Don't assume 512x512 in k-diffusion pipeline (huggingface#1625)

Don't assume 512x512 in k-diffusion pipeline.

Author: pcuenca

src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_k_diffusion.py

@@ -325,8 +325,8 @@ def prepare_latents(self, batch_size, num_channels_latents, height, width, dtype
     def __call__(
         self,
         prompt: Union[str, List[str]],
-        height: int = 512,
-        width: int = 512,
+        height: Optional[int] = None,
+        width: Optional[int] = None,
         num_inference_steps: int = 50,
         guidance_scale: float = 7.5,
         negative_prompt: Optional[Union[str, List[str]]] = None,
@@ -345,9 +345,9 @@ def __call__(
         Args:
             prompt (`str` or `List[str]`):
                 The prompt or prompts to guide the image generation.
-            height (`int`, *optional*, defaults to 512):
+            height (`int`, *optional*, defaults to self.unet.config.sample_size * self.vae_scale_factor):
                 The height in pixels of the generated image.
-            width (`int`, *optional*, defaults to 512):
+            width (`int`, *optional*, defaults to self.unet.config.sample_size * self.vae_scale_factor):
                 The width in pixels of the generated image.
             num_inference_steps (`int`, *optional*, defaults to 50):
                 The number of denoising steps. More denoising steps usually lead to a higher quality image at the
@@ -393,6 +393,9 @@ def __call__(
             list of `bool`s denoting whether the corresponding generated image likely represents "not-safe-for-work"
             (nsfw) content, according to the `safety_checker`.
         """
+        # 0. Default height and width to unet
+        height = height or self.unet.config.sample_size * self.vae_scale_factor
+        width = width or self.unet.config.sample_size * self.vae_scale_factor
 
         # 1. Check inputs. Raise error if not correct
         self.check_inputs(prompt, height, width, callback_steps)