diffusers/pr_12595/zh/hybrid_inference/api_reference.md

混合推理 API 参考

远程解码[[diffusers.utils.remote_decode]]

diffusers.utils.remote_decodediffusers.utils.remote_decodehttps://github.com/huggingface/diffusers/blob/vr_12595/src/diffusers/utils/remote_utils.py#L188[{"name": "endpoint", "val": ": str"}, {"name": "tensor", "val": ": torch.Tensor"}, {"name": "processor", "val": ": typing.Union[ForwardRef('VaeImageProcessor'), ForwardRef('VideoProcessor'), NoneType] = None"}, {"name": "do_scaling", "val": ": bool = True"}, {"name": "scaling_factor", "val": ": typing.Optional[float] = None"}, {"name": "shift_factor", "val": ": typing.Optional[float] = None"}, {"name": "output_type", "val": ": typing.Literal['mp4', 'pil', 'pt'] = 'pil'"}, {"name": "return_type", "val": ": typing.Literal['mp4', 'pil', 'pt'] = 'pil'"}, {"name": "image_format", "val": ": typing.Literal['png', 'jpg'] = 'jpg'"}, {"name": "partial_postprocess", "val": ": bool = False"}, {"name": "input_tensor_type", "val": ": typing.Literal['binary'] = 'binary'"}, {"name": "output_tensor_type", "val": ": typing.Literal['binary'] = 'binary'"}, {"name": "height", "val": ": typing.Optional[int] = None"}, {"name": "width", "val": ": typing.Optional[int] = None"}]- endpoint (str) -- Endpoint for Remote Decode.

• tensor (torch.Tensor) -- Tensor to be decoded.

• processor (VaeImageProcessor or VideoProcessor, optional) -- Used with return_type="pt", and return_type="pil" for Video models.

• do_scaling (bool, default True, optional) -- DEPRECATED. pass scaling_factor/shift_factor instead. still set do_scaling=None/do_scaling=False for no scaling until option is removed When True scaling e.g. latents / self.vae.config.scaling_factor is applied remotely. If False, input must be passed with scaling applied.

• scaling_factor (float, optional) -- Scaling is applied when passed e.g. latents / self.vae.config.scaling_factor.

  • SD v1: 0.18215
  • SD XL: 0.13025
  • Flux: 0.3611 If None, input must be passed with scaling applied.

• shift_factor (float, optional) -- Shift is applied when passed e.g. latents + self.vae.config.shift_factor.

  • Flux: 0.1159 If None, input must be passed with scaling applied.

• output_type ("mp4" or "pil" or "pt", default "pil") -- Endpoint output type. Subject to change. Report feedback on preferred type.

  "mp4": Supported by video models. Endpoint returns bytesof video."pil": Supported by image and video models. Image models: Endpoint returns bytesof an image inimage_format. Video models: Endpoint returns torch.Tensorwith partialpostprocessingapplied. Requiresprocessoras a flag (anyNonevalue will work)."pt": Support by image and video models. Endpoint returns torch.Tensor. With partial_postprocess=Truethe tensor is postprocesseduint8` image tensor.

  Recommendations: "pt" with partial_postprocess=True is the smallest transfer for full quality. "pt" with partial_postprocess=False is the most compatible with third party code. "pil" with image_format="jpg" is the smallest transfer overall.

• return_type ("mp4" or "pil" or "pt", default "pil") -- Function return type.

  "mp4": Function returns bytesof video."pil": Function returns PIL.Image.Image. With output_type="pil" no further processing is applied. With output_type="pt" a PIL.Image.Imageis created.partial_postprocess=False processoris required.partial_postprocess=True processoris **not** required."pt": Function returns torch.Tensor. processoris **not** required.partial_postprocess=Falsetensor isfloat16orbfloat16, without denormalization. partial_postprocess=Truetensor isuint8`, denormalized.

• image_format ("png" or "jpg", default jpg) -- Used with output_type="pil". Endpoint returns jpg or png.

• partial_postprocess (bool, default False) -- Used with output_type="pt". partial_postprocess=False tensor is float16 or bfloat16, without denormalization. partial_postprocess=True tensor is uint8, denormalized.

• input_tensor_type ("binary", default "binary") -- Tensor transfer type.

• output_tensor_type ("binary", default "binary") -- Tensor transfer type.

• height (int, optional) -- Required for "packed" latents.

• width (int, optional) -- Required for "packed" latents.0output (Image.Image or List[Image.Image] or bytes or torch.Tensor).

Hugging Face Hybrid Inference that allow running VAE decode remotely.

远程编码[[diffusers.utils.remote_utils.remote_encode]]

diffusers.utils.remote_utils.remote_encodediffusers.utils.remote_utils.remote_encodehttps://github.com/huggingface/diffusers/blob/vr_12595/src/diffusers/utils/remote_utils.py#L380[{"name": "endpoint", "val": ": str"}, {"name": "image", "val": ": typing.Union[ForwardRef('torch.Tensor'), PIL.Image.Image]"}, {"name": "scaling_factor", "val": ": typing.Optional[float] = None"}, {"name": "shift_factor", "val": ": typing.Optional[float] = None"}]- endpoint (str) -- Endpoint for Remote Decode.

• image (torch.Tensor or PIL.Image.Image) -- Image to be encoded.
• scaling_factor (float, optional) -- Scaling is applied when passed e.g. latents * self.vae.config.scaling_factor.
  • SD v1: 0.18215
  • SD XL: 0.13025
  • Flux: 0.3611 If None, input must be passed with scaling applied.
• shift_factor (float, optional) -- Shift is applied when passed e.g. latents - self.vae.config.shift_factor.
  • Flux: 0.1159 If None, input must be passed with scaling applied.0output (torch.Tensor).

Hugging Face Hybrid Inference that allow running VAE encode remotely.