Author: hlky

src/diffusers/models/controlnets/__init__.py

@@ -15,7 +15,7 @@
         SparseControlNetModel,
         SparseControlNetOutput,
     )
-    from .controlnet_union import ControlNetUnionInput, ControlNetUnionInputProMax, ControlNetUnionModel
+    from .controlnet_union import ControlNetUnionModel
     from .controlnet_xs import ControlNetXSAdapter, ControlNetXSOutput, UNetControlNetXSModel
     from .multicontrolnet import MultiControlNetModel
 

src/diffusers/pipelines/controlnet/pipeline_controlnet_union_sd_xl.py

@@ -43,7 +43,6 @@
     AttnProcessor2_0,
     XFormersAttnProcessor,
 )
-from ...models.controlnets import ControlNetUnionInput, ControlNetUnionInputProMax
 from ...models.lora import adjust_lora_scale_text_encoder
 from ...schedulers import KarrasDiffusionSchedulers
 from ...utils import (
@@ -786,26 +785,6 @@ def check_inputs(
                     f"`ip_adapter_image_embeds` has to be a list of 3D or 4D tensors but is {ip_adapter_image_embeds[0].ndim}D"
                 )
 
-    def check_input(
-        self,
-        image: Union[ControlNetUnionInput, ControlNetUnionInputProMax],
-    ):
-        controlnet = self.controlnet._orig_mod if is_compiled_module(self.controlnet) else self.controlnet
-
-        if not isinstance(image, (ControlNetUnionInput, ControlNetUnionInputProMax)):
-            raise ValueError(
-                "Expected type of `image` to be one of `ControlNetUnionInput` or `ControlNetUnionInputProMax`"
-            )
-        if len(image) != controlnet.config.num_control_type:
-            if isinstance(image, ControlNetUnionInput):
-                raise ValueError(
-                    f"Expected num_control_type {controlnet.config.num_control_type}, got {len(image)}. Try `ControlNetUnionInputProMax`."
-                )
-            elif isinstance(image, ControlNetUnionInputProMax):
-                raise ValueError(
-                    f"Expected num_control_type {controlnet.config.num_control_type}, got {len(image)}. Try `ControlNetUnionInput`."
-                )
-
     # Copied from diffusers.pipelines.controlnet.pipeline_controlnet.StableDiffusionControlNetPipeline.prepare_image
     def prepare_image(
         self,
@@ -1014,10 +993,7 @@ def __call__(
             prompt_2 (`str` or `List[str]`, *optional*):
                 The prompt or prompts to be sent to `tokenizer_2` and `text_encoder_2`. If not defined, `prompt` is
                 used in both text-encoders.
-            image (`Union[ControlNetUnionInput, ControlNetUnionInputProMax]`):
-                In turn this supports (`torch.FloatTensor`, `PIL.Image.Image`, `np.ndarray`, `List[torch.FloatTensor]`,
-                    `List[PIL.Image.Image]`, `List[np.ndarray]`, `List[List[torch.FloatTensor]]`,
-                    `List[List[np.ndarray]]` or `List[List[PIL.Image.Image]]`):
+            control_image (`PipelineImageInput`):
                 The ControlNet input condition to provide guidance to the `unet` for generation. If the type is
                 specified as `torch.Tensor`, it is passed to ControlNet as is. `PIL.Image.Image` can also be accepted
                 as an image. The dimensions of the output image defaults to `image`'s dimensions. If height and/or
@@ -1164,8 +1140,6 @@ def __call__(
 
         controlnet = self.controlnet._orig_mod if is_compiled_module(self.controlnet) else self.controlnet
 
-        self.check_input(control_image)
-
         # align format for control guidance
         if not isinstance(control_guidance_start, list) and isinstance(control_guidance_end, list):
             control_guidance_start = len(control_guidance_end) * [control_guidance_start]

src/diffusers/pipelines/controlnet/pipeline_controlnet_union_sd_xl_img2img.py

@@ -1116,10 +1116,7 @@ def __call__(
                     `List[List[torch.Tensor]]`, `List[List[np.ndarray]]` or `List[List[PIL.Image.Image]]`):
                 The initial image will be used as the starting point for the image generation process. Can also accept
                 image latents as `image`, if passing latents directly, it will not be encoded again.
-            control_image_list (`Union[ControlNetUnionInput, ControlNetUnionInputProMax]`):
-                In turn this supports (`torch.FloatTensor`, `PIL.Image.Image`, `np.ndarray`, `List[torch.FloatTensor]`,
-                    `List[PIL.Image.Image]`, `List[np.ndarray]`, `List[List[torch.FloatTensor]]`,
-                    `List[List[np.ndarray]]` or `List[List[PIL.Image.Image]]`)::
+            control_image (`PipelineImageInput`):
                 The ControlNet input condition. ControlNet uses this input condition to generate guidance to Unet. If
                 the type is specified as `torch.Tensor`, it is passed to ControlNet as is. `PIL.Image.Image` can also
                 be accepted as an image. The dimensions of the output image defaults to `image`'s dimensions. If height