diff --git a/docs/my-website/docs/providers/stability.md b/docs/my-website/docs/providers/stability.md
index 62a8ab43cd8..c4bc5376d1f 100644
--- a/docs/my-website/docs/providers/stability.md
+++ b/docs/my-website/docs/providers/stability.md
@@ -173,6 +173,14 @@ Stability AI returns images in base64 format. The response is OpenAI-compatible:
 
 Stability AI supports various image editing operations including inpainting, upscaling, outpainting, background removal, and more.
 
+:::info Optional Parameters
+**Important:** Different Stability models have different parameter requirements:
+- Some models don't require a `prompt` (e.g., upscaling, background removal)
+- The `style-transfer` model uses `init_image` and `style_image` instead of `image`
+- The `outpaint` model requires numeric parameters (`left`, `right`, `up`, `down`)
+LiteLLM automatically handles these differences for you.
+:::
+
 ### Usage - LiteLLM Python SDK
 
 #### Inpainting (Edit with Mask)
@@ -217,11 +225,11 @@ response = image_edit(
     creativity=0.3,  # 0-0.35, higher = more creative
 )
 
-# Fast upscaling - quick upscaling
+# Fast upscaling - quick upscaling (no prompt needed)
 response = image_edit(
     model="stability/stable-fast-upscale-v1:0",
     image=open("low_res_image.png", "rb"),
-    prompt="Quickly upscale this image",
+    # No prompt required for fast upscale
 )
 print(response)
 ```
@@ -259,7 +267,7 @@ os.environ['STABILITY_API_KEY'] = "your-api-key"
 response = image_edit(
     model="stability/stable-image-remove-background-v1:0",
     image=open("portrait.png", "rb"),
-    prompt="Remove the background",
+    # No prompt required for fast upscale
 )
 print(response)
 ```
@@ -329,10 +337,29 @@ response = image_edit(
     model="stability/stable-image-erase-object-v1:0",
     image=open("scene.png", "rb"),
     mask=open("object_mask.png", "rb"),  # Mask the object to erase
-    prompt="Remove the object",
+    # No prompt needed
 )
 print(response)
 ```
+#### Style Transfer
+
+```python showLineNumbers
+from litellm import image_edit
+import os
+
+os.environ['STABILITY_API_KEY'] = "your-api-key"
+
+# Transfer style from one image to another
+# Note: Uses init_image (via image param) and style_image
+response = image_edit(
+    model="stability/stable-style-transfer-v1:0",
+    image=open("content_image.png", "rb"),  # Maps to init_image
+    style_image=open("style_reference.png", "rb"),  # Style to apply
+    fidelity=0.5,  # 0-1, balance between content and style
+    # No prompt needed
+)
+
+print(response)
 
 ### Supported Image Edit Models
 
@@ -419,6 +446,23 @@ response = image_edit(
 )
 print(response)
 ```
+# Fast upscale without prompt
+response = image_edit(
+    model="bedrock/stability.stable-fast-upscale-v1:0",
+    image=open("low_res_image.png", "rb"),
+)
+
+# Outpaint with numeric parameters
+response = image_edit(
+    model="bedrock/stability.stable-outpaint-v1:0",
+    image=open("original_image.png", "rb"),
+    left=100,   # Automatically converted to int
+    right=100,
+    up=50,
+    down=50,
+)
+
+print(response)
 
 ### Supported Bedrock Stability Models
 
diff --git a/litellm/images/main.py b/litellm/images/main.py
index 1b09c20d350..6c4c502a7b0 100644
--- a/litellm/images/main.py
+++ b/litellm/images/main.py
@@ -714,8 +714,8 @@ def image_variation(
 
 @client
 def image_edit(  # noqa: PLR0915
-    image: Union[FileTypes, List[FileTypes]],
-    prompt: str,
+    image: Optional[Union[FileTypes, List[FileTypes]]] = None,
+    prompt: Optional[str]= None,
     model: Optional[str] = None,
     mask: Optional[str] = None,
     n: Optional[int] = None,
@@ -766,7 +766,7 @@ def image_edit(  # noqa: PLR0915
         _is_async = kwargs.pop("async_call", False) is True
 
         # add images / or return a single image
-        images = image if isinstance(image, list) else [image]
+        images = image if isinstance(image, list) else ([image] if image is not None else [])
 
         headers_from_kwargs = kwargs.get("headers")
         merged_extra_headers: Dict[str, Any] = {}
diff --git a/litellm/llms/azure_ai/image_edit/flux2_transformation.py b/litellm/llms/azure_ai/image_edit/flux2_transformation.py
index 87bae59ba0f..77d46ff9179 100644
--- a/litellm/llms/azure_ai/image_edit/flux2_transformation.py
+++ b/litellm/llms/azure_ai/image_edit/flux2_transformation.py
@@ -88,7 +88,7 @@ class AzureFoundryFlux2ImageEditConfig(OpenAIImageEditConfig):
         self,
         model: str,
         prompt: Optional[str],
-        image: FileTypes,
+        image: Optional[FileTypes],
         image_edit_optional_request_params: Dict,
         litellm_params: GenericLiteLLMParams,
         headers: dict,
@@ -102,6 +102,9 @@ class AzureFoundryFlux2ImageEditConfig(OpenAIImageEditConfig):
         if prompt is None:
             raise ValueError("FLUX 2 image edit requires a prompt.")
         
+        if image is None:
+            raise ValueError("FLUX 2 image edit requires an image.")
+        
         image_b64 = self._convert_image_to_base64(image)
 
         # Build request body with required params
diff --git a/litellm/llms/base_llm/image_edit/transformation.py b/litellm/llms/base_llm/image_edit/transformation.py
index cc723480371..b088cdf37f6 100644
--- a/litellm/llms/base_llm/image_edit/transformation.py
+++ b/litellm/llms/base_llm/image_edit/transformation.py
@@ -93,7 +93,7 @@ class BaseImageEditConfig(ABC):
         self,
         model: str,
         prompt: Optional[str],
-        image: FileTypes,
+        image: Optional[FileTypes],
         image_edit_optional_request_params: Dict,
         litellm_params: GenericLiteLLMParams,
         headers: dict,
diff --git a/litellm/llms/bedrock/image_edit/handler.py b/litellm/llms/bedrock/image_edit/handler.py
index 0f1dcff6294..ef441fa5039 100644
--- a/litellm/llms/bedrock/image_edit/handler.py
+++ b/litellm/llms/bedrock/image_edit/handler.py
@@ -62,7 +62,7 @@ class BedrockImageEdit(BaseAWSLLM):
         self,
         model: str,
         image: list,
-        prompt: str,
+        prompt: Optional[str],
         model_response: ImageResponse,
         optional_params: dict,
         logging_obj: LitellmLogging,
@@ -127,7 +127,7 @@ class BedrockImageEdit(BaseAWSLLM):
         timeout: Optional[Union[float, httpx.Timeout]],
         model: str,
         logging_obj: LitellmLogging,
-        prompt: str,
+        prompt: Optional[str],
         model_response: ImageResponse,
         client: Optional[AsyncHTTPHandler] = None,
     ) -> ImageResponse:
@@ -163,7 +163,7 @@ class BedrockImageEdit(BaseAWSLLM):
         self,
         model: str,
         image: list,
-        prompt: str,
+        prompt: Optional[str],
         optional_params: dict,
         api_base: Optional[str],
         extra_headers: Optional[dict],
@@ -176,7 +176,7 @@ class BedrockImageEdit(BaseAWSLLM):
         Args:
             model (str): The model to use for the image edit
             image (list): The images to edit
-            prompt (str): The prompt for the edit
+            prompt (Optional[str]): The prompt for the edit
             optional_params (dict): The optional parameters for the image edit
             api_base (Optional[str]): The base URL for the Bedrock API
             extra_headers (Optional[dict]): The extra headers to include in the request
@@ -248,7 +248,7 @@ class BedrockImageEdit(BaseAWSLLM):
         self,
         model: str,
         image: list,
-        prompt: str,
+        prompt: Optional[str],
         optional_params: dict,
     ) -> dict:
         """
@@ -276,7 +276,7 @@ class BedrockImageEdit(BaseAWSLLM):
         model_response: ImageResponse,
         model: str,
         logging_obj: LitellmLogging,
-        prompt: str,
+        prompt: Optional[str],
         response: httpx.Response,
         data: dict,
     ) -> ImageResponse:
diff --git a/litellm/llms/bedrock/image_edit/stability_transformation.py b/litellm/llms/bedrock/image_edit/stability_transformation.py
index e8b77812988..fc14b571a8c 100644
--- a/litellm/llms/bedrock/image_edit/stability_transformation.py
+++ b/litellm/llms/bedrock/image_edit/stability_transformation.py
@@ -150,11 +150,11 @@ class BedrockStabilityImageEditConfig(BaseImageEditConfig):
 
         return mapped_params
 
-    def transform_image_edit_request(
+    def transform_image_edit_request(  #noqa: PLR0915
         self,
         model: str,
         prompt: Optional[str],
-        image: FileTypes,
+        image: Optional[FileTypes],
         image_edit_optional_request_params: Dict,
         litellm_params: GenericLiteLLMParams,
         headers: dict,
@@ -164,32 +164,38 @@ class BedrockStabilityImageEditConfig(BaseImageEditConfig):
 
         Returns the request body dict that will be JSON-encoded by the handler.
         """
-        if prompt is None:
-            raise ValueError("Bedrock Stability image edit requires a prompt.")
-        
         # Build Bedrock Stability request
         data: Dict[str, Any] = {
-            "prompt": prompt,
             "output_format": "png",  # Default to PNG
         }
         
-        # Convert image to base64
-        image_b64: str
-        if hasattr(image, 'read') and callable(getattr(image, 'read', None)):
-            # File-like object (e.g., BufferedReader from open())
-            image_bytes = image.read()  # type: ignore
-            image_b64 = base64.b64encode(image_bytes).decode('utf-8')  # type: ignore
-        elif isinstance(image, bytes):
-            # Raw bytes
-            image_b64 = base64.b64encode(image).decode('utf-8')
-        elif isinstance(image, str):
-            # Already a base64 string
-            image_b64 = image
-        else:
-            # Try to handle as bytes
-            image_b64 = base64.b64encode(bytes(image)).decode('utf-8')  # type: ignore
+        # Add prompt only if provided (some models don't require it)
+        if prompt is not None and prompt != "":
+            data["prompt"] = prompt
+        
+        # Convert image to base64 if provided
+        if image is not None:
+            image_b64: str
+            if hasattr(image, 'read') and callable(getattr(image, 'read', None)):
+                # File-like object (e.g., BufferedReader from open())
+                image_bytes = image.read()  # type: ignore
+                image_b64 = base64.b64encode(image_bytes).decode('utf-8')  # type: ignore
+            elif isinstance(image, bytes):
+                # Raw bytes
+                image_b64 = base64.b64encode(image).decode('utf-8')
+            elif isinstance(image, str):
+                # Already a base64 string
+                image_b64 = image
+            else:
+                # Try to handle as bytes
+                image_b64 = base64.b64encode(bytes(image)).decode('utf-8')  # type: ignore
 
-        data["image"] = image_b64
+            # For style-transfer models, map image to init_image
+            model_lower = model.lower()
+            if "style-transfer" in model_lower:
+                data["init_image"] = image_b64
+            else:
+                data["image"] = image_b64
 
         # Add optional params (already mapped in map_openai_params)
         for key, value in image_edit_optional_request_params.items():  # type: ignore
@@ -221,30 +227,43 @@ class BedrockStabilityImageEditConfig(BaseImageEditConfig):
                     file_b64 = str(file_bytes)
                 data[key] = file_b64
                 continue
-
-            # Supported text fields
-            if key in [
-                "negative_prompt",
-                "aspect_ratio",
-                "seed",
-                "output_format",
-                "model",
-                "mode",
+            
+            # Numeric fields that need to be converted to int/float
+            numeric_int_fields = ["left", "right", "up", "down", "seed"]
+            numeric_float_fields = [
                 "strength",
-                "style_preset",
                 "creativity",
                 "control_strength",
                 "grow_mask",
-                "left",
-                "right",
-                "up",
-                "down",
-                "select_prompt",
-                "search_prompt",
                 "fidelity",
                 "composition_fidelity",
                 "style_strength",
                 "change_strength",
+            ]
+            
+            if key in numeric_int_fields:
+                # Convert to int (these are pixel values for outpaint)
+                try:
+                    data[key] = int(value)  # type: ignore
+                except (ValueError, TypeError):
+                    data[key] = value  # type: ignore
+            elif key in numeric_float_fields:
+                # Convert to float
+                try:
+                    data[key] = float(value)  # type: ignore
+                except (ValueError, TypeError):
+                    data[key] = value  # type: ignore
+
+            # Supported text fields
+            elif key in [
+                "negative_prompt",
+                "aspect_ratio",
+                "output_format",
+                "model",
+                "mode",
+                "style_preset",
+                "select_prompt",
+                "search_prompt",
             ]:
                 data[key] = value  # type: ignore
 
diff --git a/litellm/llms/gemini/image_edit/transformation.py b/litellm/llms/gemini/image_edit/transformation.py
index 0015155b47f..16541138217 100644
--- a/litellm/llms/gemini/image_edit/transformation.py
+++ b/litellm/llms/gemini/image_edit/transformation.py
@@ -81,21 +81,23 @@ class GeminiImageEditConfig(BaseImageEditConfig):
         self,
         model: str,
         prompt: Optional[str],
-        image: FileTypes,
+        image: Optional[FileTypes],
         image_edit_optional_request_params: Dict[str, Any],
         litellm_params: GenericLiteLLMParams,
         headers: dict,
     ) -> Tuple[Dict[str, Any], Optional[RequestFiles]]:
-        inline_parts = self._prepare_inline_image_parts(image)
+        inline_parts = self._prepare_inline_image_parts(image) if image else []
         if not inline_parts:
             raise ValueError("Gemini image edit requires at least one image.")
 
-        if prompt is None:
-            raise ValueError("Gemini image edit requires a prompt.")
+        # Build parts list with image and prompt (if provided)
+        parts = inline_parts.copy()
+        if prompt is not None and prompt != "":
+            parts.append({"text": prompt})
 
         contents = [
             {
-                "parts": inline_parts + [{"text": prompt}],
+                "parts": parts,
             }
         ]
 
diff --git a/litellm/llms/openai/image_edit/dalle2_transformation.py b/litellm/llms/openai/image_edit/dalle2_transformation.py
index 13531546d2e..fd697b210ee 100644
--- a/litellm/llms/openai/image_edit/dalle2_transformation.py
+++ b/litellm/llms/openai/image_edit/dalle2_transformation.py
@@ -31,7 +31,7 @@ class DallE2ImageEditConfig(OpenAIImageEditConfig):
         self,
         model: str,
         prompt: Optional[str],
-        image: FileTypes,
+        image: Optional[FileTypes],
         image_edit_optional_request_params: Dict,
         litellm_params: GenericLiteLLMParams,
         headers: dict,
@@ -40,18 +40,20 @@ class DallE2ImageEditConfig(OpenAIImageEditConfig):
         Transform image edit request for DALL-E-2.
 
         DALL-E-2 only accepts a single image with field name "image" (not "image[]").
-        """
-        if prompt is None:
-            raise ValueError("DALL-E-2 image edit requires a prompt.")
-        
-        request = ImageEditRequestParams(
-            model=model,
-            image=image,
-            prompt=prompt,
+        """        
+        request_params = {
+            "model": model,
             **image_edit_optional_request_params,
-        )
+        }
+        if image is not None:
+            request_params["image"] = image
+        if prompt is not None:
+            request_params["prompt"] = prompt
+            
+        request = ImageEditRequestParams(**request_params)
         request_dict = cast(Dict, request)
 
+
         #########################################################
         # Separate images and masks as `files` and send other parameters as `data`
         #########################################################
diff --git a/litellm/llms/openai/image_edit/transformation.py b/litellm/llms/openai/image_edit/transformation.py
index 9edad9ee2c9..a1e5375d098 100644
--- a/litellm/llms/openai/image_edit/transformation.py
+++ b/litellm/llms/openai/image_edit/transformation.py
@@ -80,7 +80,7 @@ class OpenAIImageEditConfig(BaseImageEditConfig):
         self,
         model: str,
         prompt: Optional[str],
-        image: FileTypes,
+        image: Optional[FileTypes],
         image_edit_optional_request_params: Dict,
         litellm_params: GenericLiteLLMParams,
         headers: dict,
@@ -91,15 +91,17 @@ class OpenAIImageEditConfig(BaseImageEditConfig):
         Handles multipart/form-data for images. Uses "image[]" field name
         to support multiple images (e.g., for gpt-image-1).
         """
-        if prompt is None:
-            raise ValueError("OpenAI image edit requires a prompt.")
-        
-        request = ImageEditRequestParams(
-            model=model,
-            image=image,
-            prompt=prompt,
+        # Build request params, only including non-None values
+        request_params = {
+            "model": model,
             **image_edit_optional_request_params,
-        )
+        }
+        if image is not None:
+            request_params["image"] = image
+        if prompt is not None:
+            request_params["prompt"] = prompt
+            
+        request = ImageEditRequestParams(**request_params)
         request_dict = cast(Dict, request)
 
         #########################################################
diff --git a/litellm/llms/recraft/image_edit/transformation.py b/litellm/llms/recraft/image_edit/transformation.py
index 9bf46704ed1..d2a56236819 100644
--- a/litellm/llms/recraft/image_edit/transformation.py
+++ b/litellm/llms/recraft/image_edit/transformation.py
@@ -102,7 +102,7 @@ class RecraftImageEditConfig(BaseImageEditConfig):
         self,
         model: str,
         prompt: Optional[str],
-        image: FileTypes,
+        image: Optional[FileTypes],
         image_edit_optional_request_params: Dict,
         litellm_params: GenericLiteLLMParams,
         headers: dict,
@@ -114,15 +114,15 @@ class RecraftImageEditConfig(BaseImageEditConfig):
         https://www.recraft.ai/docs#image-to-image
         """
         
-        if prompt is None:
-            raise ValueError("Recraft image edit requires a prompt.")
-        
-        request_body: RecraftImageEditRequestParams = RecraftImageEditRequestParams(
-            model=model,
-            prompt=prompt,
-            strength=image_edit_optional_request_params.pop("strength", self.DEFAULT_STRENGTH),
+        request_params = {
+            "model": model,
+            "strength": image_edit_optional_request_params.pop("strength", self.DEFAULT_STRENGTH),
             **image_edit_optional_request_params,
-        )
+        }
+        if prompt is not None:
+            request_params["prompt"] = prompt
+            
+        request_body = RecraftImageEditRequestParams(**request_params)
         request_dict = cast(Dict, request_body)
         #########################################################
         # Reuse OpenAI logic: Separate images as `files` and send other parameters as `data`
diff --git a/litellm/llms/stability/image_edit/transformations.py b/litellm/llms/stability/image_edit/transformations.py
index 013e3f27a02..53bdc825dd4 100644
--- a/litellm/llms/stability/image_edit/transformations.py
+++ b/litellm/llms/stability/image_edit/transformations.py
@@ -171,7 +171,7 @@ class StabilityImageEditConfig(BaseImageEditConfig):
         self,
         model: str,
         prompt: Optional[str],
-        image: FileTypes,
+        image: Optional[FileTypes],
         image_edit_optional_request_params: Dict,
         litellm_params: GenericLiteLLMParams,
         headers: dict,
@@ -190,11 +190,14 @@ class StabilityImageEditConfig(BaseImageEditConfig):
         }
         
         # Add prompt only if provided (some Stability endpoints don't require it)
-        if prompt is not None:
+        if prompt is not None and prompt != "":
             data["prompt"] = prompt
         # Handle image parameter - could be a single file or list
         image_file = image[0] if isinstance(image, list) else image  # type: ignore
-        files: Dict[str, Any] = {"image": image_file}
+        files: Dict[str, Any] = {}
+        if image is not None:
+            image_file = image[0] if isinstance(image, list) else image  # type: ignore
+            files["image"] = image_file
 
         # Add optional params (already mapped in map_openai_params)
         for key, value in image_edit_optional_request_params.items():  # type: ignore
diff --git a/litellm/llms/vertex_ai/image_edit/vertex_gemini_transformation.py b/litellm/llms/vertex_ai/image_edit/vertex_gemini_transformation.py
index 154d5669eb8..8fcd285824d 100644
--- a/litellm/llms/vertex_ai/image_edit/vertex_gemini_transformation.py
+++ b/litellm/llms/vertex_ai/image_edit/vertex_gemini_transformation.py
@@ -152,22 +152,24 @@ class VertexAIGeminiImageEditConfig(BaseImageEditConfig, VertexLLM):
         self,
         model: str,
         prompt: Optional[str],
-        image: FileTypes,
+        image: Optional[FileTypes],
         image_edit_optional_request_params: Dict[str, Any],
         litellm_params: GenericLiteLLMParams,
         headers: dict,
     ) -> Tuple[Dict[str, Any], Optional[RequestFiles]]:
-        inline_parts = self._prepare_inline_image_parts(image)
+        inline_parts = self._prepare_inline_image_parts(image) if image else []
         if not inline_parts:
             raise ValueError("Vertex AI Gemini image edit requires at least one image.")
 
-        if prompt is None:
-            raise ValueError("Vertex AI Gemini image edit requires a prompt.")
+        # Build parts list with image and prompt (if provided)
+        parts = inline_parts.copy()
+        if prompt is not None and prompt != "":
+            parts.append({"text": prompt})
 
         # Correct format for Vertex AI Gemini image editing
         contents = {
             "role": "USER",
-            "parts": inline_parts + [{"text": prompt}]
+            "parts": parts
         }
 
         request_body: Dict[str, Any] = {"contents": contents}
diff --git a/litellm/llms/vertex_ai/image_edit/vertex_imagen_transformation.py b/litellm/llms/vertex_ai/image_edit/vertex_imagen_transformation.py
index 337a4bd4dd6..b58825e1faa 100644
--- a/litellm/llms/vertex_ai/image_edit/vertex_imagen_transformation.py
+++ b/litellm/llms/vertex_ai/image_edit/vertex_imagen_transformation.py
@@ -144,7 +144,7 @@ class VertexAIImagenImageEditConfig(BaseImageEditConfig, VertexLLM):
         self,
         model: str,
         prompt: Optional[str],
-        image: FileTypes,
+        image: Optional[FileTypes],
         image_edit_optional_request_params: Dict[str, Any],
         litellm_params: GenericLiteLLMParams,
         headers: dict,
diff --git a/litellm/proxy/image_endpoints/endpoints.py b/litellm/proxy/image_endpoints/endpoints.py
index a1453e10dbf..4a2c05f8590 100644
--- a/litellm/proxy/image_endpoints/endpoints.py
+++ b/litellm/proxy/image_endpoints/endpoints.py
@@ -244,8 +244,10 @@ async def image_edit_api(
     if mask is None and mask_array is not None:
         mask = mask_array
 
-    if image is None:
-        raise HTTPException(status_code=422, detail="Field required: image")
+    # if image is None:
+    #     raise HTTPException(status_code=422, detail="Field required: image")
+    # Note: Image is optional for some models (e.g., Bedrock Stability style-transfer)
+    # The validation will be done at the model level if image is truly required
 
     from litellm.proxy.proxy_server import (
         _read_request_body,
@@ -272,6 +274,10 @@ async def image_edit_api(
         data["image"] = image_files
     if mask_files:
         data["mask"] = mask_files
+    
+    # Ensure prompt exists in data (default to None for models that don't require it)
+    if "prompt" not in data:
+        data["prompt"] = None
 
     data["model"] = (
         model