diff --git a/lightllm/server/api_models.py b/lightllm/server/api_models.py
index eb10c5b384..b2cd53a4c1 100644
--- a/lightllm/server/api_models.py
+++ b/lightllm/server/api_models.py
@@ -447,19 +447,19 @@ class ImageConfig(BaseModel):
     cfg_norm: Optional[Literal["none", "cfg_zero_star", "global", "text_channel", "channel"]] = None
     dynamic_resolution: Optional[bool] = True
     _aspect_ratio_to_resolution: ClassVar[dict] = {
-        "1:1": {"1K": (1024, 1024), "1.5K": (1536, 1536), "2K": (2048, 2048)},
-        "16:9": {"1.5K": (2048, 1152), "2K": (2720, 1536)},
-        "9:16": {"1.5K": (1152, 2048), "2K": (1536, 2720)},
-        "3:2": {"1.5K": (1888, 1248), "2K": (2496, 1664)},
-        "2:3": {"1.5K": (1248, 1888), "2K": (1664, 2496)},
-        "4:3": {"1.5K": (1760, 1312), "2K": (2368, 1760)},
-        "3:4": {"1.5K": (1312, 1760), "2K": (1760, 2368)},
-        "1:2": {"1.5K": (1088, 2144), "2K": (1440, 2880)},
-        "2:1": {"1.5K": (2144, 1088), "2K": (2880, 1440)},
-        "1:3": {"1.5K": (864, 2592), "2K": (1152, 3456)},
-        "3:1": {"1.5K": (2592, 864), "2K": (3456, 1152)},
+        "1:1": {"1K": (1024, 1024), "1.5K": (1536, 1536), "2K": (2048, 2048), "4K": (4096, 4096)},
+        "16:9": {"1.5K": (2048, 1152), "2K": (2720, 1536), "4K": (4096, 2304)},
+        "9:16": {"1.5K": (1152, 2048), "2K": (1536, 2720), "4K": (2304, 4096)},
+        "3:2": {"1.5K": (1888, 1248), "2K": (2496, 1664), "4K": (4096, 2720)},
+        "2:3": {"1.5K": (1248, 1888), "2K": (1664, 2496), "4K": (2720, 4096)},
+        "4:3": {"1.5K": (1760, 1312), "2K": (2368, 1760), "4K": (4096, 3072)},
+        "3:4": {"1.5K": (1312, 1760), "2K": (1760, 2368), "4K": (3072, 4096)},
+        "1:2": {"1.5K": (1088, 2144), "2K": (1440, 2880), "4K": (2048, 4096)},
+        "2:1": {"1.5K": (2144, 1088), "2K": (2880, 1440), "4K": (4096, 2048)},
+        "1:3": {"1.5K": (864, 2592), "2K": (1152, 3456), "4K": (1376, 4096)},
+        "3:1": {"1.5K": (2592, 864), "2K": (3456, 1152), "4K": (4096, 1376)},
     }
-    _size_set: ClassVar[set[str]] = {"1.5K", "2K"}
+    _size_set: ClassVar[set[str]] = {"1.5K", "2K", "4K"}
 
     @field_validator("image_size", mode="before")
     @classmethod
@@ -508,7 +508,7 @@ def get_resolution(self):
             base = self._aspect_ratio_to_resolution[self.aspect_ratio][self.image_size]
             w, h = base
 
-        h, w = smart_resize(h, w, factor=32, min_pixels=1024 * 1024, max_pixels=2048 * 2048)
+        h, w = smart_resize(h, w, factor=32, min_pixels=1024 * 1024, max_pixels=4096 * 4096)
         return w, h
 
 
diff --git a/lightllm/server/build_prompt.py b/lightllm/server/build_prompt.py
index 84044fccce..827c172fe6 100644
--- a/lightllm/server/build_prompt.py
+++ b/lightllm/server/build_prompt.py
@@ -79,11 +79,37 @@ def _alias_reasoning_to_reasoning_content(messages: list) -> None:
             msg["reasoning_content"] = reasoning
 
 
+def _flatten_multimodal_content(messages: list) -> None:
+    # OpenAI-style chat requests may send content as a list of parts
+    # ({"type": "text", ...}, {"type": "image_url", ...}). Most HF chat
+    # templates (Qwen, LLaMA, ...) call string methods on `content` directly
+    # and crash on lists. Flatten into a plain string with placeholder tokens
+    # so the template can render; the image data itself is already extracted
+    # upstream via `_get_images_and_audios` and fed through MultimodalParams.
+    for msg in messages:
+        content = msg.get("content")
+        if not isinstance(content, list):
+            continue
+        parts: list = []
+        for item in content:
+            if not isinstance(item, dict):
+                continue
+            t = item.get("type")
+            if t == "text":
+                parts.append(item.get("text", "") or "")
+            elif t == "image_url":
+                parts.append("<image>")
+            elif t == "audio_url":
+                parts.append("<audio>")
+        msg["content"] = "\n".join(p for p in parts if p != "")
+
+
 async def build_prompt(request, tools) -> str:
     # pydantic格式转成dict， 否则，当根据tokenizer_config.json拼template时，Jinja判断无法识别
     messages = [m.model_dump(by_alias=True, exclude_none=True) for m in request.messages]
     _normalize_tool_call_arguments(messages)
     _alias_reasoning_to_reasoning_content(messages)
+    _flatten_multimodal_content(messages)
 
     kwargs = {"conversation": messages}
     if request.character_settings:
diff --git a/lightllm/server/core/objs/x2i_params.py b/lightllm/server/core/objs/x2i_params.py
index d629f0a915..a91c48f44e 100644
--- a/lightllm/server/core/objs/x2i_params.py
+++ b/lightllm/server/core/objs/x2i_params.py
@@ -123,7 +123,7 @@ def update_hw(self, width: int, height: int):
             return
         from lightllm.models.neo_chat_moe.vision_process import smart_resize
 
-        h, w = smart_resize(height, width, factor=32, min_pixels=512 * 512, max_pixels=2048 * 2048)
+        h, w = smart_resize(height, width, factor=32, min_pixels=512 * 512, max_pixels=4096 * 4096)
         self.width = w
         self.height = h
         self.has_updated_hw = True