer 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.

forward(hidden_states, timestep, proj_embedding, encoder_hidden_states=None, attention_mask=None, return_dict=True)

Forward pass for the RBLN-optimized PriorTransformer.

Parameters:

Name Type Description Default
hidden_states Tensor

The currently predicted image embeddings.

 required
timestep Tensor | float | int

Current denoising step.

 required
proj_embedding Tensor

Projected embedding vector the denoising process is conditioned on.

 required
encoder_hidden_states Tensor | None

Hidden states of the text embeddings the denoising process is conditioned on.

 None
attention_mask Tensor | None

Text mask for the text embeddings.

 None
return_dict bool

Whether or not to return a [~diffusers.models.transformers.prior_transformer.PriorTransformerOutput] instead of a plain tuple.

 True

Returns:

Type Description
PriorTransformerOutput | tuple

(~diffusers.models.transformers.prior_transformer.PriorTransformerOutput | tuple)

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 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 | None

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 dict | RBLNModelConfig | None

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.

get_hf_class() classmethod

Lazily load and cache the HuggingFace class this model wraps.

The class is looked up in hf_library_name under the name without the RBLN prefix (e.g. RBLNLlamaForCausalLM -> LlamaForCausalLM).

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 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

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 | ModelMixin

The PyTorch model to be compiled. The object must be a HuggingFace transformers PreTrainedModel or a Diffusers component based on diffusers.ModelMixin, such as a VAE, UNet or ControlNet.

 required
config PretrainedConfig | None

The configuration object associated with the model.

 None
rbln_config RBLNModelConfig | dict | None

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.

RBLNPriorTransformerConfig

Bases: RBLNModelConfig

Configuration class for RBLN Prior Transformer models.

This class inherits from RBLNModelConfig and provides specific configuration options for Transformer models used in diffusion models like Kandinsky V2.2.

__init__(batch_size=None, embedding_dim=None, num_embeddings=None, **kwargs)

Parameters:

Name Type Description Default
batch_size int | None

The batch size for inference. Defaults to 1.

 None
embedding_dim int | None

Dimension of the embedding vectors in the model.

 None
num_embeddings int | None

Number of discrete embeddings in the codebook.

 None
kwargs Any

Additional arguments passed to the parent RBLNModelConfig.

 {}

Raises:

Type Description
ValueError

If batch_size is not a positive integer.

from_pretrained(path, rbln_config=None, return_unused_kwargs=False, **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
rbln_config dict[str, Any] | None

Additional configuration to override.

 None
return_unused_kwargs bool

Whether to return unused kwargs.

 False
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 Self | tuple[Self, dict[str, Any]]

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.

Examples:

1
config = RBLNResNetForImageClassificationConfig.from_pretrained("/path/to/model")

initialize_submodule_config(submodule_config=None, force_kwargs=False, **kwargs)

Build the config of a submodule from the parent's runtime options and kwargs.

Returns the submodule config instance when its class is known (an instance was passed, or cls_name was given), otherwise the merged kwargs dict for the model class to resolve later.

get_load_overrides()

Extract the options that must cross the load boundary, for passing to from_pretrained.

Returns the explicitly-set runtime options (device, device_map, create_runtimes, activate_profiler, timeout) and the subclass-specific non-save attributes (load-behavior flags such as _load_visual_runtime, which are never serialized so they can only travel with the caller), recursively including submodules. Compile-time attributes are not included: when loading a compiled model they come from the artifact's rbln_config.json, and this dict is merged on top of it.

Returns:

Type Description
dict[str, Any]

Dictionary of load overrides, keyed like the rbln_config dict accepted by from_pretrained.