[diffusion] model: LTX-2 Support (2/2) (#17496)

Co-authored-by: Fan Yin <1106310035@qq.com>
Co-authored-by: Yuhao Yang <47235274+yhyang201@users.noreply.github.com>

python/sglang/multimodal_gen/registry.py

@@ -45,6 +45,7 @@ from sglang.multimodal_gen.configs.pipeline_configs.flux import (
 from sglang.multimodal_gen.configs.pipeline_configs.glm_image import (
     GlmImagePipelineConfig,
 )
+from sglang.multimodal_gen.configs.pipeline_configs.ltx_2 import LTX2PipelineConfig
 from sglang.multimodal_gen.configs.pipeline_configs.qwen_image import (
     QwenImageEditPipelineConfig,
     QwenImageEditPlus_2511_PipelineConfig,
@@ -70,6 +71,7 @@ from sglang.multimodal_gen.configs.sample.hunyuan import (
     FastHunyuanSamplingParam,
     HunyuanSamplingParams,
 )
+from sglang.multimodal_gen.configs.sample.ltx_2 import LTX2SamplingParams
 from sglang.multimodal_gen.configs.sample.qwenimage import (
     QwenImage2512SamplingParams,
     QwenImageEditPlusSamplingParams,
@@ -423,6 +425,16 @@ def get_model_info(
 
 # Registration of model configs
 def _register_configs():
+    # LTX-2
+    register_configs(
+        sampling_param_cls=LTX2SamplingParams,
+        pipeline_config_cls=LTX2PipelineConfig,
+        model_detectors=[
+            lambda path: "ltx" in path.lower() and "video" in path.lower(),
+            lambda path: "ltx-2" in path.lower(),
+        ],
+    )
+
     # Hunyuan
     register_configs(
         sampling_param_cls=HunyuanSamplingParams,