[diffusion] model: support FireRed-Image-Edit (#20862)

Co-authored-by: yuumn <1010797597@qqã.com>

python/sglang/multimodal_gen/configs/models/encoders/qwen_image.py

@@ -46,6 +46,11 @@ class QwenImageArchConfig(TextEncoderArchConfig):
     head_dim: int | None = None
     hidden_state_skip_layer: int = 2
     text_len: int = 512
+    vision_start_token_id: int = 151652
+    vision_end_token_id: int = 151653
+    vision_token_id: int = 151654
+    image_token_id: int = 151655
+    video_token_id: int = 151656
 
     stacked_params_mapping: list[tuple[str, str, str]] = field(
         default_factory=lambda: [

python/sglang/multimodal_gen/registry.py

@@ -829,6 +829,16 @@ def _register_configs():
         model_detectors=[lambda hf_id: "sana" in hf_id.lower()],
     )
 
+    # FireRed-Image-Edit
+    register_configs(
+        sampling_param_cls=QwenImageEditPlusSamplingParams,
+        pipeline_config_cls=QwenImageEditPlusPipelineConfig,
+        hf_model_paths=[
+            "FireRedTeam/FireRed-Image-Edit-1.0",
+            "FireRedTeam/FireRed-Image-Edit-1.1",
+        ],
+    )
+
 
 _register_configs()