Skip to content

Stable Diffusion XL ControlNet

ControlNet can also be applied to the more advanced Stable Diffusion XL (SDXL) model, allowing for high-resolution image generation with precise structural guidance from condition images. Optimum RBLN provides accelerated SDXL ControlNet pipelines for RBLN NPUs.

Supported Pipelines

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

Key Classes

Important: Batch Size Configuration for Guidance Scale

Batch Size and Guidance Scale (SDXL)

As with other SDXL pipelines, using ControlNet SDXL pipelines with guidance_scale > 1.0 doubles the effective batch size of the UNet and the ControlNet model.

Ensure the batch_size specified in the unet and controlnet sections of your RBLNStableDiffusionXLControlNetPipelineConfig matches the expected runtime batch size (typically 2 × the inference batch size if guidance_scale > 1.0). Omitting these will result in automatic doubling based on the pipeline's batch_size.

API Reference

Classes

RBLNStableDiffusionXLControlNetPipeline

Bases: RBLNDiffusionMixin, StableDiffusionXLControlNetPipeline

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.

RBLNStableDiffusionXLControlNetImg2ImgPipeline

Bases: RBLNDiffusionMixin, StableDiffusionXLControlNetImg2ImgPipeline

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

RBLNStableDiffusionXLControlNetPipelineBaseConfig

Bases: RBLNModelConfig

Functions

__init__(text_encoder=None, text_encoder_2=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 primary text encoder.

None
text_encoder_2 Optional[RBLNCLIPTextModelWithProjectionConfig]

Configuration for the secondary text encoder.

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.

RBLNStableDiffusionXLControlNetPipelineConfig

Bases: RBLNStableDiffusionXLControlNetPipelineBaseConfig

Functions

__init__(text_encoder=None, text_encoder_2=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 primary text encoder.

None
text_encoder_2 Optional[RBLNCLIPTextModelWithProjectionConfig]

Configuration for the secondary text encoder.

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.

RBLNStableDiffusionXLControlNetImg2ImgPipelineConfig

Bases: RBLNStableDiffusionXLControlNetPipelineBaseConfig

Functions

__init__(text_encoder=None, text_encoder_2=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 primary text encoder.

None
text_encoder_2 Optional[RBLNCLIPTextModelWithProjectionConfig]

Configuration for the secondary text encoder.

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.