Fix the Kandinsky docstring examples (#3695)

- use the correct Prior hub model id
 - use the new names in KandinskyPriorPipelineOutput

Author: freespirit

src/diffusers/pipelines/kandinsky/pipeline_kandinsky.py

@@ -41,21 +41,21 @@
         >>> from diffusers import KandinskyPipeline, KandinskyPriorPipeline
         >>> import torch
 
-        >>> pipe_prior = KandinskyPriorPipeline.from_pretrained("kandinsky-community/Kandinsky-prior")
+        >>> pipe_prior = KandinskyPriorPipeline.from_pretrained("kandinsky-community/Kandinsky-2-1-prior")
         >>> pipe_prior.to("cuda")
 
         >>> prompt = "red cat, 4k photo"
         >>> out = pipe_prior(prompt)
-        >>> image_emb = out.images
-        >>> zero_image_emb = out.zero_embeds
+        >>> image_emb = out.image_embeds
+        >>> negative_image_emb = out.negative_image_embeds
 
         >>> pipe = KandinskyPipeline.from_pretrained("kandinsky-community/kandinsky-2-1")
         >>> pipe.to("cuda")
 
         >>> image = pipe(
         ...     prompt,
         ...     image_embeds=image_emb,
-        ...     negative_image_embeds=zero_image_emb,
+        ...     negative_image_embeds=negative_image_emb,
         ...     height=768,
         ...     width=768,
         ...     num_inference_steps=100,

src/diffusers/pipelines/kandinsky/pipeline_kandinsky_prior.py

@@ -45,16 +45,16 @@
 
         >>> prompt = "red cat, 4k photo"
         >>> out = pipe_prior(prompt)
-        >>> image_emb = out.images
-        >>> zero_image_emb = out.zero_embeds
+        >>> image_emb = out.image_embeds
+        >>> negative_image_emb = out.negative_image_embeds
 
         >>> pipe = KandinskyPipeline.from_pretrained("kandinsky-community/kandinsky-2-1")
         >>> pipe.to("cuda")
 
         >>> image = pipe(
         ...     prompt,
         ...     image_embeds=image_emb,
-        ...     negative_image_embeds=zero_image_emb,
+        ...     negative_image_embeds=negative_image_emb,
         ...     height=768,
         ...     width=768,
         ...     num_inference_steps=100,