Add fast image processor Janus, Deepseek VL, Deepseek VL hybrid (#39739)

* add fast image processor Janus, deepseek_vl, deepseek_vl_hybrid

* fix after review

docs/source/en/model_doc/deepseek_vl.md

@@ -209,6 +209,10 @@ model = DeepseekVLForConditionalGeneration.from_pretrained(
 
 [[autodoc]] DeepseekVLImageProcessor
 
+## DeepseekVLImageProcessorFast
+
+[[autodoc]] DeepseekVLImageProcessorFast
+
 ## DeepseekVLModel
 
 [[autodoc]] DeepseekVLModel

docs/source/en/model_doc/deepseek_vl_hybrid.md

@@ -208,6 +208,10 @@ model = DeepseekVLHybridForConditionalGeneration.from_pretrained(
 
 [[autodoc]] DeepseekVLHybridImageProcessor
 
+## DeepseekVLHybridImageProcessorFast
+
+[[autodoc]] DeepseekVLHybridImageProcessorFast
+
 ## DeepseekVLHybridModel
 
 [[autodoc]] DeepseekVLHybridModel

docs/source/en/model_doc/janus.md

@@ -44,11 +44,11 @@ Here is the example of visual understanding with a single image.
 > Note that the model has been trained with a specific prompt format for chatting. Use `processor.apply_chat_template(my_conversation_dict)` to correctly format your prompts.
 
 ```python
-import torch  
-from PIL import Image  
-import requests  
+import torch
+from PIL import Image
+import requests
 
-from transformers import JanusForConditionalGeneration, JanusProcessor  
+from transformers import JanusForConditionalGeneration, JanusProcessor
 
 model_id = "deepseek-community/Janus-Pro-1B"
 # Prepare Input for generation.
@@ -64,7 +64,7 @@ messages = [
 
 # Set generation mode to `text` to perform text generation.
 processor = JanusProcessor.from_pretrained(model_id)
-model = JanusForConditionalGeneration.from_pretrained(model_id,     
+model = JanusForConditionalGeneration.from_pretrained(model_id,
         torch_dtype=torch.bfloat16,
         device_map="auto")
 
@@ -209,6 +209,10 @@ for i, image in enumerate(images['pixel_values']):
 
 [[autodoc]] JanusImageProcessor
 
+## JanusImageProcessorFast
+
+[[autodoc]] JanusImageProcessorFast
+
 ## JanusVisionModel
 
 [[autodoc]] JanusVisionModel