AutoPipeline

AutoPipline은 이름이나 경로를 기반으로 비슷한 디퓨전 파이프라인 모델(가중치, 설정, 어휘 등)을 자동으로 불러옵니다. 이를 통해 사용자는 정확한 모델 아키텍처를 알지 못해도 모델을 쉽게 불러올 수 있습니다.

핵심 클래스

• RBLNAutoPipelineForText2Image: 문자에서 이미지를 생성하는 모델들을 위한 오토파이프라인
• RBLNAutoPipelineForImage2Image: 이미지에서 이미지를 생성하는 모델들을 위한 오토파이프라인
• RBLNAutoPipelineForInpainting: 채우기를 수행하는 모델을 위한 오토파이프라인

지원되는 파이프라인

• 텍스트-투-이미지 변환 (Text2Image)

Model	Model Architecture	AutoPipeline
Stable Diffusion	StableDiffusionPipeline	RBLNAutoPipelineForText2Image
Stable Diffusion + LoRA	StableDiffusionPipeline	RBLNAutoModelForText2Image
Stable Diffusion V3†	StableDiffusion3Pipeline	RBLNAutoPipelineForText2Image
Stable Diffusion XL	StableDiffusionXLPipeline	RBLNAutoPipelineForText2Image
Stable Diffusion XL + multi-LoRA	StableDiffusionXLPipeline	RBLNAutoModelForText2Image
SDXL-turbo	StableDiffusionXLPipeline	RBLNAutoPipelineForText2Image
Stable Diffusion + ControlNet	StableDiffusionControlNetPipeline	RBLNAutoPipelineForText2Image
Stable Diffusion XL + ControlNet	StableDiffusionXLControlNetPipeline	RBLNAutoPipelineForText2Image
Kandinsky V2.2	KandinskyV22CombinedPipeline	RBLNAutoPipelineForText2Image

• 이미지-투-이미지 변환 (Image2Image)

Model	Model Architecture	AutoPipeline
Stable Diffusion	StableDiffusionImg2ImgPipeline	RBLNAutoPipelineForImage2Image
Stable Diffusion V3†	StableDiffusion3Img2ImgPipeline	RBLNAutoPipelineForImage2Image
Stable Diffusion XL	StableDiffusionXLImg2ImgPipeline	RBLNAutoPipelineForImage2Image
SDXL-turbo	StableDiffusionXLImg2ImgPipeline	RBLNAutoPipelineForImage2Image
Stable Diffusion + ControlNet	StableDiffusionControlNetImg2ImgPipeline	RBLNAutoPipelineForImage2Image
Stable Diffusion XL + ControlNet	StableDiffusionXLControlNetImg2ImgPipeline	RBLNAutoPipelineForImage2Image
Kandinsky V2.2	KandinskyV22Img2ImgCombinedPipeline	RBLNAutoPipelineForImage2Image

• 인페인팅 (Inpainting)

Model	Model Architecture	AutoPipeline
Stable Diffusion	StableDiffusionInpaintPipeline	RBLNAutoPipelineForInpainting
Stable Diffusion V3†	StableDiffusion3InpaintPipeline	RBLNAutoPipelineForInpainting
Stable Diffusion XL	StableDiffusionXLInpaintPipeline	RBLNAutoPipelineForInpainting
Kandinsky V2.2	KandinskyV22InpaintCombinedPipeline	RBLNAutoPipelineForInpainting

API 참조

Classes

RBLNAutoPipelineBase

Functions

from_pretrained(model_id, *, export=None, rbln_config={}, **kwargs) classmethod

Load an RBLN-accelerated Diffusers pipeline from a pretrained checkpoint or a compiled RBLN artifact.

This method determines the concrete RBLN* model class that corresponds to the underlying Diffusers pipeline architecture and dispatches to that class's from_pretrained() implementation. If a compiled RBLN folder is detected at model_id (or export=False is explicitly passed), it loads the compiled artifacts; otherwise it compiles from the original Diffusers checkpoint.

Parameters:

Name	Type	Description	Default
model_id	Union[str, Path]	HF repo id or local path. For compiled models, this should point to a directory (optionally under subfolder) that contains *.rbln files and rbln_config.json.	required
export	bool	Force compilation from a Diffusers checkpoint. When None, this is inferred by checking whether compiled artifacts exist at model_id.	None
rbln_config	Union[Dict[str, Any], RBLNModelConfig]	RBLN compilation/runtime configuration. May be provided as a dictionary or as an instance of the specific model's config class (e.g., RBLNFluxPipelineConfig).	{}
kwargs	Any	Additional keyword arguments. - Arguments prefixed with rbln_ are forwarded to the RBLN config. - Remaining arguments are forwarded to the Diffusers loader.	{}

Returns:

Name	Type	Description
RBLNBaseModel		An instantiated RBLN model wrapping the Diffusers pipeline, ready for
		inference on RBLN NPUs.

register(rbln_cls, exist_ok=False) staticmethod

Register a new RBLN model class.

Parameters:

Name	Type	Description	Default
rbln_cls	Type[RBLNBaseModel]	The RBLN model class to register.	required
exist_ok	bool	Whether to allow registering an already registered model.	False

RBLNAutoPipelineForText2Image

Bases: RBLNAutoPipelineBase, AutoPipelineForText2Image

Text2Image AutoPipeline for RBLN NPUs.

Functions

from_pretrained(model_id, *, export=None, rbln_config={}, **kwargs) classmethod

Load an RBLN-accelerated Diffusers pipeline from a pretrained checkpoint or a compiled RBLN artifact.

This method determines the concrete RBLN* model class that corresponds to the underlying Diffusers pipeline architecture and dispatches to that class's from_pretrained() implementation. If a compiled RBLN folder is detected at model_id (or export=False is explicitly passed), it loads the compiled artifacts; otherwise it compiles from the original Diffusers checkpoint.

Parameters:

Name	Type	Description	Default
model_id	Union[str, Path]	HF repo id or local path. For compiled models, this should point to a directory (optionally under subfolder) that contains *.rbln files and rbln_config.json.	required
export	bool	Force compilation from a Diffusers checkpoint. When None, this is inferred by checking whether compiled artifacts exist at model_id.	None
rbln_config	Union[Dict[str, Any], RBLNModelConfig]	RBLN compilation/runtime configuration. May be provided as a dictionary or as an instance of the specific model's config class (e.g., RBLNFluxPipelineConfig).	{}
kwargs	Any	Additional keyword arguments. - Arguments prefixed with rbln_ are forwarded to the RBLN config. - Remaining arguments are forwarded to the Diffusers loader.	{}

Returns:

Name	Type	Description
RBLNBaseModel		An instantiated RBLN model wrapping the Diffusers pipeline, ready for
		inference on RBLN NPUs.

register(rbln_cls, exist_ok=False) staticmethod

Register a new RBLN model class.

Parameters:

Name	Type	Description	Default
rbln_cls	Type[RBLNBaseModel]	The RBLN model class to register.	required
exist_ok	bool	Whether to allow registering an already registered model.	False

RBLNAutoPipelineForImage2Image

Bases: RBLNAutoPipelineBase, AutoPipelineForImage2Image

Image2Image AutoPipeline for RBLN NPUs.

Functions

from_pretrained(model_id, *, export=None, rbln_config={}, **kwargs) classmethod

Load an RBLN-accelerated Diffusers pipeline from a pretrained checkpoint or a compiled RBLN artifact.

This method determines the concrete RBLN* model class that corresponds to the underlying Diffusers pipeline architecture and dispatches to that class's from_pretrained() implementation. If a compiled RBLN folder is detected at model_id (or export=False is explicitly passed), it loads the compiled artifacts; otherwise it compiles from the original Diffusers checkpoint.

Parameters:

Name	Type	Description	Default
model_id	Union[str, Path]	HF repo id or local path. For compiled models, this should point to a directory (optionally under subfolder) that contains *.rbln files and rbln_config.json.	required
export	bool	Force compilation from a Diffusers checkpoint. When None, this is inferred by checking whether compiled artifacts exist at model_id.	None
rbln_config	Union[Dict[str, Any], RBLNModelConfig]	RBLN compilation/runtime configuration. May be provided as a dictionary or as an instance of the specific model's config class (e.g., RBLNFluxPipelineConfig).	{}
kwargs	Any	Additional keyword arguments. - Arguments prefixed with rbln_ are forwarded to the RBLN config. - Remaining arguments are forwarded to the Diffusers loader.	{}

Returns:

Name	Type	Description
RBLNBaseModel		An instantiated RBLN model wrapping the Diffusers pipeline, ready for
		inference on RBLN NPUs.

register(rbln_cls, exist_ok=False) staticmethod

Register a new RBLN model class.

Parameters:

Name	Type	Description	Default
rbln_cls	Type[RBLNBaseModel]	The RBLN model class to register.	required
exist_ok	bool	Whether to allow registering an already registered model.	False

RBLNAutoPipelineForInpainting

Bases: RBLNAutoPipelineBase, AutoPipelineForInpainting

Inpainting AutoPipeline for RBLN NPUs.

Functions

from_pretrained(model_id, *, export=None, rbln_config={}, **kwargs) classmethod

Load an RBLN-accelerated Diffusers pipeline from a pretrained checkpoint or a compiled RBLN artifact.

This method determines the concrete RBLN* model class that corresponds to the underlying Diffusers pipeline architecture and dispatches to that class's from_pretrained() implementation. If a compiled RBLN folder is detected at model_id (or export=False is explicitly passed), it loads the compiled artifacts; otherwise it compiles from the original Diffusers checkpoint.

Parameters:

Name	Type	Description	Default
model_id	Union[str, Path]	HF repo id or local path. For compiled models, this should point to a directory (optionally under subfolder) that contains *.rbln files and rbln_config.json.	required
export	bool	Force compilation from a Diffusers checkpoint. When None, this is inferred by checking whether compiled artifacts exist at model_id.	None
rbln_config	Union[Dict[str, Any], RBLNModelConfig]	RBLN compilation/runtime configuration. May be provided as a dictionary or as an instance of the specific model's config class (e.g., RBLNFluxPipelineConfig).	{}
kwargs	Any	Additional keyword arguments. - Arguments prefixed with rbln_ are forwarded to the RBLN config. - Remaining arguments are forwarded to the Diffusers loader.	{}

Returns:

Name	Type	Description
RBLNBaseModel		An instantiated RBLN model wrapping the Diffusers pipeline, ready for
		inference on RBLN NPUs.

register(rbln_cls, exist_ok=False) staticmethod

Register a new RBLN model class.

Parameters:

Name	Type	Description	Default
rbln_cls	Type[RBLNBaseModel]	The RBLN model class to register.	required
exist_ok	bool	Whether to allow registering an already registered model.	False