fix generations reponse body (#3094)

Signed-off-by: hx02481871@antgroup.com <hx02481871@antgroup.com>
Co-authored-by: hx02481871@antgroup.com <hx02481871@antgroup.com>

vllm_omni/entrypoints/openai/api_server.py

@@ -1572,13 +1572,23 @@ async def generate_images(request: ImageGenerationRequest, raw_request: Request)
 
         logger.info(f"Successfully generated {len(images)} image(s)")
 
-        # Encode images to base64
-        image_data = [ImageData(b64_json=encode_image_base64(img), revised_prompt=None) for img in images]
+        # Determine output format (default to png)
+        output_format = _choose_output_format(request.output_format or "png", None)
 
-        return ImageGenerationResponse(
-            created=int(time.time()),
-            data=image_data,
-        )
+        # Encode images to base64 with the specified format
+        image_data = [
+            ImageData(b64_json=_encode_image_base64_with_compression(img, format=output_format), revised_prompt=None)
+            for img in images
+        ]
+
+        response_kwargs = {
+            "created": int(time.time()),
+            "data": image_data,
+            "output_format": output_format,
+        }
+        if request.size:
+            response_kwargs["size"] = size_str
+        return ImageGenerationResponse(**response_kwargs)
 
     except (EngineGenerateError, EngineDeadError) as exc:
         return _create_engine_error_json_response(raw_request, exc)

vllm_omni/entrypoints/openai/protocol/images.py

@@ -139,6 +139,12 @@ class ImageGenerationRequest(BaseModel):
     vae_use_slicing: bool | None = Field(default=False, description="Enable VAE slicing")
     vae_use_tiling: bool | None = Field(default=False, description="Enable VAE tiling")
 
+    # Output format for generated images
+    output_format: str | None = Field(
+        default=None,
+        description="Output image format: 'png', 'jpeg', or 'webp'. Defaults to 'png'.",
+    )
+
 
 class ImageData(BaseModel):
     """Single generated image data"""