update ltx-2

Fix AttributeError when pipe.dit is None during split training

README.md

@@ -645,6 +645,8 @@ Example code for LTX-2 is available at: [/examples/ltx2/](/examples/ltx2/)
 | Model ID | Extra Args | Inference | Low-VRAM Inference | Full Training | Full Training Validation | LoRA Training | LoRA Training Validation |
 |-|-|-|-|-|-|-|-|
 |[Lightricks/LTX-2: OneStagePipeline-T2AV](https://www.modelscope.cn/models/Lightricks/LTX-2)||[code](/examples/ltx2/model_inference/LTX-2-T2AV-OneStage.py)|[code](/examples/ltx2/model_inference_low_vram/LTX-2-T2AV-OneStage.py)|[code](/examples/ltx2/model_training/full/LTX-2-T2AV-splited.sh)|[code](/examples/ltx2/model_training/validate_full/LTX-2-T2AV.py)|[code](/examples/ltx2/model_training/lora/LTX-2-T2AV-splited.sh)|[code](/examples/ltx2/model_training/validate_lora/LTX-2-T2AV.py)|
+|[Lightricks/LTX-2-19b-IC-LoRA-Union-Control](https://www.modelscope.cn/models/Lightricks/LTX-2-19b-IC-LoRA-Union-Control)|`in_context_videos`,`in_context_downsample_factor`|[code](/examples/ltx2/model_inference/LTX-2-T2AV-IC-LoRA-Union-Control.py)|[code](/examples/ltx2/model_inference_low_vram/LTX-2-T2AV-IC-LoRA-Union-Control.py)|-|-|[code](/examples/ltx2/model_training/lora/LTX-2-T2AV-IC-LoRA-splited.sh)|[code](/examples/ltx2/model_training/validate_lora/LTX-2-T2AV-IC-LoRA.py)|
+|[Lightricks/LTX-2-19b-IC-LoRA-Detailer](https://www.modelscope.cn/models/Lightricks/LTX-2-19b-IC-LoRA-Detailer)|`in_context_videos`,`in_context_downsample_factor`|[code](/examples/ltx2/model_inference/LTX-2-T2AV-IC-LoRA-Detailer.py)|[code](/examples/ltx2/model_inference_low_vram/LTX-2-T2AV-IC-LoRA-Detailer.py)|-|-|[code](/examples/ltx2/model_training/lora/LTX-2-T2AV-IC-LoRA-splited.sh)|[code](/examples/ltx2/model_training/validate_lora/LTX-2-T2AV-IC-LoRA.py)|
 |[Lightricks/LTX-2: TwoStagePipeline-T2AV](https://www.modelscope.cn/models/Lightricks/LTX-2)||[code](/examples/ltx2/model_inference/LTX-2-T2AV-TwoStage.py)|[code](/examples/ltx2/model_inference_low_vram/LTX-2-T2AV-TwoStage.py)|-|-|-|-|
 |[Lightricks/LTX-2: DistilledPipeline-T2AV](https://www.modelscope.cn/models/Lightricks/LTX-2)||[code](/examples/ltx2/model_inference/LTX-2-T2AV-DistilledPipeline.py)|[code](/examples/ltx2/model_inference_low_vram/LTX-2-T2AV-DistilledPipeline.py)|-|-|-|-|
 |[Lightricks/LTX-2: OneStagePipeline-I2AV](https://www.modelscope.cn/models/Lightricks/LTX-2)|`input_images`|[code](/examples/ltx2/model_inference/LTX-2-I2AV-OneStage.py)|[code](/examples/ltx2/model_inference_low_vram/LTX-2-I2AV-OneStage.py)|-|-|-|-|

README_zh.md

@@ -645,6 +645,8 @@ LTX-2 的示例代码位于：[/examples/ltx2/](/examples/ltx2/)
 |模型 ID|额外参数|推理|低显存推理|全量训练|全量训练后验证|LoRA 训练|LoRA 训练后验证|
 |-|-|-|-|-|-|-|-|
 |[Lightricks/LTX-2: OneStagePipeline-T2AV](https://www.modelscope.cn/models/Lightricks/LTX-2)||[code](/examples/ltx2/model_inference/LTX-2-T2AV-OneStage.py)|[code](/examples/ltx2/model_inference_low_vram/LTX-2-T2AV-OneStage.py)|[code](/examples/ltx2/model_training/full/LTX-2-T2AV-splited.sh)|[code](/examples/ltx2/model_training/validate_full/LTX-2-T2AV.py)|[code](/examples/ltx2/model_training/lora/LTX-2-T2AV-splited.sh)|[code](/examples/ltx2/model_training/validate_lora/LTX-2-T2AV.py)|
+|[Lightricks/LTX-2-19b-IC-LoRA-Union-Control](https://www.modelscope.cn/models/Lightricks/LTX-2-19b-IC-LoRA-Union-Control)|`in_context_videos`,`in_context_downsample_factor`|[code](/examples/ltx2/model_inference/LTX-2-T2AV-IC-LoRA-Union-Control.py)|[code](/examples/ltx2/model_inference_low_vram/LTX-2-T2AV-IC-LoRA-Union-Control.py)|-|-|[code](/examples/ltx2/model_training/lora/LTX-2-T2AV-IC-LoRA-splited.sh)|[code](/examples/ltx2/model_training/validate_lora/LTX-2-T2AV-IC-LoRA.py)|
+|[Lightricks/LTX-2-19b-IC-LoRA-Detailer](https://www.modelscope.cn/models/Lightricks/LTX-2-19b-IC-LoRA-Detailer)|`in_context_videos`,`in_context_downsample_factor`|[code](/examples/ltx2/model_inference/LTX-2-T2AV-IC-LoRA-Detailer.py)|[code](/examples/ltx2/model_inference_low_vram/LTX-2-T2AV-IC-LoRA-Detailer.py)|-|-|[code](/examples/ltx2/model_training/lora/LTX-2-T2AV-IC-LoRA-splited.sh)|[code](/examples/ltx2/model_training/validate_lora/LTX-2-T2AV-IC-LoRA.py)|
 |[Lightricks/LTX-2: TwoStagePipeline-T2AV](https://www.modelscope.cn/models/Lightricks/LTX-2)||[code](/examples/ltx2/model_inference/LTX-2-T2AV-TwoStage.py)|[code](/examples/ltx2/model_inference_low_vram/LTX-2-T2AV-TwoStage.py)|-|-|-|-|
 |[Lightricks/LTX-2: DistilledPipeline-T2AV](https://www.modelscope.cn/models/Lightricks/LTX-2)||[code](/examples/ltx2/model_inference/LTX-2-T2AV-DistilledPipeline.py)|[code](/examples/ltx2/model_inference_low_vram/LTX-2-T2AV-DistilledPipeline.py)|-|-|-|-|
 |[Lightricks/LTX-2: OneStagePipeline-I2AV](https://www.modelscope.cn/models/Lightricks/LTX-2)|`input_images`|[code](/examples/ltx2/model_inference/LTX-2-I2AV-OneStage.py)|[code](/examples/ltx2/model_inference_low_vram/LTX-2-I2AV-OneStage.py)|-|-|-|-|

diffsynth/diffusion/base_pipeline.py

@@ -94,19 +94,22 @@ class BasePipeline(torch.nn.Module):
         return self
 
 
-    def check_resize_height_width(self, height, width, num_frames=None):
+    def check_resize_height_width(self, height, width, num_frames=None, verbose=1):
         # Shape check
         if height % self.height_division_factor != 0:
             height = (height + self.height_division_factor - 1) // self.height_division_factor * self.height_division_factor
+            if verbose > 0:
                 print(f"height % {self.height_division_factor} != 0. We round it up to {height}.")
         if width % self.width_division_factor != 0:
             width = (width + self.width_division_factor - 1) // self.width_division_factor * self.width_division_factor
+            if verbose > 0:
                 print(f"width % {self.width_division_factor} != 0. We round it up to {width}.")
         if num_frames is None:
             return height, width
         else:
             if num_frames % self.time_division_factor != self.time_division_remainder:
                 num_frames = (num_frames + self.time_division_factor - 1) // self.time_division_factor * self.time_division_factor + self.time_division_remainder
+                if verbose > 0:
                     print(f"num_frames % {self.time_division_factor} != {self.time_division_remainder}. We round it up to {num_frames}.")
             return height, width, num_frames
 

diffsynth/diffusion/loss.py

@@ -121,7 +121,9 @@ class TrajectoryImitationLoss(torch.nn.Module):
                 progress_id_teacher = torch.argmin((timesteps_teacher - pipe.scheduler.timesteps[progress_id + 1]).abs())
                 latents_ = trajectory_teacher[progress_id_teacher]
             
-            target = (latents_ - inputs_shared["latents"]) / (sigma_ - sigma)
+            denom = sigma_ - sigma
+            denom = torch.sign(denom) * torch.clamp(denom.abs(), min=1e-6)
+            target = (latents_ - inputs_shared["latents"]) / denom
             loss = loss + torch.nn.functional.mse_loss(noise_pred.float(), target.float()) * pipe.scheduler.training_weight(timestep)
         return loss
     

diffsynth/models/ltx2_dit.py

@@ -8,6 +8,7 @@ import torch
 from einops import rearrange
 from .ltx2_common import rms_norm, Modality
 from ..core.attention.attention import attention_forward
+from ..core import gradient_checkpoint_forward
 
 
 def get_timestep_embedding(
@@ -1352,24 +1353,17 @@ class LTXModel(torch.nn.Module):
         video: TransformerArgs | None,
         audio: TransformerArgs | None,
         perturbations: BatchedPerturbationConfig,
+        use_gradient_checkpointing: bool = False,
+        use_gradient_checkpointing_offload: bool = False,
     ) -> tuple[TransformerArgs, TransformerArgs]:
         """Process transformer blocks for LTXAV."""
 
         # Process transformer blocks
         for block in self.transformer_blocks:
-            if self._enable_gradient_checkpointing and self.training:
-                # Use gradient checkpointing to save memory during training.
-                # With use_reentrant=False, we can pass dataclasses directly -
-                # PyTorch will track all tensor leaves in the computation graph.
-                video, audio = torch.utils.checkpoint.checkpoint(
+            video, audio = gradient_checkpoint_forward(
                 block,
-                    video,
-                    audio,
-                    perturbations,
-                    use_reentrant=False,
-                )
-            else:
-                video, audio = block(
+                use_gradient_checkpointing,
+                use_gradient_checkpointing_offload,
                 video=video,
                 audio=audio,
                 perturbations=perturbations,
@@ -1398,7 +1392,12 @@ class LTXModel(torch.nn.Module):
         return x
 
     def _forward(
-        self, video: Modality | None, audio: Modality | None, perturbations: BatchedPerturbationConfig
+        self,
+        video: Modality | None,
+        audio: Modality | None,
+        perturbations: BatchedPerturbationConfig,
+        use_gradient_checkpointing: bool = False,
+        use_gradient_checkpointing_offload: bool = False,
     ) -> tuple[torch.Tensor, torch.Tensor]:
         """
         Forward pass for LTX models.
@@ -1417,6 +1416,8 @@ class LTXModel(torch.nn.Module):
             video=video_args,
             audio=audio_args,
             perturbations=perturbations,
+            use_gradient_checkpointing=use_gradient_checkpointing,
+            use_gradient_checkpointing_offload=use_gradient_checkpointing_offload,
         )
 
         # Process output
@@ -1440,12 +1441,12 @@ class LTXModel(torch.nn.Module):
         )
         return vx, ax
 
-    def forward(self, video_latents, video_positions, video_context, video_timesteps, audio_latents, audio_positions, audio_context, audio_timesteps):
+    def forward(self, video_latents, video_positions, video_context, video_timesteps, audio_latents, audio_positions, audio_context, audio_timesteps, use_gradient_checkpointing=False, use_gradient_checkpointing_offload=False):
         cross_pe_max_pos = None
         if self.model_type.is_video_enabled() and self.model_type.is_audio_enabled():
             cross_pe_max_pos = max(self.positional_embedding_max_pos[0], self.audio_positional_embedding_max_pos[0])
         self._init_preprocessors(cross_pe_max_pos)
         video = Modality(video_latents, video_timesteps, video_positions, video_context)
         audio = Modality(audio_latents, audio_timesteps, audio_positions, audio_context) if audio_latents is not None else None
-        vx, ax = self._forward(video=video, audio=audio, perturbations=None)
+        vx, ax = self._forward(video=video, audio=audio, perturbations=None, use_gradient_checkpointing=use_gradient_checkpointing, use_gradient_checkpointing_offload=use_gradient_checkpointing_offload)
         return vx, ax

diffsynth/models/wan_video_vae.py

@@ -469,7 +469,7 @@ class Down_ResidualBlock(nn.Module):
     def forward(self, x, feat_cache=None, feat_idx=[0]):
         x_copy = x.clone()
         for module in self.downsamples:
-            x = module(x, feat_cache, feat_idx)
+            x, feat_cache, feat_idx = module(x, feat_cache, feat_idx)
 
         return x + self.avg_shortcut(x_copy), feat_cache, feat_idx
 
@@ -506,10 +506,10 @@ class Up_ResidualBlock(nn.Module):
     def forward(self, x, feat_cache=None, feat_idx=[0], first_chunk=False):
         x_main = x.clone()
         for module in self.upsamples:
-            x_main = module(x_main, feat_cache, feat_idx)
+            x_main, feat_cache, feat_idx = module(x_main, feat_cache, feat_idx)
         if self.avg_shortcut is not None:
             x_shortcut = self.avg_shortcut(x, first_chunk)
-            return x_main + x_shortcut
+            return x_main + x_shortcut, feat_cache, feat_idx
         else:
             return x_main, feat_cache, feat_idx
 

diffsynth/pipelines/ltx2_audio_video.py

@@ -61,6 +61,7 @@ class LTX2AudioVideoPipeline(BasePipeline):
             LTX2AudioVideoUnit_InputAudioEmbedder(),
             LTX2AudioVideoUnit_InputVideoEmbedder(),
             LTX2AudioVideoUnit_InputImagesEmbedder(),
+            LTX2AudioVideoUnit_InContextVideoEmbedder(),
         ]
         self.model_fn = model_fn_ltx2
 
@@ -105,6 +106,8 @@ class LTX2AudioVideoPipeline(BasePipeline):
 
     def stage2_denoise(self, inputs_shared, inputs_posi, inputs_nega, progress_bar_cmd=tqdm):
         if inputs_shared["use_two_stage_pipeline"]:
+            if inputs_shared.get("clear_lora_before_state_two", False):
+                self.clear_lora()
             latent = self.video_vae_encoder.per_channel_statistics.un_normalize(inputs_shared["video_latents"])
             self.load_models_to_device('upsampler',)
             latent = self.upsampler(latent)
@@ -112,11 +115,17 @@ class LTX2AudioVideoPipeline(BasePipeline):
             self.scheduler.set_timesteps(special_case="stage2")
             inputs_shared.update({k.replace("stage2_", ""): v for k, v in inputs_shared.items() if k.startswith("stage2_")})
             denoise_mask_video = 1.0
+            # input image
             if inputs_shared.get("input_images", None) is not None:
                 latent, denoise_mask_video, initial_latents = self.apply_input_images_to_latents(
                     latent, inputs_shared.pop("input_latents"), inputs_shared["input_images_indexes"],
                     inputs_shared["input_images_strength"], latent.clone())
                 inputs_shared.update({"input_latents_video": initial_latents, "denoise_mask_video": denoise_mask_video})
+            # remove in-context video control in stage 2
+            inputs_shared.pop("in_context_video_latents", None)
+            inputs_shared.pop("in_context_video_positions", None)
+
+            # initialize latents for stage 2
             inputs_shared["video_latents"] = self.scheduler.sigmas[0] * denoise_mask_video * inputs_shared[
                 "video_noise"] + (1 - self.scheduler.sigmas[0] * denoise_mask_video) * latent
             inputs_shared["audio_latents"] = self.scheduler.sigmas[0] * inputs_shared["audio_noise"] + (
@@ -145,11 +154,14 @@ class LTX2AudioVideoPipeline(BasePipeline):
         # Prompt
         prompt: str,
         negative_prompt: Optional[str] = "",
-        # Image-to-video
         denoising_strength: float = 1.0,
+        # Image-to-video
         input_images: Optional[list[Image.Image]] = None,
         input_images_indexes: Optional[list[int]] = None,
         input_images_strength: Optional[float] = 1.0,
+        # In-Context Video Control
+        in_context_videos: Optional[list[list[Image.Image]]] = None,
+        in_context_downsample_factor: Optional[int] = 2,
         # Randomness
         seed: Optional[int] = None,
         rand_device: Optional[str] = "cpu",
@@ -157,6 +169,7 @@ class LTX2AudioVideoPipeline(BasePipeline):
         height: Optional[int] = 512,
         width: Optional[int] = 768,
         num_frames=121,
+        frame_rate=24,
         # Classifier-free guidance
         cfg_scale: Optional[float] = 3.0,
         # Scheduler
@@ -169,6 +182,7 @@ class LTX2AudioVideoPipeline(BasePipeline):
         tile_overlap_in_frames: Optional[int] = 24,
         # Special Pipelines
         use_two_stage_pipeline: Optional[bool] = False,
+        clear_lora_before_state_two: Optional[bool] = False,
         use_distilled_pipeline: Optional[bool] = False,
         # progress_bar
         progress_bar_cmd=tqdm,
@@ -185,12 +199,13 @@ class LTX2AudioVideoPipeline(BasePipeline):
         }
         inputs_shared = {
             "input_images": input_images, "input_images_indexes": input_images_indexes, "input_images_strength": input_images_strength,
+            "in_context_videos": in_context_videos, "in_context_downsample_factor": in_context_downsample_factor,
             "seed": seed, "rand_device": rand_device,
-            "height": height, "width": width, "num_frames": num_frames,
+            "height": height, "width": width, "num_frames": num_frames, "frame_rate": frame_rate,
             "cfg_scale": cfg_scale,
             "tiled": tiled, "tile_size_in_pixels": tile_size_in_pixels, "tile_overlap_in_pixels": tile_overlap_in_pixels,
             "tile_size_in_frames": tile_size_in_frames, "tile_overlap_in_frames": tile_overlap_in_frames,
-            "use_two_stage_pipeline": use_two_stage_pipeline, "use_distilled_pipeline": use_distilled_pipeline,
+            "use_two_stage_pipeline": use_two_stage_pipeline, "use_distilled_pipeline": use_distilled_pipeline, "clear_lora_before_state_two": clear_lora_before_state_two,
             "video_patchifier": self.video_patchifier, "audio_patchifier": self.audio_patchifier,
         }
         for unit in self.units:
@@ -417,8 +432,8 @@ class LTX2AudioVideoUnit_PromptEmbedder(PipelineUnit):
 class LTX2AudioVideoUnit_NoiseInitializer(PipelineUnit):
     def __init__(self):
         super().__init__(
-            input_params=("height", "width", "num_frames", "seed", "rand_device", "use_two_stage_pipeline"),
-            output_params=("video_noise", "audio_noise",),
+            input_params=("height", "width", "num_frames", "seed", "rand_device", "frame_rate", "use_two_stage_pipeline"),
+            output_params=("video_noise", "audio_noise", "video_positions", "audio_positions", "video_latent_shape", "audio_latent_shape")
         )
 
     def process_stage(self, pipe: LTX2AudioVideoPipeline, height, width, num_frames, seed, rand_device, frame_rate=24.0):
@@ -471,7 +486,6 @@ class LTX2AudioVideoUnit_InputVideoEmbedder(PipelineUnit):
             if pipe.scheduler.training:
                 return {"video_latents": input_latents, "input_latents": input_latents}
             else:
-                # TODO: implement video-to-video
                 raise NotImplementedError("Video-to-video not implemented yet.")
 
 class LTX2AudioVideoUnit_InputAudioEmbedder(PipelineUnit):
@@ -495,14 +509,13 @@ class LTX2AudioVideoUnit_InputAudioEmbedder(PipelineUnit):
             if pipe.scheduler.training:
                 return {"audio_latents": audio_input_latents, "audio_input_latents": audio_input_latents, "audio_positions": audio_positions, "audio_latent_shape": audio_latent_shape}
             else:
-                # TODO: implement video-to-video
-                raise NotImplementedError("Video-to-video not implemented yet.")
+                raise NotImplementedError("Audio-to-video not supported.")
 
 class LTX2AudioVideoUnit_InputImagesEmbedder(PipelineUnit):
     def __init__(self):
         super().__init__(
             input_params=("input_images", "input_images_indexes", "input_images_strength", "video_latents", "height", "width", "num_frames", "tiled", "tile_size_in_pixels", "tile_overlap_in_pixels", "use_two_stage_pipeline"),
-            output_params=("video_latents"),
+            output_params=("video_latents", "denoise_mask_video", "input_latents_video", "stage2_input_latents"),
             onload_model_names=("video_vae_encoder")
         )
 
@@ -537,6 +550,54 @@ class LTX2AudioVideoUnit_InputImagesEmbedder(PipelineUnit):
             return output_dicts
 
 
+class LTX2AudioVideoUnit_InContextVideoEmbedder(PipelineUnit):
+    def __init__(self):
+        super().__init__(
+            input_params=("in_context_videos", "height", "width", "num_frames", "frame_rate", "in_context_downsample_factor", "tiled", "tile_size_in_pixels", "tile_overlap_in_pixels", "use_two_stage_pipeline"),
+            output_params=("in_context_video_latents", "in_context_video_positions"),
+            onload_model_names=("video_vae_encoder")
+        )
+
+    def check_in_context_video(self, pipe, in_context_video, height, width, num_frames, in_context_downsample_factor, use_two_stage_pipeline=True):
+        if in_context_video is None or len(in_context_video) == 0:
+            raise ValueError("In-context video is None or empty.")
+        in_context_video = in_context_video[:num_frames]
+        expected_height = height // in_context_downsample_factor // 2 if use_two_stage_pipeline else height // in_context_downsample_factor
+        expected_width = width // in_context_downsample_factor // 2 if use_two_stage_pipeline else width // in_context_downsample_factor
+        current_h, current_w, current_f = in_context_video[0].size[1], in_context_video[0].size[0], len(in_context_video)
+        h, w, f = pipe.check_resize_height_width(expected_height, expected_width, current_f, verbose=0)
+        if current_h != h or current_w != w:
+            in_context_video = [img.resize((w, h)) for img in in_context_video]
+        if current_f != f:
+            # pad black frames at the end
+            in_context_video = in_context_video + [Image.new("RGB", (w, h), (0, 0, 0))] * (f - current_f)
+        return in_context_video
+
+    def process(self, pipe: LTX2AudioVideoPipeline, in_context_videos, height, width, num_frames, frame_rate, in_context_downsample_factor, tiled, tile_size_in_pixels, tile_overlap_in_pixels, use_two_stage_pipeline=True):
+        if in_context_videos is None or len(in_context_videos) == 0:
+            return {}
+        else:
+            pipe.load_models_to_device(self.onload_model_names)
+            latents, positions = [], []
+            for in_context_video in in_context_videos:
+                in_context_video = self.check_in_context_video(pipe, in_context_video, height, width, num_frames, in_context_downsample_factor, use_two_stage_pipeline)
+                in_context_video = pipe.preprocess_video(in_context_video)
+                in_context_latents = pipe.video_vae_encoder.encode(in_context_video, tiled, tile_size_in_pixels, tile_overlap_in_pixels).to(dtype=pipe.torch_dtype, device=pipe.device)
+
+                latent_coords = pipe.video_patchifier.get_patch_grid_bounds(output_shape=VideoLatentShape.from_torch_shape(in_context_latents.shape), device=pipe.device)
+                video_positions = get_pixel_coords(latent_coords, VIDEO_SCALE_FACTORS, True).float()
+                video_positions[:, 0, ...] = video_positions[:, 0, ...] / frame_rate
+                video_positions[:, 1, ...] *= in_context_downsample_factor  # height axis
+                video_positions[:, 2, ...] *= in_context_downsample_factor  # width axis
+                video_positions = video_positions.to(pipe.torch_dtype)
+
+                latents.append(in_context_latents)
+                positions.append(video_positions)
+            latents = torch.cat(latents, dim=1)
+            positions = torch.cat(positions, dim=1)
+            return {"in_context_video_latents": latents, "in_context_video_positions": positions}
+
+
 def model_fn_ltx2(
     dit: LTXModel,
     video_latents=None,
@@ -549,6 +610,8 @@ def model_fn_ltx2(
     audio_patchifier=None,
     timestep=None,
     denoise_mask_video=None,
+    in_context_video_latents=None,
+    in_context_video_positions=None,
     use_gradient_checkpointing=False,
     use_gradient_checkpointing_offload=False,
     **kwargs,
@@ -558,16 +621,25 @@ def model_fn_ltx2(
     # patchify
     b, c_v, f, h, w = video_latents.shape
     video_latents = video_patchifier.patchify(video_latents)
+    seq_len_video = video_latents.shape[1]
     video_timesteps = timestep.repeat(1, video_latents.shape[1], 1)
     if denoise_mask_video is not None:
         video_timesteps = video_patchifier.patchify(denoise_mask_video) * video_timesteps
+
+    if in_context_video_latents is not None:
+        in_context_video_latents = video_patchifier.patchify(in_context_video_latents)
+        in_context_video_timesteps = timestep.repeat(1, in_context_video_latents.shape[1], 1) * 0.
+        video_latents = torch.cat([video_latents, in_context_video_latents], dim=1)
+        video_positions = torch.cat([video_positions, in_context_video_positions], dim=2)
+        video_timesteps = torch.cat([video_timesteps, in_context_video_timesteps], dim=1)
+
     if audio_latents is not None:
         _, c_a, _, mel_bins  = audio_latents.shape
         audio_latents = audio_patchifier.patchify(audio_latents)
         audio_timesteps = timestep.repeat(1, audio_latents.shape[1], 1)
     else:
         audio_timesteps = None
-    #TODO: support gradient checkpointing in training
+
     vx, ax = dit(
         video_latents=video_latents,
         video_positions=video_positions,
@@ -577,7 +649,11 @@ def model_fn_ltx2(
         audio_positions=audio_positions,
         audio_context=audio_context,
         audio_timesteps=audio_timesteps,
+        use_gradient_checkpointing=use_gradient_checkpointing,
+        use_gradient_checkpointing_offload=use_gradient_checkpointing_offload,
     )
+
+    vx = vx[:, :seq_len_video, ...]
     # unpatchify
     vx = video_patchifier.unpatchify_video(vx, f, h, w)
     ax = audio_patchifier.unpatchify_audio(ax, c_a, mel_bins) if ax is not None else None

diffsynth/pipelines/z_image.py

@@ -299,7 +299,7 @@ class ZImageUnit_PromptEmbedder(PipelineUnit):
 
     def process(self, pipe: ZImagePipeline, prompt, edit_image):
         pipe.load_models_to_device(self.onload_model_names)
-        if hasattr(pipe, "dit") and pipe.dit.siglip_embedder is not None:
+        if hasattr(pipe, "dit") and pipe.dit is not None and pipe.dit.siglip_embedder is not None:
             # Z-Image-Turbo and Z-Image-Omni-Base use different prompt encoding methods.
             # We determine which encoding method to use based on the model architecture.
             # If you are using two-stage split training,

diffsynth/utils/data/__init__.py

@@ -116,7 +116,7 @@ class VideoData:
         if self.height is not None and self.width is not None:
             return self.height, self.width
         else:
-            height, width, _ = self.__getitem__(0).shape
+            width, height = self.__getitem__(0).size
             return height, width
 
     def __getitem__(self, item):

docs/en/Model_Details/LTX-2.md

@@ -112,6 +112,8 @@ write_video_audio_ltx2(
 |Model ID|Additional Parameters|Inference|Low VRAM Inference|Full Training|Validation After Full Training|LoRA Training|Validation After LoRA Training|
 |-|-|-|-|-|-|-|-|
 |[Lightricks/LTX-2: OneStagePipeline-T2AV](https://www.modelscope.cn/models/Lightricks/LTX-2)||[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/ltx2/model_inference/LTX-2-T2AV-OneStage.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/ltx2/model_inference_low_vram/LTX-2-T2AV-OneStage.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/ltx2/model_training/full/LTX-2-T2AV-splited.sh)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/ltx2/model_training/validate_full/LTX-2-T2AV.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/ltx2/model_training/lora/LTX-2-T2AV-splited.sh)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/ltx2/model_training/validate_lora/LTX-2-T2AV.py)|
+|[Lightricks/LTX-2-19b-IC-LoRA-Union-Control](https://www.modelscope.cn/models/Lightricks/LTX-2-19b-IC-LoRA-Union-Control)|`in_context_videos`,`in_context_downsample_factor`|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/ltx2/model_inference/LTX-2-T2AV-IC-LoRA-Union-Control.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/ltx2/model_inference_low_vram/LTX-2-T2AV-IC-LoRA-Union-Control.py)|-|-|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/ltx2/model_training/lora/LTX-2-T2AV-IC-LoRA-splited.sh)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/ltx2/model_training/validate_lora/LTX-2-T2AV-IC-LoRA.py)|
+|[Lightricks/LTX-2-19b-IC-LoRA-Detailer](https://www.modelscope.cn/models/Lightricks/LTX-2-19b-IC-LoRA-Detailer)|`in_context_videos`,`in_context_downsample_factor`|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/ltx2/model_inference/LTX-2-T2AV-IC-LoRA-Detailer.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/ltx2/model_inference_low_vram/LTX-2-T2AV-IC-LoRA-Detailer.py)|-|-|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/ltx2/model_training/lora/LTX-2-T2AV-IC-LoRA-splited.sh)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/ltx2/model_training/validate_lora/LTX-2-T2AV-IC-LoRA.py)|
 |[Lightricks/LTX-2: TwoStagePipeline-T2AV](https://www.modelscope.cn/models/Lightricks/LTX-2)||[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/ltx2/model_inference/LTX-2-T2AV-TwoStage.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/ltx2/model_inference_low_vram/LTX-2-T2AV-TwoStage.py)|-|-|-|-|
 |[Lightricks/LTX-2: DistilledPipeline-T2AV](https://www.modelscope.cn/models/Lightricks/LTX-2)||[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/ltx2/model_inference/LTX-2-T2AV-DistilledPipeline.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/ltx2/model_inference_low_vram/LTX-2-T2AV-DistilledPipeline.py)|-|-|-|-|
 |[Lightricks/LTX-2: OneStagePipeline-I2AV](https://www.modelscope.cn/models/Lightricks/LTX-2)|`input_images`|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/ltx2/model_inference/LTX-2-I2AV-OneStage.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/ltx2/model_inference_low_vram/LTX-2-I2AV-OneStage.py)|-|-|-|-|

docs/en/Pipeline_Usage/GPU_support.md

@@ -91,3 +91,4 @@ Set 0 or not set: indicates not enabling the binding function
 |----------------|---------------------------|-------------------|
 | Wan 14B series | --initialize_model_on_cpu | The 14B model needs to be initialized on the CPU |
 | Qwen-Image series | --initialize_model_on_cpu | The model needs to be initialized on the CPU |
+| Z-Image series | --enable_npu_patch | Using NPU fusion operator to replace the corresponding operator in Z-image model to improve the performance of the model on NPU |

docs/en/Pipeline_Usage/Setup.md

@@ -37,9 +37,9 @@ pip install torch torchvision --index-url https://download.pytorch.org/whl/rocm6
    git clone https://github.com/modelscope/DiffSynth-Studio.git
    cd DiffSynth-Studio
    # aarch64/ARM
-   pip install -e .[npu_aarch64] --extra-index-url "https://download.pytorch.org/whl/cpu"
+   pip install -e .[npu_aarch64] 
    # x86
-   pip install -e .[npu]
+   pip install -e .[npu] --extra-index-url "https://download.pytorch.org/whl/cpu"
 
 When using Ascend NPU, please replace `"cuda"` with `"npu"` in your Python code. For details, see [NPU Support](../Pipeline_Usage/GPU_support.md#ascend-npu).
 

docs/en/index.rst

@@ -27,6 +27,7 @@ Welcome to DiffSynth-Studio's Documentation
    Model_Details/Qwen-Image
    Model_Details/FLUX2
    Model_Details/Z-Image
+   Model_Details/LTX-2
 
 .. toctree::
    :maxdepth: 2

docs/zh/Model_Details/LTX-2.md

@@ -112,6 +112,8 @@ write_video_audio_ltx2(
 |模型 ID|额外参数|推理|低显存推理|全量训练|全量训练后验证|LoRA 训练|LoRA 训练后验证|
 |-|-|-|-|-|-|-|-|
 |[Lightricks/LTX-2: OneStagePipeline-T2AV](https://www.modelscope.cn/models/Lightricks/LTX-2)||[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/ltx2/model_inference/LTX-2-T2AV-OneStage.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/ltx2/model_inference_low_vram/LTX-2-T2AV-OneStage.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/ltx2/model_training/full/LTX-2-T2AV-splited.sh)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/ltx2/model_training/validate_full/LTX-2-T2AV.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/ltx2/model_training/lora/LTX-2-T2AV-splited.sh)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/ltx2/model_training/validate_lora/LTX-2-T2AV.py)|
+|[Lightricks/LTX-2-19b-IC-LoRA-Union-Control](https://www.modelscope.cn/models/Lightricks/LTX-2-19b-IC-LoRA-Union-Control)|`in_context_videos`,`in_context_downsample_factor`|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/ltx2/model_inference/LTX-2-T2AV-IC-LoRA-Union-Control.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/ltx2/model_inference_low_vram/LTX-2-T2AV-IC-LoRA-Union-Control.py)|-|-|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/ltx2/model_training/lora/LTX-2-T2AV-IC-LoRA-splited.sh)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/ltx2/model_training/validate_lora/LTX-2-T2AV-IC-LoRA.py)|
+|[Lightricks/LTX-2-19b-IC-LoRA-Detailer](https://www.modelscope.cn/models/Lightricks/LTX-2-19b-IC-LoRA-Detailer)|`in_context_videos`,`in_context_downsample_factor`|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/ltx2/model_inference/LTX-2-T2AV-IC-LoRA-Detailer.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/ltx2/model_inference_low_vram/LTX-2-T2AV-IC-LoRA-Detailer.py)|-|-|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/ltx2/model_training/lora/LTX-2-T2AV-IC-LoRA-splited.sh)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/ltx2/model_training/validate_lora/LTX-2-T2AV-IC-LoRA.py)|
 |[Lightricks/LTX-2: TwoStagePipeline-T2AV](https://www.modelscope.cn/models/Lightricks/LTX-2)||[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/ltx2/model_inference/LTX-2-T2AV-TwoStage.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/ltx2/model_inference_low_vram/LTX-2-T2AV-TwoStage.py)|-|-|-|-|
 |[Lightricks/LTX-2: DistilledPipeline-T2AV](https://www.modelscope.cn/models/Lightricks/LTX-2)||[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/ltx2/model_inference/LTX-2-T2AV-DistilledPipeline.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/ltx2/model_inference_low_vram/LTX-2-T2AV-DistilledPipeline.py)|-|-|-|-|
 |[Lightricks/LTX-2: OneStagePipeline-I2AV](https://www.modelscope.cn/models/Lightricks/LTX-2)|`input_images`|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/ltx2/model_inference/LTX-2-I2AV-OneStage.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/ltx2/model_inference_low_vram/LTX-2-I2AV-OneStage.py)|-|-|-|-|

docs/zh/Pipeline_Usage/GPU_support.md

@@ -90,3 +90,4 @@ export CPU_AFFINITY_CONF=1
 |-----------|------|-------------------|
 | Wan 14B系列 | --initialize_model_on_cpu | 14B模型需要在cpu上进行初始化 |
 | Qwen-Image系列 | --initialize_model_on_cpu | 模型需要在cpu上进行初始化 |
+| Z-Image 系列 | --enable_npu_patch | 使用NPU融合算子来替换Z-image模型中的对应算子以提升模型在NPU上的性能 |

docs/zh/Pipeline_Usage/Setup.md

@@ -37,9 +37,9 @@ pip install torch torchvision --index-url https://download.pytorch.org/whl/rocm6
    git clone https://github.com/modelscope/DiffSynth-Studio.git
    cd DiffSynth-Studio
    # aarch64/ARM
-   pip install -e .[npu_aarch64] --extra-index-url "https://download.pytorch.org/whl/cpu"
+   pip install -e .[npu_aarch64] 
    # x86
-   pip install -e .[npu]
+   pip install -e .[npu] --extra-index-url "https://download.pytorch.org/whl/cpu"
 
 使用 Ascend NPU 时，请将 Python 代码中的 `"cuda"` 改为 `"npu"`，详见[NPU 支持](../Pipeline_Usage/GPU_support.md#ascend-npu)。
 

docs/zh/index.rst

@@ -27,6 +27,7 @@
    Model_Details/Qwen-Image
    Model_Details/FLUX2
    Model_Details/Z-Image
+   Model_Details/LTX-2
 
 .. toctree::
    :maxdepth: 2

examples/ltx2/model_inference/LTX-2-I2AV-TwoStage.py

@@ -46,7 +46,6 @@ negative_prompt = (
     "inconsistent tone, cinematic oversaturation, stylized filters, or AI artifacts."
 )
 height, width, num_frames = 512 * 2, 768 * 2, 121
-height, width, num_frames = 512 * 2, 768 * 2, 121
 dataset_snapshot_download(
     dataset_id="DiffSynth-Studio/examples_in_diffsynth",
     local_dir="./",

examples/ltx2/model_inference/LTX-2-T2AV-IC-LoRA-Detailer.py

@@ -0,0 +1,77 @@
+import torch
+from diffsynth.pipelines.ltx2_audio_video import LTX2AudioVideoPipeline, ModelConfig
+from diffsynth.utils.data.media_io_ltx2 import write_video_audio_ltx2
+from diffsynth.utils.data import VideoData
+from modelscope import dataset_snapshot_download
+
+vram_config = {
+    "offload_dtype": torch.bfloat16,
+    "offload_device": "cpu",
+    "onload_dtype": torch.bfloat16,
+    "onload_device": "cuda",
+    "preparing_dtype": torch.bfloat16,
+    "preparing_device": "cuda",
+    "computation_dtype": torch.bfloat16,
+    "computation_device": "cuda",
+}
+pipe = LTX2AudioVideoPipeline.from_pretrained(
+    torch_dtype=torch.bfloat16,
+    device="cuda",
+    model_configs=[
+        ModelConfig(model_id="google/gemma-3-12b-it-qat-q4_0-unquantized", origin_file_pattern="model-*.safetensors", **vram_config),
+        ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="transformer.safetensors", **vram_config),
+        ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="text_encoder_post_modules.safetensors", **vram_config),
+        ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="video_vae_decoder.safetensors", **vram_config),
+        ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="audio_vae_decoder.safetensors", **vram_config),
+        ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="audio_vocoder.safetensors", **vram_config),
+        ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="video_vae_encoder.safetensors", **vram_config),
+        ModelConfig(model_id="Lightricks/LTX-2", origin_file_pattern="ltx-2-spatial-upscaler-x2-1.0.safetensors", **vram_config),
+    ],
+    tokenizer_config=ModelConfig(model_id="google/gemma-3-12b-it-qat-q4_0-unquantized"),
+    stage2_lora_config=ModelConfig(model_id="Lightricks/LTX-2", origin_file_pattern="ltx-2-19b-distilled-lora-384.safetensors"),
+)
+pipe.load_lora(pipe.dit, ModelConfig(model_id="Lightricks/LTX-2-19b-IC-LoRA-Detailer", origin_file_pattern="ltx-2-19b-ic-lora-detailer.safetensors"))
+dataset_snapshot_download("DiffSynth-Studio/example_video_dataset", allow_file_pattern="ltx2/*", local_dir="data/example_video_dataset")
+
+prompt = "[VISUAL]:Two cute orange cats, wearing boxing gloves, stand on a boxing ring and fight each other. [SOUNDS]:the sound of two cats boxing"
+negative_prompt = (
+    "blurry, out of focus, overexposed, underexposed, low contrast, washed out colors, excessive noise, "
+    "grainy texture, poor lighting, flickering, motion blur, distorted proportions, unnatural skin tones, "
+    "deformed facial features, asymmetrical face, missing facial features, extra limbs, disfigured hands, "
+    "wrong hand count, artifacts around text, inconsistent perspective, camera shake, incorrect depth of "
+    "field, background too sharp, background clutter, distracting reflections, harsh shadows, inconsistent "
+    "lighting direction, color banding, cartoonish rendering, 3D CGI look, unrealistic materials, uncanny "
+    "valley effect, incorrect ethnicity, wrong gender, exaggerated expressions, wrong gaze direction, "
+    "mismatched lip sync, silent or muted audio, distorted voice, robotic voice, echo, background noise, "
+    "off-sync audio, incorrect dialogue, added dialogue, repetitive speech, jittery movement, awkward "
+    "pauses, incorrect timing, unnatural transitions, inconsistent framing, tilted camera, flat lighting, "
+    "inconsistent tone, cinematic oversaturation, stylized filters, or AI artifacts."
+)
+height, width, num_frames = 512 * 2, 768 * 2, 121
+ref_scale_factor = 1
+frame_rate = 24
+# the frame rate of the video should better be the same with the reference video
+# the spatial resolution of the first frame should be the resolution of stage 1 video generation divided by ref_scale_factor
+input_video = VideoData("data/example_video_dataset/ltx2/video1.mp4", height=height // ref_scale_factor // 2, width=width // ref_scale_factor // 2)
+input_video = input_video.raw_data()
+video, audio = pipe(
+    prompt=prompt,
+    negative_prompt=negative_prompt,
+    seed=43,
+    height=height,
+    width=width,
+    num_frames=num_frames,
+    frame_rate=frame_rate,
+    in_context_videos=[input_video],
+    in_context_downsample_factor=ref_scale_factor,
+    tiled=True,
+    use_two_stage_pipeline=True,
+    clear_lora_before_state_two=True,
+)
+write_video_audio_ltx2(
+    video=video,
+    audio=audio,
+    output_path='ltx2_twostage_iclora.mp4',
+    fps=frame_rate,
+    audio_sample_rate=24000,
+)

examples/ltx2/model_inference/LTX-2-T2AV-IC-LoRA-Union-Control.py

@@ -0,0 +1,77 @@
+import torch
+from diffsynth.pipelines.ltx2_audio_video import LTX2AudioVideoPipeline, ModelConfig
+from diffsynth.utils.data.media_io_ltx2 import write_video_audio_ltx2
+from diffsynth.utils.data import VideoData
+from modelscope import dataset_snapshot_download
+
+vram_config = {
+    "offload_dtype": torch.bfloat16,
+    "offload_device": "cpu",
+    "onload_dtype": torch.bfloat16,
+    "onload_device": "cuda",
+    "preparing_dtype": torch.bfloat16,
+    "preparing_device": "cuda",
+    "computation_dtype": torch.bfloat16,
+    "computation_device": "cuda",
+}
+pipe = LTX2AudioVideoPipeline.from_pretrained(
+    torch_dtype=torch.bfloat16,
+    device="cuda",
+    model_configs=[
+        ModelConfig(model_id="google/gemma-3-12b-it-qat-q4_0-unquantized", origin_file_pattern="model-*.safetensors", **vram_config),
+        ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="transformer.safetensors", **vram_config),
+        ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="text_encoder_post_modules.safetensors", **vram_config),
+        ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="video_vae_decoder.safetensors", **vram_config),
+        ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="audio_vae_decoder.safetensors", **vram_config),
+        ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="audio_vocoder.safetensors", **vram_config),
+        ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="video_vae_encoder.safetensors", **vram_config),
+        ModelConfig(model_id="Lightricks/LTX-2", origin_file_pattern="ltx-2-spatial-upscaler-x2-1.0.safetensors", **vram_config),
+    ],
+    tokenizer_config=ModelConfig(model_id="google/gemma-3-12b-it-qat-q4_0-unquantized"),
+    stage2_lora_config=ModelConfig(model_id="Lightricks/LTX-2", origin_file_pattern="ltx-2-19b-distilled-lora-384.safetensors"),
+)
+pipe.load_lora(pipe.dit, ModelConfig(model_id="Lightricks/LTX-2-19b-IC-LoRA-Union-Control", origin_file_pattern="ltx-2-19b-ic-lora-union-control-ref0.5.safetensors"))
+dataset_snapshot_download("DiffSynth-Studio/example_video_dataset", allow_file_pattern="ltx2/*", local_dir="data/example_video_dataset")
+
+prompt = "[VISUAL]:Two cute orange cats, wearing boxing gloves, stand on a boxing ring and fight each other. [SOUNDS]:the sound of two cats boxing"
+negative_prompt = (
+    "blurry, out of focus, overexposed, underexposed, low contrast, washed out colors, excessive noise, "
+    "grainy texture, poor lighting, flickering, motion blur, distorted proportions, unnatural skin tones, "
+    "deformed facial features, asymmetrical face, missing facial features, extra limbs, disfigured hands, "
+    "wrong hand count, artifacts around text, inconsistent perspective, camera shake, incorrect depth of "
+    "field, background too sharp, background clutter, distracting reflections, harsh shadows, inconsistent "
+    "lighting direction, color banding, cartoonish rendering, 3D CGI look, unrealistic materials, uncanny "
+    "valley effect, incorrect ethnicity, wrong gender, exaggerated expressions, wrong gaze direction, "
+    "mismatched lip sync, silent or muted audio, distorted voice, robotic voice, echo, background noise, "
+    "off-sync audio, incorrect dialogue, added dialogue, repetitive speech, jittery movement, awkward "
+    "pauses, incorrect timing, unnatural transitions, inconsistent framing, tilted camera, flat lighting, "
+    "inconsistent tone, cinematic oversaturation, stylized filters, or AI artifacts."
+)
+height, width, num_frames = 512 * 2, 768 * 2, 121
+ref_scale_factor = 2
+frame_rate = 24
+# the frame rate of the video should better be the same with the reference video
+# the spatial resolution of the first frame should be the resolution of stage 1 video generation divided by ref_scale_factor
+input_video = VideoData("data/example_video_dataset/ltx2/depth_video.mp4", height=height // ref_scale_factor // 2, width=width // ref_scale_factor // 2)
+input_video = input_video.raw_data()
+video, audio = pipe(
+    prompt=prompt,
+    negative_prompt=negative_prompt,
+    seed=43,
+    height=height,
+    width=width,
+    num_frames=num_frames,
+    frame_rate=frame_rate,
+    in_context_videos=[input_video],
+    in_context_downsample_factor=ref_scale_factor,
+    tiled=True,
+    use_two_stage_pipeline=True,
+    clear_lora_before_state_two=True,
+)
+write_video_audio_ltx2(
+    video=video,
+    audio=audio,
+    output_path='ltx2_twostage_iclora.mp4',
+    fps=frame_rate,
+    audio_sample_rate=24000,
+)

examples/ltx2/model_inference_low_vram/LTX-2-T2AV-IC-LoRA-Detailer.py

@@ -0,0 +1,77 @@
+import torch
+from diffsynth.pipelines.ltx2_audio_video import LTX2AudioVideoPipeline, ModelConfig
+from diffsynth.utils.data.media_io_ltx2 import write_video_audio_ltx2
+from diffsynth.utils.data import VideoData
+from modelscope import dataset_snapshot_download
+
+vram_config = {
+    "offload_dtype": torch.float8_e5m2,
+    "offload_device": "cpu",
+    "onload_dtype": torch.float8_e5m2,
+    "onload_device": "cpu",
+    "preparing_dtype": torch.float8_e5m2,
+    "preparing_device": "cuda",
+    "computation_dtype": torch.bfloat16,
+    "computation_device": "cuda",
+}
+pipe = LTX2AudioVideoPipeline.from_pretrained(
+    torch_dtype=torch.bfloat16,
+    device="cuda",
+    model_configs=[
+        ModelConfig(model_id="google/gemma-3-12b-it-qat-q4_0-unquantized", origin_file_pattern="model-*.safetensors", **vram_config),
+        ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="transformer.safetensors", **vram_config),
+        ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="text_encoder_post_modules.safetensors", **vram_config),
+        ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="video_vae_decoder.safetensors", **vram_config),
+        ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="audio_vae_decoder.safetensors", **vram_config),
+        ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="audio_vocoder.safetensors", **vram_config),
+        ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="video_vae_encoder.safetensors", **vram_config),
+        ModelConfig(model_id="Lightricks/LTX-2", origin_file_pattern="ltx-2-spatial-upscaler-x2-1.0.safetensors", **vram_config),
+    ],
+    tokenizer_config=ModelConfig(model_id="google/gemma-3-12b-it-qat-q4_0-unquantized"),
+    stage2_lora_config=ModelConfig(model_id="Lightricks/LTX-2", origin_file_pattern="ltx-2-19b-distilled-lora-384.safetensors"),
+)
+pipe.load_lora(pipe.dit, ModelConfig(model_id="Lightricks/LTX-2-19b-IC-LoRA-Detailer", origin_file_pattern="ltx-2-19b-ic-lora-detailer.safetensors"))
+dataset_snapshot_download("DiffSynth-Studio/example_video_dataset", allow_file_pattern="ltx2/*", local_dir="data/example_video_dataset")
+
+prompt = "[VISUAL]:Two cute orange cats, wearing boxing gloves, stand on a boxing ring and fight each other. [SOUNDS]:the sound of two cats boxing"
+negative_prompt = (
+    "blurry, out of focus, overexposed, underexposed, low contrast, washed out colors, excessive noise, "
+    "grainy texture, poor lighting, flickering, motion blur, distorted proportions, unnatural skin tones, "
+    "deformed facial features, asymmetrical face, missing facial features, extra limbs, disfigured hands, "
+    "wrong hand count, artifacts around text, inconsistent perspective, camera shake, incorrect depth of "
+    "field, background too sharp, background clutter, distracting reflections, harsh shadows, inconsistent "
+    "lighting direction, color banding, cartoonish rendering, 3D CGI look, unrealistic materials, uncanny "
+    "valley effect, incorrect ethnicity, wrong gender, exaggerated expressions, wrong gaze direction, "
+    "mismatched lip sync, silent or muted audio, distorted voice, robotic voice, echo, background noise, "
+    "off-sync audio, incorrect dialogue, added dialogue, repetitive speech, jittery movement, awkward "
+    "pauses, incorrect timing, unnatural transitions, inconsistent framing, tilted camera, flat lighting, "
+    "inconsistent tone, cinematic oversaturation, stylized filters, or AI artifacts."
+)
+height, width, num_frames = 512 * 2, 768 * 2, 121
+ref_scale_factor = 1
+frame_rate = 24
+# the frame rate of the video should better be the same with the reference video
+# the spatial resolution of the first frame should be the resolution of stage 1 video generation divided by ref_scale_factor
+input_video = VideoData("data/example_video_dataset/ltx2/video1.mp4", height=height // ref_scale_factor // 2, width=width // ref_scale_factor // 2)
+input_video = input_video.raw_data()
+video, audio = pipe(
+    prompt=prompt,
+    negative_prompt=negative_prompt,
+    seed=43,
+    height=height,
+    width=width,
+    num_frames=num_frames,
+    frame_rate=frame_rate,
+    in_context_videos=[input_video],
+    in_context_downsample_factor=ref_scale_factor,
+    tiled=True,
+    use_two_stage_pipeline=True,
+    clear_lora_before_state_two=True,
+)
+write_video_audio_ltx2(
+    video=video,
+    audio=audio,
+    output_path='ltx2_twostage_iclora.mp4',
+    fps=frame_rate,
+    audio_sample_rate=24000,
+)

examples/ltx2/model_inference_low_vram/LTX-2-T2AV-IC-LoRA-Union-Control.py

@@ -0,0 +1,77 @@
+import torch
+from diffsynth.pipelines.ltx2_audio_video import LTX2AudioVideoPipeline, ModelConfig
+from diffsynth.utils.data.media_io_ltx2 import write_video_audio_ltx2
+from diffsynth.utils.data import VideoData
+from modelscope import dataset_snapshot_download
+
+vram_config = {
+    "offload_dtype": torch.float8_e5m2,
+    "offload_device": "cpu",
+    "onload_dtype": torch.float8_e5m2,
+    "onload_device": "cpu",
+    "preparing_dtype": torch.float8_e5m2,
+    "preparing_device": "cuda",
+    "computation_dtype": torch.bfloat16,
+    "computation_device": "cuda",
+}
+pipe = LTX2AudioVideoPipeline.from_pretrained(
+    torch_dtype=torch.bfloat16,
+    device="cuda",
+    model_configs=[
+        ModelConfig(model_id="google/gemma-3-12b-it-qat-q4_0-unquantized", origin_file_pattern="model-*.safetensors", **vram_config),
+        ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="transformer.safetensors", **vram_config),
+        ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="text_encoder_post_modules.safetensors", **vram_config),
+        ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="video_vae_decoder.safetensors", **vram_config),
+        ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="audio_vae_decoder.safetensors", **vram_config),
+        ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="audio_vocoder.safetensors", **vram_config),
+        ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="video_vae_encoder.safetensors", **vram_config),
+        ModelConfig(model_id="Lightricks/LTX-2", origin_file_pattern="ltx-2-spatial-upscaler-x2-1.0.safetensors", **vram_config),
+    ],
+    tokenizer_config=ModelConfig(model_id="google/gemma-3-12b-it-qat-q4_0-unquantized"),
+    stage2_lora_config=ModelConfig(model_id="Lightricks/LTX-2", origin_file_pattern="ltx-2-19b-distilled-lora-384.safetensors"),
+)
+pipe.load_lora(pipe.dit, ModelConfig(model_id="Lightricks/LTX-2-19b-IC-LoRA-Union-Control", origin_file_pattern="ltx-2-19b-ic-lora-union-control-ref0.5.safetensors"))
+dataset_snapshot_download("DiffSynth-Studio/example_video_dataset", allow_file_pattern="ltx2/*", local_dir="data/example_video_dataset")
+
+prompt = "[VISUAL]:Two cute orange cats, wearing boxing gloves, stand on a boxing ring and fight each other. [SOUNDS]:the sound of two cats boxing"
+negative_prompt = (
+    "blurry, out of focus, overexposed, underexposed, low contrast, washed out colors, excessive noise, "
+    "grainy texture, poor lighting, flickering, motion blur, distorted proportions, unnatural skin tones, "
+    "deformed facial features, asymmetrical face, missing facial features, extra limbs, disfigured hands, "
+    "wrong hand count, artifacts around text, inconsistent perspective, camera shake, incorrect depth of "
+    "field, background too sharp, background clutter, distracting reflections, harsh shadows, inconsistent "
+    "lighting direction, color banding, cartoonish rendering, 3D CGI look, unrealistic materials, uncanny "
+    "valley effect, incorrect ethnicity, wrong gender, exaggerated expressions, wrong gaze direction, "
+    "mismatched lip sync, silent or muted audio, distorted voice, robotic voice, echo, background noise, "
+    "off-sync audio, incorrect dialogue, added dialogue, repetitive speech, jittery movement, awkward "
+    "pauses, incorrect timing, unnatural transitions, inconsistent framing, tilted camera, flat lighting, "
+    "inconsistent tone, cinematic oversaturation, stylized filters, or AI artifacts."
+)
+height, width, num_frames = 512 * 2, 768 * 2, 121
+ref_scale_factor = 2
+frame_rate = 24
+# the frame rate of the video should better be the same with the reference video
+# the spatial resolution of the first frame should be the resolution of stage 1 video generation divided by ref_scale_factor
+input_video = VideoData("data/example_video_dataset/ltx2/depth_video.mp4", height=height // ref_scale_factor // 2, width=width // ref_scale_factor // 2)
+input_video = input_video.raw_data()
+video, audio = pipe(
+    prompt=prompt,
+    negative_prompt=negative_prompt,
+    seed=43,
+    height=height,
+    width=width,
+    num_frames=num_frames,
+    frame_rate=frame_rate,
+    in_context_videos=[input_video],
+    in_context_downsample_factor=ref_scale_factor,
+    tiled=True,
+    use_two_stage_pipeline=True,
+    clear_lora_before_state_two=True,
+)
+write_video_audio_ltx2(
+    video=video,
+    audio=audio,
+    output_path='ltx2_twostage_iclora.mp4',
+    fps=frame_rate,
+    audio_sample_rate=24000,
+)

examples/ltx2/model_training/full/LTX-2-T2AV-splited.sh

@@ -6,7 +6,7 @@ accelerate launch examples/ltx2/model_training/train.py \
   --extra_inputs "input_audio" \
   --height 512 \
   --width 768 \
-  --num_frames 49 \
+  --num_frames 121 \
   --dataset_repeat 1 \
   --model_id_with_origin_paths "DiffSynth-Studio/LTX-2-Repackage:text_encoder_post_modules.safetensors,DiffSynth-Studio/LTX-2-Repackage:video_vae_encoder.safetensors,DiffSynth-Studio/LTX-2-Repackage:audio_vae_encoder.safetensors,google/gemma-3-12b-it-qat-q4_0-unquantized:model-*.safetensors" \
   --learning_rate 1e-4 \
@@ -23,7 +23,7 @@ accelerate launch --config_file examples/qwen_image/model_training/full/accelera
   --extra_inputs "input_audio" \
   --height 512 \
   --width 768 \
-  --num_frames 49 \
+  --num_frames 121 \
   --dataset_repeat 100 \
   --model_id_with_origin_paths "DiffSynth-Studio/LTX-2-Repackage:transformer.safetensors" \
   --learning_rate 1e-4 \

examples/ltx2/model_training/lora/LTX-2-T2AV-IC-LoRA-splited.sh

@@ -0,0 +1,39 @@
+# Splited Training
+accelerate launch examples/ltx2/model_training/train.py \
+  --dataset_base_path data/example_video_dataset/ltx2 \
+  --dataset_metadata_path data/example_video_dataset/ltx2_t2av_iclora.json \
+  --data_file_keys "video,input_audio,in_context_videos" \
+  --extra_inputs "input_audio,in_context_videos,in_context_downsample_factor,frame_rate" \
+  --height 512 \
+  --width 768 \
+  --num_frames 81 \
+  --dataset_repeat 1 \
+  --model_id_with_origin_paths "DiffSynth-Studio/LTX-2-Repackage:text_encoder_post_modules.safetensors,DiffSynth-Studio/LTX-2-Repackage:video_vae_encoder.safetensors,DiffSynth-Studio/LTX-2-Repackage:audio_vae_encoder.safetensors,google/gemma-3-12b-it-qat-q4_0-unquantized:model-*.safetensors" \
+  --learning_rate 1e-4 \
+  --num_epochs 5 \
+  --remove_prefix_in_ckpt "pipe.dit." \
+  --output_path "./models/train/LTX2-T2AV-IC-LoRA-splited-cache" \
+  --lora_base_model "dit" \
+  --lora_target_modules "to_k,to_q,to_v,to_out.0" \
+  --lora_rank 32 \
+  --use_gradient_checkpointing \
+  --task "sft:data_process"
+
+accelerate launch examples/ltx2/model_training/train.py \
+  --dataset_base_path ./models/train/LTX2-T2AV-IC-LoRA-splited-cache \
+  --data_file_keys "video,input_audio,in_context_videos" \
+  --extra_inputs "input_audio,in_context_videos,in_context_downsample_factor,frame_rate" \
+  --height 512 \
+  --width 768 \
+  --num_frames 81 \
+  --dataset_repeat 100 \
+  --model_id_with_origin_paths "DiffSynth-Studio/LTX-2-Repackage:transformer.safetensors" \
+  --learning_rate 1e-4 \
+  --num_epochs 5 \
+  --remove_prefix_in_ckpt "pipe.dit." \
+  --output_path "./models/train/LTX2-T2AV-IC-LoRA" \
+  --lora_base_model "dit" \
+  --lora_target_modules "to_k,to_q,to_v,to_out.0" \
+  --lora_rank 32 \
+  --use_gradient_checkpointing \
+  --task "sft:train"

examples/ltx2/model_training/lora/LTX-2-T2AV-noaudio.sh

@@ -24,7 +24,7 @@ accelerate launch examples/ltx2/model_training/train.py \
   --dataset_metadata_path data/example_video_dataset/ltx2_t2av.csv \
   --height 512 \
   --width 768 \
-  --num_frames 49\
+  --num_frames 121\
   --dataset_repeat 1 \
   --model_id_with_origin_paths "DiffSynth-Studio/LTX-2-Repackage:text_encoder_post_modules.safetensors,DiffSynth-Studio/LTX-2-Repackage:video_vae_encoder.safetensors,DiffSynth-Studio/LTX-2-Repackage:audio_vae_encoder.safetensors,google/gemma-3-12b-it-qat-q4_0-unquantized:model-*.safetensors" \
   --learning_rate 1e-4 \
@@ -42,7 +42,7 @@ accelerate launch examples/ltx2/model_training/train.py \
   --dataset_base_path ./models/train/LTX2-T2AV-noaudio_lora-splited-cache \
   --height 512 \
   --width 768 \
-  --num_frames 49\
+  --num_frames 121\
   --dataset_repeat 100 \
   --model_id_with_origin_paths "DiffSynth-Studio/LTX-2-Repackage:transformer.safetensors" \
   --learning_rate 1e-4 \

examples/ltx2/model_training/lora/LTX-2-T2AV-splited.sh

@@ -27,7 +27,7 @@ accelerate launch examples/ltx2/model_training/train.py \
   --extra_inputs "input_audio" \
   --height 512 \
   --width 768 \
-  --num_frames 49 \
+  --num_frames 121 \
   --dataset_repeat 1 \
   --model_id_with_origin_paths "DiffSynth-Studio/LTX-2-Repackage:text_encoder_post_modules.safetensors,DiffSynth-Studio/LTX-2-Repackage:video_vae_encoder.safetensors,DiffSynth-Studio/LTX-2-Repackage:audio_vae_encoder.safetensors,google/gemma-3-12b-it-qat-q4_0-unquantized:model-*.safetensors" \
   --learning_rate 1e-4 \
@@ -46,7 +46,7 @@ accelerate launch examples/ltx2/model_training/train.py \
   --extra_inputs "input_audio" \
   --height 512 \
   --width 768 \
-  --num_frames 49 \
+  --num_frames 121 \
   --dataset_repeat 100 \
   --model_id_with_origin_paths "DiffSynth-Studio/LTX-2-Repackage:transformer.safetensors" \
   --learning_rate 1e-4 \

examples/ltx2/model_training/train.py

@@ -1,7 +1,6 @@
 import torch, os, argparse, accelerate, warnings
 from diffsynth.core import UnifiedDataset
-from diffsynth.core.data.operators import LoadAudioWithTorchaudio, ToAbsolutePath
-from diffsynth.pipelines.wan_video import WanVideoPipeline, ModelConfig
+from diffsynth.core.data.operators import LoadAudioWithTorchaudio, ToAbsolutePath, RouteByType, SequencialProcess
 from diffsynth.pipelines.ltx2_audio_video import LTX2AudioVideoPipeline, ModelConfig
 from diffsynth.diffusion import *
 os.environ["TOKENIZERS_PARALLELISM"] = "false"
@@ -69,6 +68,7 @@ class LTX2TrainingModule(DiffusionTrainingModule):
             "height": data["video"][0].size[1],
             "width": data["video"][0].size[0],
             "num_frames": len(data["video"]),
+            "frame_rate": data.get("frame_rate", 24),
             # Please do not modify the following parameters
             # unless you clearly know what this will cause.
             "cfg_scale": 1,
@@ -108,24 +108,29 @@ if __name__ == "__main__":
         gradient_accumulation_steps=args.gradient_accumulation_steps,
         kwargs_handlers=[accelerate.DistributedDataParallelKwargs(find_unused_parameters=args.find_unused_parameters)],
     )
+    video_processor = UnifiedDataset.default_video_operator(
+            base_path=args.dataset_base_path,
+            max_pixels=args.max_pixels,
+            height=args.height,
+            width=args.width,
+            height_division_factor=32,
+            width_division_factor=32,
+            num_frames=args.num_frames,
+            time_division_factor=8,
+            time_division_remainder=1,
+        )
     dataset = UnifiedDataset(
         base_path=args.dataset_base_path,
         metadata_path=args.dataset_metadata_path,
         repeat=args.dataset_repeat,
         data_file_keys=args.data_file_keys.split(","),
-        main_data_operator=UnifiedDataset.default_video_operator(
-            base_path=args.dataset_base_path,
-            max_pixels=args.max_pixels,
-            height=args.height,
-            width=args.width,
-            height_division_factor=16,
-            width_division_factor=16,
-            num_frames=args.num_frames,
-            time_division_factor=4,
-            time_division_remainder=1,
-        ),
+        main_data_operator=video_processor,
         special_operator_map={
             "input_audio": ToAbsolutePath(args.dataset_base_path) >> LoadAudioWithTorchaudio(duration=float(args.num_frames) / float(args.frame_rate)),
+            "in_context_videos": RouteByType(operator_map=[
+                (str, video_processor),
+                (list, SequencialProcess(video_processor)),
+            ]),
         }
     )
     model = LTX2TrainingModule(

examples/ltx2/model_training/validate_full/LTX-2-T2AV.py

@@ -27,7 +27,7 @@ pipe = LTX2AudioVideoPipeline.from_pretrained(
 )
 prompt = "A beautiful sunset over the ocean."
 negative_prompt = "blurry, out of focus, overexposed, underexposed, low contrast, washed out colors, excessive noise, grainy texture, poor lighting, flickering, motion blur, distorted proportions, unnatural skin tones, deformed facial features, asymmetrical face, missing facial features, extra limbs, disfigured hands, wrong hand count, artifacts around text, inconsistent perspective, camera shake, incorrect depth of field, background too sharp, background clutter, distracting reflections, harsh shadows, inconsistent lighting direction, color banding, cartoonish rendering, 3D CGI look, unrealistic materials, uncanny valley effect, incorrect ethnicity, wrong gender, exaggerated expressions, wrong gaze direction, mismatched lip sync, silent or muted audio, distorted voice, robotic voice, echo, background noise, off-sync audio, incorrect dialogue, added dialogue, repetitive speech, jittery movement, awkward pauses, incorrect timing, unnatural transitions, inconsistent framing, tilted camera, flat lighting, inconsistent tone, cinematic oversaturation, stylized filters, or AI artifacts."
-height, width, num_frames = 512, 768, 49
+height, width, num_frames = 512, 768, 121
 video, audio = pipe(
     prompt=prompt,
     negative_prompt=negative_prompt,

examples/ltx2/model_training/validate_lora/LTX-2-T2AV-IC-LoRA.py

@@ -0,0 +1,56 @@
+import torch
+from diffsynth.pipelines.ltx2_audio_video import LTX2AudioVideoPipeline, ModelConfig
+from diffsynth.utils.data.media_io_ltx2 import write_video_audio_ltx2
+from diffsynth.utils.data import VideoData
+
+vram_config = {
+    "offload_dtype": torch.bfloat16,
+    "offload_device": "cpu",
+    "onload_dtype": torch.bfloat16,
+    "onload_device": "cuda",
+    "preparing_dtype": torch.bfloat16,
+    "preparing_device": "cuda",
+    "computation_dtype": torch.bfloat16,
+    "computation_device": "cuda",
+}
+pipe = LTX2AudioVideoPipeline.from_pretrained(
+    torch_dtype=torch.bfloat16,
+    device="cuda",
+    model_configs=[
+        ModelConfig(model_id="google/gemma-3-12b-it-qat-q4_0-unquantized", origin_file_pattern="model-*.safetensors", **vram_config),
+        ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="transformer.safetensors", **vram_config),
+        ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="text_encoder_post_modules.safetensors", **vram_config),
+        ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="video_vae_decoder.safetensors", **vram_config),
+        ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="audio_vae_decoder.safetensors", **vram_config),
+        ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="audio_vocoder.safetensors", **vram_config),
+        ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="video_vae_encoder.safetensors", **vram_config),
+    ],
+    tokenizer_config=ModelConfig(model_id="google/gemma-3-12b-it-qat-q4_0-unquantized"),
+)
+pipe.load_lora(pipe.dit, "./models/train/LTX2-T2AV-IC-LoRA/epoch-4.safetensors")
+prompt = "[VISUAL]:Two cute orange cats, wearing boxing gloves, stand on a boxing ring and fight each other. [SOUNDS]:the sound of two cats boxing"
+negative_prompt = "blurry, out of focus, overexposed, underexposed, low contrast, washed out colors, excessive noise, grainy texture, poor lighting, flickering, motion blur, distorted proportions, unnatural skin tones, deformed facial features, asymmetrical face, missing facial features, extra limbs, disfigured hands, wrong hand count, artifacts around text, inconsistent perspective, camera shake, incorrect depth of field, background too sharp, background clutter, distracting reflections, harsh shadows, inconsistent lighting direction, color banding, cartoonish rendering, 3D CGI look, unrealistic materials, uncanny valley effect, incorrect ethnicity, wrong gender, exaggerated expressions, wrong gaze direction, mismatched lip sync, silent or muted audio, distorted voice, robotic voice, echo, background noise, off-sync audio, incorrect dialogue, added dialogue, repetitive speech, jittery movement, awkward pauses, incorrect timing, unnatural transitions, inconsistent framing, tilted camera, flat lighting, inconsistent tone, cinematic oversaturation, stylized filters, or AI artifacts."
+height, width, num_frames = 512, 768, 81
+ref_scale_factor = 2
+frame_rate = 24
+input_video = VideoData("data/example_video_dataset/ltx2/depth_video.mp4", height=height // ref_scale_factor // 2, width=width // ref_scale_factor // 2)
+input_video = input_video.raw_data()
+video, audio = pipe(
+    prompt=prompt,
+    negative_prompt=negative_prompt,
+    seed=43,
+    height=height,
+    width=width,
+    num_frames=num_frames,
+    frame_rate=frame_rate,
+    tiled=True,
+    in_context_videos=[input_video],
+    in_context_downsample_factor=ref_scale_factor,
+)
+write_video_audio_ltx2(
+    video=video,
+    audio=audio,
+    output_path='ltx2_onestage_ic.mp4',
+    fps=frame_rate,
+    audio_sample_rate=24000,
+)

examples/ltx2/model_training/validate_lora/LTX-2-T2AV.py

@@ -28,7 +28,7 @@ pipe = LTX2AudioVideoPipeline.from_pretrained(
 pipe.load_lora(pipe.dit, "models/train/LTX2-T2AV_lora/epoch-4.safetensors")
 prompt = "A beautiful sunset over the ocean."
 negative_prompt = "blurry, out of focus, overexposed, underexposed, low contrast, washed out colors, excessive noise, grainy texture, poor lighting, flickering, motion blur, distorted proportions, unnatural skin tones, deformed facial features, asymmetrical face, missing facial features, extra limbs, disfigured hands, wrong hand count, artifacts around text, inconsistent perspective, camera shake, incorrect depth of field, background too sharp, background clutter, distracting reflections, harsh shadows, inconsistent lighting direction, color banding, cartoonish rendering, 3D CGI look, unrealistic materials, uncanny valley effect, incorrect ethnicity, wrong gender, exaggerated expressions, wrong gaze direction, mismatched lip sync, silent or muted audio, distorted voice, robotic voice, echo, background noise, off-sync audio, incorrect dialogue, added dialogue, repetitive speech, jittery movement, awkward pauses, incorrect timing, unnatural transitions, inconsistent framing, tilted camera, flat lighting, inconsistent tone, cinematic oversaturation, stylized filters, or AI artifacts."
-height, width, num_frames = 512, 768, 49
+height, width, num_frames = 512, 768, 121
 video, audio = pipe(
     prompt=prompt,
     negative_prompt=negative_prompt,

examples/ltx2/model_training/validate_lora/LTX-2-T2AV_noaudio.py

@@ -28,7 +28,7 @@ pipe = LTX2AudioVideoPipeline.from_pretrained(
 pipe.load_lora(pipe.dit, "models/train/LTX2-T2AV-noaudio_lora/epoch-4.safetensors")
 prompt = "A beautiful sunset over the ocean."
 negative_prompt = "blurry, out of focus, overexposed, underexposed, low contrast, washed out colors, excessive noise, grainy texture, poor lighting, flickering, motion blur, distorted proportions, unnatural skin tones, deformed facial features, asymmetrical face, missing facial features, extra limbs, disfigured hands, wrong hand count, artifacts around text, inconsistent perspective, camera shake, incorrect depth of field, background too sharp, background clutter, distracting reflections, harsh shadows, inconsistent lighting direction, color banding, cartoonish rendering, 3D CGI look, unrealistic materials, uncanny valley effect, incorrect ethnicity, wrong gender, exaggerated expressions, wrong gaze direction, mismatched lip sync, silent or muted audio, distorted voice, robotic voice, echo, background noise, off-sync audio, incorrect dialogue, added dialogue, repetitive speech, jittery movement, awkward pauses, incorrect timing, unnatural transitions, inconsistent framing, tilted camera, flat lighting, inconsistent tone, cinematic oversaturation, stylized filters, or AI artifacts."
-height, width, num_frames = 512, 768, 49
+height, width, num_frames = 512, 768, 121
 video, audio = pipe(
     prompt=prompt,
     negative_prompt=negative_prompt,