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 오토파이프라인RBLNAutoPipelineForImage2Image: 이미지에서 이미지를 생성하는 모델들을 위한 오토파이프라인RBLNAutoPipelineForInpainting: 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¶
RBLNAutoPipelineForText2Image
¶
Bases: RBLNAutoPipelineBase, AutoPipelineForText2Image
Text2Image AutoPipeline for RBLN NPUs.
Functions¶
from_pretrained(model_id, **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
|
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 | |
kwargs
|
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 |
|---|---|
|
A RBLN model instance ready for inference on RBLN NPU devices. |
from_model(model, **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
|
The PyTorch model to be compiled. The object must be an instance of the HuggingFace transformers PreTrainedModel class. |
required | |
kwargs
|
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:
- Compiles the PyTorch model into an optimized RBLN graph
- Configures the model for the specified NPU device
- Creates the necessary runtime objects if requested
- Saves the compiled model and configurations
Returns:
| Type | Description |
|---|---|
|
A RBLN model instance ready for inference on RBLN NPU devices. |
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, **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
|
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 | |
kwargs
|
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 |
|---|---|
|
A RBLN model instance ready for inference on RBLN NPU devices. |
from_model(model, **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
|
The PyTorch model to be compiled. The object must be an instance of the HuggingFace transformers PreTrainedModel class. |
required | |
kwargs
|
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:
- Compiles the PyTorch model into an optimized RBLN graph
- Configures the model for the specified NPU device
- Creates the necessary runtime objects if requested
- Saves the compiled model and configurations
Returns:
| Type | Description |
|---|---|
|
A RBLN model instance ready for inference on RBLN NPU devices. |
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, **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
|
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 | |
kwargs
|
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 |
|---|---|
|
A RBLN model instance ready for inference on RBLN NPU devices. |
from_model(model, **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
|
The PyTorch model to be compiled. The object must be an instance of the HuggingFace transformers PreTrainedModel class. |
required | |
kwargs
|
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:
- Compiles the PyTorch model into an optimized RBLN graph
- Configures the model for the specified NPU device
- Creates the necessary runtime objects if requested
- Saves the compiled model and configurations
Returns:
| Type | Description |
|---|---|
|
A RBLN model instance ready for inference on RBLN NPU devices. |
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
|