Stable Diffusion ControlNet

ControlNet integrates conditional control into standard Stable Diffusion models (like v1.5), enabling image generation guided by auxiliary inputs such as canny edges, depth maps, or human pose estimations. Optimum RBLN provides accelerated pipelines for these models on RBLN NPUs.

Supported Pipelines

• Text-to-Image with ControlNet: Generate images from text prompts, guided by a control image.
• Image-to-Image with ControlNet: Modify an existing image based on a text prompt and a control image.

Key Classes

• RBLNStableDiffusionControlNetPipeline: Text-to-image pipeline with ControlNet guidance.
• RBLNStableDiffusionControlNetPipelineConfig: Configuration for the text-to-image ControlNet pipeline.
• RBLNStableDiffusionControlNetImg2ImgPipeline: Image-to-image pipeline with ControlNet guidance.
• RBLNStableDiffusionControlNetImg2ImgPipelineConfig: Configuration for the image-to-image ControlNet pipeline.
• RBLNControlNetModel: The RBLN-optimized ControlNet model itself.

Important: Batch Size Configuration for Guidance Scale

Batch Size and Guidance Scale

Similar to standard Stable Diffusion, using ControlNet pipelines with a guidance scale > 1.0 (the default is 7.5) doubles the effective batch size of both the UNet and the ControlNet model during runtime.

Ensure the batch_size specified in the unet and controlnet sections of your RBLNStableDiffusionControlNetPipelineConfig matches the expected runtime batch size (typically 2 × the inference batch size if guidance_scale > 1.0).

Default Behavior

If you don't explicitly set batch sizes for unet and controlnet in the configuration, Optimum RBLN assumes guidance_scale > 1.0 and automatically sets their batch sizes to 2 × the pipeline's batch_size.

API Reference

Classes

RBLNStableDiffusionControlNetPipeline

Bases: RBLNDiffusionMixin, StableDiffusionControlNetPipeline

Functions

from_pretrained(model_id, *, export=False, model_save_dir=None, rbln_config={}, lora_ids=None, lora_weights_names=None, lora_scales=None, **kwargs) classmethod

Load a pretrained diffusion pipeline from a model checkpoint, with optional compilation for RBLN NPUs.

This method has two distinct operating modes:

• When export=True: Takes a PyTorch-based diffusion model, compiles it for RBLN NPUs, and loads the compiled model
• When export=False: Loads an already compiled RBLN model from model_id without recompilation

It supports various diffusion pipelines including Stable Diffusion, Kandinsky, ControlNet, and other diffusers-based models.

Parameters:

Name	Type	Description	Default
model_id	str	The model ID or path to the pretrained model to load. Can be either: A model ID from the Hugging Face Hub A local path to a saved model directory	required
export	bool	If True, takes a PyTorch model from model_id and compiles it for RBLN NPU execution. If False, loads an already compiled RBLN model from model_id without recompilation.	False
model_save_dir	Optional[PathLike]	Directory to save the compiled model artifacts. Only used when export=True. If not provided and export=True, a temporary directory is used.	None
rbln_config	Dict[str, Any]	Configuration options for RBLN compilation. Can include settings for specific submodules such as text_encoder, unet, and vae. Configuration can be tailored to the specific pipeline being compiled.	{}
lora_ids	Optional[Union[str, List[str]]]	LoRA adapter ID(s) to load and apply before compilation. LoRA weights are fused into the model weights during compilation. Only used when export=True.	None
lora_weights_names	Optional[Union[str, List[str]]]	Names of specific LoRA weight files to load, corresponding to lora_ids. Only used when export=True.	None
lora_scales	Optional[Union[float, List[float]]]	Scaling factor(s) to apply to the LoRA adapter(s). Only used when export=True.	None
**kwargs	Dict[str, Any]	Additional arguments to pass to the underlying diffusion pipeline constructor or the RBLN compilation process. These may include parameters specific to individual submodules or the particular diffusion pipeline being used.	{}

Returns:

Type	Description
Self	A compiled diffusion pipeline that can be used for inference on RBLN NPU. The returned object is an instance of the class that called this method, inheriting from RBLNDiffusionMixin.

RBLNStableDiffusionControlNetImg2ImgPipeline

Bases: RBLNDiffusionMixin, StableDiffusionControlNetImg2ImgPipeline

Functions

from_pretrained(model_id, *, export=False, model_save_dir=None, rbln_config={}, lora_ids=None, lora_weights_names=None, lora_scales=None, **kwargs) classmethod

Load a pretrained diffusion pipeline from a model checkpoint, with optional compilation for RBLN NPUs.

This method has two distinct operating modes:

• When export=True: Takes a PyTorch-based diffusion model, compiles it for RBLN NPUs, and loads the compiled model
• When export=False: Loads an already compiled RBLN model from model_id without recompilation

It supports various diffusion pipelines including Stable Diffusion, Kandinsky, ControlNet, and other diffusers-based models.

Parameters:

Name	Type	Description	Default
model_id	str	The model ID or path to the pretrained model to load. Can be either: A model ID from the Hugging Face Hub A local path to a saved model directory	required
export	bool	If True, takes a PyTorch model from model_id and compiles it for RBLN NPU execution. If False, loads an already compiled RBLN model from model_id without recompilation.	False
model_save_dir	Optional[PathLike]	Directory to save the compiled model artifacts. Only used when export=True. If not provided and export=True, a temporary directory is used.	None
rbln_config	Dict[str, Any]	Configuration options for RBLN compilation. Can include settings for specific submodules such as text_encoder, unet, and vae. Configuration can be tailored to the specific pipeline being compiled.	{}
lora_ids	Optional[Union[str, List[str]]]	LoRA adapter ID(s) to load and apply before compilation. LoRA weights are fused into the model weights during compilation. Only used when export=True.	None
lora_weights_names	Optional[Union[str, List[str]]]	Names of specific LoRA weight files to load, corresponding to lora_ids. Only used when export=True.	None
lora_scales	Optional[Union[float, List[float]]]	Scaling factor(s) to apply to the LoRA adapter(s). Only used when export=True.	None
**kwargs	Dict[str, Any]	Additional arguments to pass to the underlying diffusion pipeline constructor or the RBLN compilation process. These may include parameters specific to individual submodules or the particular diffusion pipeline being used.	{}

Returns:

Type	Description
Self	A compiled diffusion pipeline that can be used for inference on RBLN NPU. The returned object is an instance of the class that called this method, inheriting from RBLNDiffusionMixin.

Classes

RBLNStableDiffusionControlNetPipelineBaseConfig

Bases: RBLNModelConfig

Functions

__init__(text_encoder=None, unet=None, vae=None, controlnet=None, *, batch_size=None, img_height=None, img_width=None, sample_size=None, image_size=None, guidance_scale=None, **kwargs)

Parameters:

Name	Type	Description	Default
text_encoder	Optional[RBLNCLIPTextModelConfig]	Configuration for the text encoder component.	None
unet	Optional[RBLNUNet2DConditionModelConfig]	Configuration for the UNet model component.	None
vae	Optional[RBLNAutoencoderKLConfig]	Configuration for the VAE model component.	None
controlnet	Optional[RBLNControlNetModelConfig]	Configuration for the ControlNet model component.	None
batch_size	Optional[int]	Batch size for inference, applied to all submodules.	None
img_height	Optional[int]	Height of the generated images.	None
img_width	Optional[int]	Width of the generated images.	None
sample_size	Optional[Tuple[int, int]]	Spatial dimensions for the UNet model.	None
image_size	Optional[Tuple[int, int]]	Alternative way to specify image dimensions.	None
guidance_scale	Optional[float]	Scale for classifier-free guidance.	None
**kwargs	Dict[str, Any]	Additional arguments.	{}

Note

Guidance scale affects UNet and ControlNet batch sizes. If guidance_scale > 1.0, their batch sizes are doubled.

RBLNStableDiffusionControlNetPipelineConfig

Bases: RBLNStableDiffusionControlNetPipelineBaseConfig

Functions

__init__(text_encoder=None, unet=None, vae=None, controlnet=None, *, batch_size=None, img_height=None, img_width=None, sample_size=None, image_size=None, guidance_scale=None, **kwargs)

Parameters:

Name	Type	Description	Default
text_encoder	Optional[RBLNCLIPTextModelConfig]	Configuration for the text encoder component.	None
unet	Optional[RBLNUNet2DConditionModelConfig]	Configuration for the UNet model component.	None
vae	Optional[RBLNAutoencoderKLConfig]	Configuration for the VAE model component.	None
controlnet	Optional[RBLNControlNetModelConfig]	Configuration for the ControlNet model component.	None
batch_size	Optional[int]	Batch size for inference, applied to all submodules.	None
img_height	Optional[int]	Height of the generated images.	None
img_width	Optional[int]	Width of the generated images.	None
sample_size	Optional[Tuple[int, int]]	Spatial dimensions for the UNet model.	None
image_size	Optional[Tuple[int, int]]	Alternative way to specify image dimensions.	None
guidance_scale	Optional[float]	Scale for classifier-free guidance.	None
**kwargs	Dict[str, Any]	Additional arguments.	{}

Note

Guidance scale affects UNet and ControlNet batch sizes. If guidance_scale > 1.0, their batch sizes are doubled.

RBLNStableDiffusionControlNetImg2ImgPipelineConfig

Bases: RBLNStableDiffusionControlNetPipelineBaseConfig

Functions

__init__(text_encoder=None, unet=None, vae=None, controlnet=None, *, batch_size=None, img_height=None, img_width=None, sample_size=None, image_size=None, guidance_scale=None, **kwargs)

Parameters:

Name	Type	Description	Default
text_encoder	Optional[RBLNCLIPTextModelConfig]	Configuration for the text encoder component.	None
unet	Optional[RBLNUNet2DConditionModelConfig]	Configuration for the UNet model component.	None
vae	Optional[RBLNAutoencoderKLConfig]	Configuration for the VAE model component.	None
controlnet	Optional[RBLNControlNetModelConfig]	Configuration for the ControlNet model component.	None
batch_size	Optional[int]	Batch size for inference, applied to all submodules.	None
img_height	Optional[int]	Height of the generated images.	None
img_width	Optional[int]	Width of the generated images.	None
sample_size	Optional[Tuple[int, int]]	Spatial dimensions for the UNet model.	None
image_size	Optional[Tuple[int, int]]	Alternative way to specify image dimensions.	None
guidance_scale	Optional[float]	Scale for classifier-free guidance.	None
**kwargs	Dict[str, Any]	Additional arguments.	{}

Note

Guidance scale affects UNet and ControlNet batch sizes. If guidance_scale > 1.0, their batch sizes are doubled.