Fix missing LTX2 exports and add layerwise offload compatibility

- Restore LTX2VideoConfig and add to dits __init__
- Add LTX2VAEConfig export to vaes __init__
- Add LTX2Transformer3DModel and CausalVideoAutoencoder to model registry
- Add compatibility check for layerwise offload (skip for models without nn.ModuleList)

fastvideo/configs/models/dits/__init__.py

@@ -3,11 +3,12 @@ from fastvideo.configs.models.dits.cosmos2_5 import Cosmos25VideoConfig
 from fastvideo.configs.models.dits.hunyuanvideo import HunyuanVideoConfig
 from fastvideo.configs.models.dits.hunyuanvideo15 import HunyuanVideo15Config
 from fastvideo.configs.models.dits.longcat import LongCatVideoConfig
+from fastvideo.configs.models.dits.ltx2 import LTX2VideoConfig
 from fastvideo.configs.models.dits.stepvideo import StepVideoConfig
 from fastvideo.configs.models.dits.wanvideo import WanVideoConfig
 
 __all__ = [
     "HunyuanVideoConfig", "HunyuanVideo15Config", "WanVideoConfig",
     "StepVideoConfig", "CosmosVideoConfig", "Cosmos25VideoConfig",
-    "LongCatVideoConfig"
+    "LongCatVideoConfig", "LTX2VideoConfig"
 ]

fastvideo/configs/models/dits/ltx2.py

@@ -0,0 +1,84 @@
+# SPDX-License-Identifier: Apache-2.0
+"""
+LTX-2 Transformer configuration for native FastVideo integration.
+"""
+
+from dataclasses import dataclass, field
+
+from fastvideo.configs.models.dits.base import DiTArchConfig, DiTConfig
+
+
+def is_ltx2_blocks(name: str, _module) -> bool:
+    """FSDP shard condition for LTX-2 transformer blocks."""
+    return "transformer_blocks" in name
+
+
+@dataclass
+class LTX2VideoArchConfig(DiTArchConfig):
+    """Architecture configuration for LTX-2 video transformer."""
+
+    _fsdp_shard_conditions: list = field(
+        default_factory=lambda: [is_ltx2_blocks])
+    _compile_conditions: list = field(default_factory=lambda: [is_ltx2_blocks])
+
+    # Parameter name mapping for weight conversion (hf/comfy -> FastVideo)
+    param_names_mapping: dict = field(
+        default_factory=lambda: {
+            r"^model\.diffusion_model\.(.*)$": r"model.\1",
+            r"^diffusion_model\.(.*)$": r"model.\1",
+            r"^model\.(.*)$": r"model.\1",
+            r"^(.*)$": r"model.\1",
+        })
+
+    reverse_param_names_mapping: dict = field(default_factory=lambda: {})
+    lora_param_names_mapping: dict = field(default_factory=lambda: {})
+
+    # Core transformer settings (defaults from LTX-2 metadata)
+    num_attention_heads: int = 32
+    attention_head_dim: int = 128
+    num_layers: int = 48
+    cross_attention_dim: int = 4096
+    caption_channels: int = 3840
+    norm_eps: float = 1e-6
+    attention_type: str = "default"
+    rope_type: str = "split"
+    double_precision_rope: bool = True
+
+    positional_embedding_theta: float = 10000.0
+    positional_embedding_max_pos: list[int] = field(
+        default_factory=lambda: [20, 2048, 2048])
+    timestep_scale_multiplier: int = 1000
+    use_middle_indices_grid: bool = True
+
+    # Patchification (video-only path)
+    patch_size: tuple[int, int, int] = (1, 1, 1)
+    num_channels_latents: int = 128
+    in_channels: int | None = None
+    out_channels: int | None = None
+
+    # Audio defaults (reserved for joint AV ports)
+    audio_num_attention_heads: int = 32
+    audio_attention_head_dim: int = 64
+    audio_in_channels: int = 128
+    audio_out_channels: int = 128
+    audio_cross_attention_dim: int = 2048
+    audio_positional_embedding_max_pos: list[int] = field(
+        default_factory=lambda: [20])
+    av_ca_timestep_scale_multiplier: int = 1
+
+    def __post_init__(self):
+        super().__post_init__()
+        patch_volume = self.patch_size[0] * self.patch_size[
+            1] * self.patch_size[2]
+        if self.in_channels is None:
+            self.in_channels = self.num_channels_latents * patch_volume
+        if self.out_channels is None:
+            self.out_channels = self.in_channels
+
+
+@dataclass
+class LTX2VideoConfig(DiTConfig):
+    """Main configuration for LTX-2 transformer."""
+
+    arch_config: DiTArchConfig = field(default_factory=LTX2VideoArchConfig)
+    prefix: str = "ltx2"

fastvideo/configs/models/vaes/__init__.py

@@ -2,6 +2,7 @@ from fastvideo.configs.models.vaes.cosmosvae import CosmosVAEConfig
 from fastvideo.configs.models.vaes.cosmos2_5vae import Cosmos25VAEConfig
 from fastvideo.configs.models.vaes.hunyuanvae import HunyuanVAEConfig
 from fastvideo.configs.models.vaes.hunyuan15vae import Hunyuan15VAEConfig
+from fastvideo.configs.models.vaes.ltx2vae import LTX2VAEConfig
 from fastvideo.configs.models.vaes.stepvideovae import StepVideoVAEConfig
 from fastvideo.configs.models.vaes.wanvae import WanVAEConfig
 
@@ -12,4 +13,5 @@ __all__ = [
     "CosmosVAEConfig",
     "Cosmos25VAEConfig",
     "Hunyuan15VAEConfig",
+    "LTX2VAEConfig",
 ]

fastvideo/models/loader/component_loader.py

@@ -837,7 +837,18 @@ class TransformerLoader(ComponentLoader):
         model = model.eval()
 
         if fastvideo_args.inference_mode and fastvideo_args.dit_layerwise_offload:
-            enable_layerwise_offload(model)
+            # Check if model has nn.ModuleList for layerwise offload compatibility
+            has_module_list = any(
+                isinstance(m, nn.ModuleList) for m in model.children()
+            )
+            if has_module_list:
+                enable_layerwise_offload(model)
+            else:
+                logger.warning(
+                    "Layerwise offload requested but model %s does not have "
+                    "nn.ModuleList structure. Skipping layerwise offload.",
+                    cls_name
+                )
         return model
 
 

fastvideo/models/registry.py

@@ -33,6 +33,7 @@ _TEXT_TO_VIDEO_DIT_MODELS = {
     "Cosmos25Transformer3DModel": ("dits", "cosmos2_5", "Cosmos25Transformer3DModel"),
     "LongCatVideoTransformer3DModel": ("dits", "longcat_video_dit", "LongCatVideoTransformer3DModel"),  # Wrapper (Phase 1)
     "LongCatTransformer3DModel": ("dits", "longcat", "LongCatTransformer3DModel"),  # Native (Phase 2)
+    "LTX2Transformer3DModel": ("dits", "ltx2", "LTX2Transformer3DModel"),
 }
 
 _IMAGE_TO_VIDEO_DIT_MODELS = {
@@ -68,7 +69,8 @@ _VAE_MODELS = {
     ("vaes", "hunyuanvae", "AutoencoderKLHunyuanVideo"),
     "AutoencoderKLHunyuanVideo15": ("vaes", "hunyuan15vae", "AutoencoderKLHunyuanVideo15"),
     "AutoencoderKLWan": ("vaes", "wanvae", "AutoencoderKLWan"),
-    "AutoencoderKLStepvideo": ("vaes", "stepvideovae", "AutoencoderKLStepvideo")
+    "AutoencoderKLStepvideo": ("vaes", "stepvideovae", "AutoencoderKLStepvideo"),
+    "CausalVideoAutoencoder": ("vaes", "ltx2vae", "LTX2CausalVideoAutoencoder"),
 }
 
 _AUDIO_MODELS = {