matrixgame3_i2v_pipeline

Matrix-Game 3.0 I2V pipeline implementation.

fastvideo.pipelines.basic.matrixgame3.matrixgame3_i2v_pipeline.FastVideoArgs

FastVideoArgs(model_path: str, mode: ExecutionMode = ExecutionMode.INFERENCE, workload_type: WorkloadType = WorkloadType.T2V, distributed_executor_backend: str = 'mp', enable_streaming_ipc_queues: bool = False, ray_placement_group: PlacementGroup | None = None, ray_runtime_env: RuntimeEnv | None = None, inference_mode: bool = True, trust_remote_code: bool = False, revision: str | None = None, num_gpus: int = 1, tp_size: int = -1, sp_size: int = -1, hsdp_replicate_dim: int = 1, hsdp_shard_dim: int = -1, dist_timeout: int | None = None, pipeline_config: PipelineConfig = PipelineConfig(), preprocess_config: PreprocessConfig | None = None, lora_path: str | None = None, lora_nickname: str = 'default', lora_strength: float = 1.0, lora_target_modules: list[str] | None = None, output_type: str = 'pil', attention_backend: str | None = None, dit_cpu_offload: bool = True, use_fsdp_inference: bool = False, dit_layerwise_offload: bool = True, text_encoder_cpu_offload: bool = True, image_encoder_cpu_offload: bool = True, vae_cpu_offload: bool = True, pin_cpu_memory: bool = True, h3_sequential_load: bool | None = None, h3_encoder_split: bool | None = None, h3_encoder_nodes: int = -1, h3_encoder_workers: int = 0, video_decode_backend: str = 'h3-vae', taeh3_checkpoint: str | None = None, taeh3_chunk_size: int = 5, h3_vae_nvfp4_decoder: str | None = None, lazy_module_load: bool | None = None, vae_parallel_decode: bool = False, vae_parallel_encode: bool = False, vae_parallel_decode_strategy: str | None = None, enable_torch_compile: bool = False, regional_compile: bool = False, enable_torch_compile_text_encoder: bool = False, enable_torch_compile_vae: bool = False, enable_torch_compile_audio_vae: bool = False, torch_compile_kwargs: dict[str, Any] = dict(), torch_compile_kwargs_dit: dict[str, Any] = dict(), torch_compile_kwargs_text_encoder: dict[str, Any] = dict(), torch_compile_kwargs_vae: dict[str, Any] = dict(), torch_compile_kwargs_audio_vae: dict[str, Any] = dict(), inference_torch_compile: bool = False, h3_vsa_fp4: dict[str, Any] = dict(), disable_autocast: bool = False, VSA_sparsity: float | None = None, VSA_tile_size: int | None = None, moba_config_path: str | None = None, moba_config: dict[str, Any] = dict(), master_port: int | None = None, enable_stage_verification: bool = True, prompt_txt: str | None = None, ltx2_vae_tiling: bool | None = None, ltx2_vae_spatial_tile_size_in_pixels: int | None = None, ltx2_vae_spatial_tile_overlap_in_pixels: int | None = None, ltx2_vae_temporal_tile_size_in_frames: int | None = None, ltx2_vae_temporal_tile_overlap_in_frames: int | None = None, ltx2_initial_latent_path: str | None = None, ltx2_audio_latent_path: str | None = None, refine_enabled: bool | None = None, refine_upsampler_path: str | None = None, refine_transformer_path: str | None = None, refine_lora_path: str | None = None, refine_num_inference_steps: int | None = None, refine_guidance_scale: float | None = None, refine_add_noise: bool | None = None, refine_noise_path: str | None = None, refine_audio_noise_path: str | None = None, ltx2_refine_enabled: bool = False, ltx2_refine_upsampler_path: str | None = None, ltx2_refine_transformer_path: str | None = None, ltx2_refine_lora_path: str | None = None, ltx2_refine_num_inference_steps: int = 3, ltx2_refine_guidance_scale: float = 1.0, ltx2_refine_add_noise: bool = True, ltx2_refine_noise_path: str | None = None, ltx2_refine_audio_noise_path: str | None = None, ltx2_legacy_native_noise_order: bool = False, ltx2_use_distilled_sigmas: bool = True, model_paths: dict[str, str] = dict(), model_loaded: dict[str, bool] = (lambda: {'transformer': True, 'vae': True, 'upsampler': True})(), override_text_encoder_safetensors: str | None = None, override_text_encoder_quant: QuantizationMethods = None, transformer_quant: Any | None = None, override_transformer_cls_name: str | None = None, init_weights_from_safetensors: str = '', init_weights_from_safetensors_2: str = '', override_pipeline_cls_name: str | None = None, boundary_ratio: float | None = 0.875)

fastvideo.pipelines.basic.matrixgame3.matrixgame3_i2v_pipeline.FastVideoArgs.is_output_rank

is_output_rank: bool

Whether this process may materialize user-facing outputs.

This is runtime state assigned by an SPMD executor, not a public configuration field, so dataclass serialization and typed config parsing deliberately ignore it.

fastvideo.pipelines.basic.matrixgame3.matrixgame3_i2v_pipeline.FastVideoArgs.add_cli_args

add_cli_args(parser: FlexibleArgumentParser) -> FlexibleArgumentParser

fastvideo.pipelines.basic.matrixgame3.matrixgame3_i2v_pipeline.FastVideoArgs.from_cli_args

from_cli_args(args: argparse.Namespace) -> FastVideoArgs

fastvideo.pipelines.basic.matrixgame3.matrixgame3_i2v_pipeline.FastVideoArgs.from_kwargs

from_kwargs(**kwargs: Any) -> FastVideoArgs

fastvideo.pipelines.basic.matrixgame3.matrixgame3_i2v_pipeline.FastVideoArgs.check_fastvideo_args

check_fastvideo_args() -> None

Validate inference arguments for consistency

fastvideo.pipelines.basic.matrixgame3.matrixgame3_i2v_pipeline.FastVideoArgs.finalize_device_offload_policy

finalize_device_offload_policy(device_id: int = 0) -> bool

Apply device-local memory policy, then resolve incompatible modes.

fastvideo.pipelines.basic.matrixgame3.matrixgame3_i2v_pipeline.FastVideoArgs.disable_offload_on_unified_memory

disable_offload_on_unified_memory(device_id: int = 0, *, offload_flag: str | None = None) -> bool

Disable host offload after a worker has selected its device.

CUDA's unified-memory probe reads runtime device properties and may initialize a CUDA context. Callers must therefore use this only inside a device-owning process, after selecting and binding device_id. Returning the classification lets direct component-loader callers apply the same policy to explicit per-call overrides. When offload_flag is given, the return value says whether this policy covers that component role.

fastvideo.pipelines.basic.matrixgame3.matrixgame3_i2v_pipeline.init_logger

init_logger(name: str) -> _FastvideoLogger

The main purpose of this function is to ensure that loggers are retrieved in such a way that we can be sure the root fastvideo logger has already been configured.

fastvideo.pipelines.basic.matrixgame3.matrixgame3_i2v_pipeline.FlowUniPCMultistepScheduler

FlowUniPCMultistepScheduler(num_train_timesteps: int = 1000, solver_order: int = 2, prediction_type: str = 'flow_prediction', shift: float | None = 1.0, use_dynamic_shifting = False, thresholding: bool = False, dynamic_thresholding_ratio: float = 0.995, sample_max_value: float = 1.0, predict_x0: bool = True, solver_type: str = 'bh2', lower_order_final: bool = True, disable_corrector: tuple = (), solver_p: SchedulerMixin = None, timestep_spacing: str = 'linspace', steps_offset: int = 0, final_sigmas_type: str | None = 'zero', **kwargs)

UniPCMultistepScheduler is a training-free framework designed for the fast sampling of diffusion models.

This model inherits from [SchedulerMixin] and [ConfigMixin]. Check the superclass documentation for the generic methods the library implements for all schedulers such as loading and saving.

Parameters

num_train_timesteps: `int`, defaults to 1000

The number of diffusion steps to train the model.

solver_order: `int`, default `2`

The UniPC order which can be any positive integer. The effective order of accuracy is solver_order + 1 due to the UniC. It is recommended to use solver_order=2 for guided sampling, and solver_order=3 for unconditional sampling.

prediction_type: `str`, defaults to "flow_prediction"

Prediction type of the scheduler function; must be flow_prediction for this scheduler, which predicts the flow of the diffusion process.

thresholding: `bool`, defaults to `False`

Whether to use the "dynamic thresholding" method. This is unsuitable for latent-space diffusion models such as Stable Diffusion.

dynamic_thresholding_ratio: `float`, defaults to 0.995

The ratio for the dynamic thresholding method. Valid only when thresholding=True.

sample_max_value: `float`, defaults to 1.0

The threshold value for dynamic thresholding. Valid only when thresholding=True and predict_x0=True.

predict_x0: `bool`, defaults to `True`

Whether to use the updating algorithm on the predicted x0.

solver_type: `str`, default `bh2`

Solver type for UniPC. It is recommended to use bh1 for unconditional sampling when steps < 10, and bh2 otherwise.

lower_order_final: `bool`, default `True`

Whether to use lower-order solvers in the final steps. Only valid for < 15 inference steps. This can stabilize the sampling of DPMSolver for steps < 15, especially for steps <= 10.

disable_corrector: `list`, default `[]`

Decides which step to disable the corrector to mitigate the misalignment between epsilon_theta(x_t, c) and epsilon_theta(x_t^c, c) which can influence convergence for a large guidance scale. Corrector is usually disabled during the first few steps.

solver_p: `SchedulerMixin`, default `None`

Any other scheduler that if specified, the algorithm becomes solver_p + UniC.

use_karras_sigmas: `bool`, *optional*, defaults to `False`

Whether to use Karras sigmas for step sizes in the noise schedule during the sampling process. If True, the sigmas are determined according to a sequence of noise levels {σi}.

use_exponential_sigmas: `bool`, *optional*, defaults to `False`

Whether to use exponential sigmas for step sizes in the noise schedule during the sampling process.

timestep_spacing: `str`, defaults to `"linspace"`

The way the timesteps should be scaled. Refer to Table 2 of the Common Diffusion Noise Schedules and Sample Steps are Flawed for more information.

steps_offset: `int`, defaults to 0

An offset added to the inference steps, as required by some model families.

final_sigmas_type: `str`, defaults to `"zero"`

The final sigma value for the noise schedule during the sampling process. If "sigma_min", the final sigma is the same as the last sigma in the training schedule. If zero, the final sigma is set to 0.

fastvideo.pipelines.basic.matrixgame3.matrixgame3_i2v_pipeline.FlowUniPCMultistepScheduler.step_index

step_index

The index counter for current timestep. It will increase 1 after each scheduler step.

fastvideo.pipelines.basic.matrixgame3.matrixgame3_i2v_pipeline.FlowUniPCMultistepScheduler.begin_index

begin_index

The index for the first timestep. It should be set from pipeline with set_begin_index method.

fastvideo.pipelines.basic.matrixgame3.matrixgame3_i2v_pipeline.FlowUniPCMultistepScheduler.set_shift

set_shift(shift: float) -> None

fastvideo.pipelines.basic.matrixgame3.matrixgame3_i2v_pipeline.FlowUniPCMultistepScheduler.set_begin_index

set_begin_index(begin_index: int = 0)

Sets the begin index for the scheduler. This function should be run from pipeline before the inference.

Parameters

begin_index: `int`

The begin index for the scheduler.

fastvideo.pipelines.basic.matrixgame3.matrixgame3_i2v_pipeline.FlowUniPCMultistepScheduler.set_timesteps

set_timesteps(num_inference_steps: int | None = None, device: str | torch.device = None, sigmas: list[float] | None = None, mu: float | None | None = None, shift: float | None | None = None, use_karras_sigmas: bool | None = None, use_kerras_sigma: bool | None = None)

Sets the discrete timesteps used for the diffusion chain (to be run before inference). Args: num_inference_steps (int): Total number of the spacing of the time steps. device (str or torch.device, optional): The device to which the timesteps should be moved to. If None, the timesteps are not moved.

fastvideo.pipelines.basic.matrixgame3.matrixgame3_i2v_pipeline.FlowUniPCMultistepScheduler.time_shift

time_shift(mu: float, sigma: float, t: torch.Tensor)

fastvideo.pipelines.basic.matrixgame3.matrixgame3_i2v_pipeline.FlowUniPCMultistepScheduler.convert_model_output

convert_model_output(model_output: torch.Tensor, *args, sample: torch.Tensor = None, **kwargs) -> torch.Tensor

Convert the model output to the corresponding type the UniPC algorithm needs.

Parameters

model_output: `torch.Tensor`

The direct output from the learned diffusion model.

timestep: `int`

The current discrete timestep in the diffusion chain.

sample: `torch.Tensor`

A current instance of a sample created by the diffusion process.

Returns

torch.Tensor

torch.Tensor: The converted model output.

fastvideo.pipelines.basic.matrixgame3.matrixgame3_i2v_pipeline.FlowUniPCMultistepScheduler.multistep_uni_p_bh_update

multistep_uni_p_bh_update(model_output: torch.Tensor, *args, sample: torch.Tensor = None, order: int | None = None, **kwargs) -> torch.Tensor

One step for the UniP (B(h) version). Alternatively, self.solver_p is used if is specified.

Parameters

model_output: `torch.Tensor`

The direct output from the learned diffusion model at the current timestep.

prev_timestep: `int`

The previous discrete timestep in the diffusion chain.

sample: `torch.Tensor`

A current instance of a sample created by the diffusion process.

order: `int`

The order of UniP at this timestep (corresponds to the p in UniPC-p).

Returns

torch.Tensor

torch.Tensor: The sample tensor at the previous timestep.

fastvideo.pipelines.basic.matrixgame3.matrixgame3_i2v_pipeline.FlowUniPCMultistepScheduler.multistep_uni_c_bh_update

multistep_uni_c_bh_update(this_model_output: torch.Tensor, *args, last_sample: torch.Tensor = None, this_sample: torch.Tensor = None, order: int | None = None, **kwargs) -> torch.Tensor

One step for the UniC (B(h) version).

Parameters

this_model_output: `torch.Tensor`

The model outputs at x_t.

this_timestep: `int`

The current timestep t.

last_sample: `torch.Tensor`

The generated sample before the last predictor x_{t-1}.

this_sample: `torch.Tensor`

The generated sample after the last predictor x_{t}.

order: `int`

The p of UniC-p at this step. The effective order of accuracy should be order + 1.

Returns

torch.Tensor

torch.Tensor: The corrected sample tensor at the current timestep.

fastvideo.pipelines.basic.matrixgame3.matrixgame3_i2v_pipeline.FlowUniPCMultistepScheduler.index_for_timestep

index_for_timestep(timestep, schedule_timesteps = None) -> int

fastvideo.pipelines.basic.matrixgame3.matrixgame3_i2v_pipeline.FlowUniPCMultistepScheduler.step

step(model_output: torch.Tensor, timestep: int | torch.Tensor, sample: torch.Tensor, return_dict: bool = True, generator = None) -> SchedulerOutput | tuple

Predict the sample from the previous timestep by reversing the SDE. This function propagates the sample with the multistep UniPC.

Parameters

model_output: `torch.Tensor`

The direct output from learned diffusion model.

timestep: `int`

The current discrete timestep in the diffusion chain.

sample: `torch.Tensor`

A current instance of a sample created by the diffusion process.

return_dict: `bool`

Whether or not to return a [~schedulers.scheduling_utils.SchedulerOutput] or tuple.

Returns

SchedulerOutput | tuple

[~schedulers.scheduling_utils.SchedulerOutput] or tuple: If return_dict is True, [~schedulers.scheduling_utils.SchedulerOutput] is returned, otherwise a tuple is returned where the first element is the sample tensor.

fastvideo.pipelines.basic.matrixgame3.matrixgame3_i2v_pipeline.FlowUniPCMultistepScheduler.scale_model_input

scale_model_input(sample: torch.Tensor, *args, **kwargs) -> torch.Tensor

Ensures interchangeability with schedulers that need to scale the denoising model input depending on the current timestep.

Parameters

sample: `torch.Tensor`

The input sample.

Returns

torch.Tensor

torch.Tensor: A scaled input sample.

fastvideo.pipelines.basic.matrixgame3.matrixgame3_i2v_pipeline.FlowUniPCMultistepScheduler.add_noise

add_noise(original_samples: torch.Tensor, noise: torch.Tensor, timesteps: torch.IntTensor) -> torch.Tensor

fastvideo.pipelines.basic.matrixgame3.matrixgame3_i2v_pipeline.ComposedPipelineBase

ComposedPipelineBase(model_path: str, fastvideo_args: FastVideoArgs | TrainingArgs, required_config_modules: list[str] | None = None, loaded_modules: dict[str, torch.nn.Module] | None = None)

Base class for pipelines composed of multiple stages.

This class provides the framework for creating pipelines by composing multiple stages together. Each stage is responsible for a specific part of the diffusion process, and the pipeline orchestrates the execution of these stages.

Initialize the pipeline. After init, the pipeline should be ready to use. The pipeline should be stateless and not hold any batch state.

fastvideo.pipelines.basic.matrixgame3.matrixgame3_i2v_pipeline.ComposedPipelineBase.get_hf_download_component_dirs

get_hf_download_component_dirs() -> tuple[str, ...] | None

Return component directories for an opt-in partial Hub download.

fastvideo.pipelines.basic.matrixgame3.matrixgame3_i2v_pipeline.ComposedPipelineBase.get_hf_download_allow_patterns

get_hf_download_allow_patterns() -> list[str] | None

Return Hub patterns for the manifest and selected components.

fastvideo.pipelines.basic.matrixgame3.matrixgame3_i2v_pipeline.ComposedPipelineBase.set_trainable

set_trainable() -> None

fastvideo.pipelines.basic.matrixgame3.matrixgame3_i2v_pipeline.ComposedPipelineBase.post_init

post_init() -> None

fastvideo.pipelines.basic.matrixgame3.matrixgame3_i2v_pipeline.ComposedPipelineBase.initialize_training_pipeline

initialize_training_pipeline(training_args: TrainingArgs)

fastvideo.pipelines.basic.matrixgame3.matrixgame3_i2v_pipeline.ComposedPipelineBase.initialize_validation_pipeline

initialize_validation_pipeline(training_args: TrainingArgs)

fastvideo.pipelines.basic.matrixgame3.matrixgame3_i2v_pipeline.ComposedPipelineBase.from_pretrained

from_pretrained(model_path: str, device: str | None = None, torch_dtype: torch.dtype | None = None, pipeline_config: str | PipelineConfig | None = None, args: argparse.Namespace | None = None, required_config_modules: list[str] | None = None, loaded_modules: dict[str, torch.nn.Module] | None = None, **kwargs) -> ComposedPipelineBase

Load a pipeline from a pretrained model. loaded_modules: Optional[Dict[str, torch.nn.Module]] = None, If provided, loaded_modules will be used instead of loading from config/pretrained weights.

fastvideo.pipelines.basic.matrixgame3.matrixgame3_i2v_pipeline.ComposedPipelineBase.get_module

get_module(module_name: str, default_value: Any = None) -> Any

fastvideo.pipelines.basic.matrixgame3.matrixgame3_i2v_pipeline.ComposedPipelineBase.add_module

add_module(module_name: str, module: Any)

fastvideo.pipelines.basic.matrixgame3.matrixgame3_i2v_pipeline.ComposedPipelineBase.required_config_modules

required_config_modules: list[str]

List of modules that are required by the pipeline. The names should match the diffusers directory and model_index.json file. These modules will be loaded using the PipelineComponentLoader and made available in the modules dictionary. Access these modules using the get_module method.

class ConcretePipeline(ComposedPipelineBase): _required_config_modules = ["vae", "text_encoder", "transformer", "scheduler", "tokenizer"]

@property
def required_config_modules(self):
    return self._required_config_modules

fastvideo.pipelines.basic.matrixgame3.matrixgame3_i2v_pipeline.ComposedPipelineBase.stages

stages: list[PipelineStage]

List of stages in the pipeline.

fastvideo.pipelines.basic.matrixgame3.matrixgame3_i2v_pipeline.ComposedPipelineBase.create_pipeline_stages

create_pipeline_stages(fastvideo_args: FastVideoArgs)

Create the inference pipeline stages.

fastvideo.pipelines.basic.matrixgame3.matrixgame3_i2v_pipeline.ComposedPipelineBase.create_training_stages

create_training_stages(training_args: TrainingArgs)

Create the training pipeline stages.

fastvideo.pipelines.basic.matrixgame3.matrixgame3_i2v_pipeline.ComposedPipelineBase.initialize_pipeline

initialize_pipeline(fastvideo_args: FastVideoArgs)

Initialize the pipeline.

fastvideo.pipelines.basic.matrixgame3.matrixgame3_i2v_pipeline.ComposedPipelineBase.load_modules

load_modules(fastvideo_args: FastVideoArgs, loaded_modules: dict[str, torch.nn.Module] | None = None) -> dict[str, Any]

Load the modules from the config. loaded_modules: Optional[Dict[str, torch.nn.Module]] = None, If provided, loaded_modules will be used instead of loading from config/pretrained weights.

fastvideo.pipelines.basic.matrixgame3.matrixgame3_i2v_pipeline.ComposedPipelineBase.add_stage

add_stage(stage_name: str, stage: PipelineStage)

fastvideo.pipelines.basic.matrixgame3.matrixgame3_i2v_pipeline.ComposedPipelineBase.forward

forward(batch: ForwardBatch, fastvideo_args: FastVideoArgs) -> ForwardBatch

Generate a video or image using the pipeline.

Parameters

batch: ForwardBatch

The batch to generate from.

fastvideo_args: FastVideoArgs

The inference arguments.

Returns: ForwardBatch: The batch with the generated video or image.

fastvideo.pipelines.basic.matrixgame3.matrixgame3_i2v_pipeline.ComposedPipelineBase.train

train() -> None

fastvideo.pipelines.basic.matrixgame3.matrixgame3_i2v_pipeline.ComposedPipelineBase.close

close() -> None

fastvideo.pipelines.basic.matrixgame3.matrixgame3_i2v_pipeline.LoRAPipeline

LoRAPipeline(*args, **kwargs)

Pipeline that supports injecting LoRA adapters into the diffusion transformer. TODO: support training.

fastvideo.pipelines.basic.matrixgame3.matrixgame3_i2v_pipeline.LoRAPipeline.add_module

add_module(module_name: str, module: Any) -> None

fastvideo.pipelines.basic.matrixgame3.matrixgame3_i2v_pipeline.LoRAPipeline.is_target_layer

is_target_layer(module_name: str) -> bool

fastvideo.pipelines.basic.matrixgame3.matrixgame3_i2v_pipeline.LoRAPipeline.convert_adapter_state_dict

convert_adapter_state_dict(state_dict: dict[str, torch.Tensor], lora_path: str) -> dict[str, torch.Tensor]

Rewrite a foreign-layout adapter into the layout the model's name mapping speaks.

The default leaves the adapter alone. Pipelines override it for model families whose published adapters use another naming or fusion scheme, and raise when the adapter is unusable.

fastvideo.pipelines.basic.matrixgame3.matrixgame3_i2v_pipeline.LoRAPipeline.set_trainable

set_trainable() -> None

fastvideo.pipelines.basic.matrixgame3.matrixgame3_i2v_pipeline.LoRAPipeline.convert_to_lora_layers

convert_to_lora_layers() -> None

Unified method to convert the transformer to a LoRA transformer.

fastvideo.pipelines.basic.matrixgame3.matrixgame3_i2v_pipeline.LoRAPipeline.set_lora_adapter

set_lora_adapter(lora_nickname: str, lora_path: str | None = None, strength: float = 1.0, accumulate: bool = False)

Load a LoRA adapter into the pipeline and merge it into the transformer. Args: lora_nickname: The "nick name" of the adapter when referenced in the pipeline. lora_path: The path to the adapter, either a local path or a Hugging Face repo id. strength: Scale for the low-rank adapter. Hybrid adapters must set this at construction so their dense payload receives the same scale. accumulate: Add this adapter to an already merged pure low-rank adapter.

fastvideo.pipelines.basic.matrixgame3.matrixgame3_i2v_pipeline.LoRAPipeline.merge_lora_weights

merge_lora_weights() -> None

Merge LoRA weights, then repack the packed quantized buffers for the merged state.

NVFP4 layers are only supported while their BF16 weight is retained: a purged BF16 weight cannot be unmerged and remerged.

fastvideo.pipelines.basic.matrixgame3.matrixgame3_i2v_pipeline.LoRAPipeline.unmerge_lora_weights

unmerge_lora_weights() -> None

Unmerge LoRA weights, then repack the packed quantized buffers for the unmerged state.

NVFP4 is rejected: its FP4 buffers cannot be rebuilt from a purged BF16 weight.

fastvideo.pipelines.basic.matrixgame3.matrixgame3_i2v_pipeline.ConditioningStage

ConditioningStage()

Stage for applying conditioning to the diffusion process.

This stage handles the application of conditioning, such as classifier-free guidance, to the diffusion process.

fastvideo.pipelines.basic.matrixgame3.matrixgame3_i2v_pipeline.ConditioningStage.forward

forward(batch: ForwardBatch, fastvideo_args: FastVideoArgs) -> ForwardBatch

Apply conditioning to the diffusion process.

Parameters

batch: ForwardBatch

The current batch information.

fastvideo_args: FastVideoArgs

The inference arguments.

Returns

ForwardBatch

The batch with applied conditioning.

fastvideo.pipelines.basic.matrixgame3.matrixgame3_i2v_pipeline.ConditioningStage.verify_input

verify_input(batch: ForwardBatch, fastvideo_args: FastVideoArgs) -> VerificationResult

Verify conditioning stage inputs.

fastvideo.pipelines.basic.matrixgame3.matrixgame3_i2v_pipeline.ConditioningStage.verify_output

verify_output(batch: ForwardBatch, fastvideo_args: FastVideoArgs) -> VerificationResult

Verify conditioning stage outputs.

fastvideo.pipelines.basic.matrixgame3.matrixgame3_i2v_pipeline.DecodingStage

DecodingStage(vae, pipeline = None)

Stage for decoding latent representations into pixel space.

This stage handles the decoding of latent representations into the final output format (e.g., pixel values).

fastvideo.pipelines.basic.matrixgame3.matrixgame3_i2v_pipeline.DecodingStage.verify_input

verify_input(batch: ForwardBatch, fastvideo_args: FastVideoArgs) -> VerificationResult

Verify decoding stage inputs.

fastvideo.pipelines.basic.matrixgame3.matrixgame3_i2v_pipeline.DecodingStage.verify_output

verify_output(batch: ForwardBatch, fastvideo_args: FastVideoArgs) -> VerificationResult

Verify decoding stage outputs.

fastvideo.pipelines.basic.matrixgame3.matrixgame3_i2v_pipeline.DecodingStage.decode

decode(latents: torch.Tensor, fastvideo_args: FastVideoArgs) -> torch.Tensor

Decode latent representations into pixel space using VAE.

Parameters

latents: torch.Tensor

Input latent tensor with shape (batch, channels, frames, height_latents, width_latents)

fastvideo_args: FastVideoArgs

Configuration containing: - disable_autocast: Whether to disable automatic mixed precision (default: False) - pipeline_config.vae_precision: VAE computation precision ("fp32", "fp16", "bf16") - pipeline_config.vae_tiling: Whether to enable VAE tiling for memory efficiency

Returns

torch.Tensor

Decoded video tensor with shape (batch, channels, frames, height, width),

torch.Tensor

normalized to [0, 1] range and moved to CPU as float32

fastvideo.pipelines.basic.matrixgame3.matrixgame3_i2v_pipeline.DecodingStage.streaming_decode

streaming_decode(latents: torch.Tensor, fastvideo_args: FastVideoArgs, cache: list[torch.Tensor | None] | None = None, is_first_chunk: bool = False) -> tuple[torch.Tensor, list[torch.Tensor | None]]

Decode latent representations into pixel space using VAE with streaming cache.

Parameters

latents: torch.Tensor

Input latent tensor with shape (batch, channels, frames, height_latents, width_latents)

fastvideo_args: FastVideoArgs

Configuration object.

cache: list[torch.Tensor | None] | None

VAE cache from previous call, or None to initialize a new cache.

is_first_chunk: bool

Whether this is the first chunk.

Returns

tuple[torch.Tensor, list[torch.Tensor | None]]

A tuple of (decoded_frames, updated_cache).

fastvideo.pipelines.basic.matrixgame3.matrixgame3_i2v_pipeline.DecodingStage.forward

forward(batch: ForwardBatch, fastvideo_args: FastVideoArgs) -> ForwardBatch

Decode latent representations into pixel space.

This method processes the batch through the VAE decoder, converting latent representations to pixel-space video/images. It also optionally decodes trajectory latents for visualization purposes.

Parameters

batch: ForwardBatch

The current batch containing: - latents: Tensor to decode (batch, channels, frames, height_latents, width_latents) - return_trajectory_decoded (optional): Flag to decode trajectory latents - trajectory_latents (optional): Latents at different timesteps - trajectory_timesteps (optional): Corresponding timesteps

fastvideo_args: FastVideoArgs

Configuration containing: - output_type: "latent" to skip decoding, otherwise decode to pixels - vae_cpu_offload: Whether to offload VAE to CPU after decoding - model_loaded: Track VAE loading state - model_paths: Path to VAE model if loading needed

Returns

ForwardBatch

Modified batch with: - output: Decoded frames (batch, channels, frames, height, width) as CPU float32 - trajectory_decoded (if requested): List of decoded frames per timestep

fastvideo.pipelines.basic.matrixgame3.matrixgame3_i2v_pipeline.InputValidationStage

InputValidationStage()

Stage for validating and preparing inputs for diffusion pipelines.

This stage validates that all required inputs are present and properly formatted before proceeding with the diffusion process.

fastvideo.pipelines.basic.matrixgame3.matrixgame3_i2v_pipeline.InputValidationStage.forward

forward(batch: ForwardBatch, fastvideo_args: FastVideoArgs) -> ForwardBatch

Validate and prepare inputs.

Parameters

batch: ForwardBatch

The current batch information.

fastvideo_args: FastVideoArgs

The inference arguments.

Returns

ForwardBatch

The validated batch information.

fastvideo.pipelines.basic.matrixgame3.matrixgame3_i2v_pipeline.InputValidationStage.verify_input

verify_input(batch: ForwardBatch, fastvideo_args: FastVideoArgs) -> VerificationResult

Verify input validation stage inputs.

fastvideo.pipelines.basic.matrixgame3.matrixgame3_i2v_pipeline.InputValidationStage.verify_output

verify_output(batch: ForwardBatch, fastvideo_args: FastVideoArgs) -> VerificationResult

Verify input validation stage outputs.

fastvideo.pipelines.basic.matrixgame3.matrixgame3_i2v_pipeline.LatentPreparationStage

LatentPreparationStage(scheduler, transformer, use_btchw_layout: bool = False)

Stage for preparing initial latent variables for the diffusion process.

This stage handles the preparation of the initial latent variables that will be denoised during the diffusion process.

fastvideo.pipelines.basic.matrixgame3.matrixgame3_i2v_pipeline.LatentPreparationStage.forward

forward(batch: ForwardBatch, fastvideo_args: FastVideoArgs) -> ForwardBatch

Prepare initial latent variables for the diffusion process.

Parameters

batch: ForwardBatch

The current batch information.

fastvideo_args: FastVideoArgs

The inference arguments.

Returns

ForwardBatch

The batch with prepared latent variables.

fastvideo.pipelines.basic.matrixgame3.matrixgame3_i2v_pipeline.LatentPreparationStage.verify_input

verify_input(batch: ForwardBatch, fastvideo_args: FastVideoArgs) -> VerificationResult

Verify latent preparation stage inputs.

fastvideo.pipelines.basic.matrixgame3.matrixgame3_i2v_pipeline.LatentPreparationStage.verify_output

verify_output(batch: ForwardBatch, fastvideo_args: FastVideoArgs) -> VerificationResult

Verify latent preparation stage outputs.

fastvideo.pipelines.basic.matrixgame3.matrixgame3_i2v_pipeline.MatrixGame3DenoisingStage

MatrixGame3DenoisingStage(transformer, scheduler, pipeline = None, transformer_2 = None, vae = None)

fastvideo.pipelines.basic.matrixgame3.matrixgame3_i2v_pipeline.MatrixGame3DenoisingStage.verify_input

verify_input(batch: ForwardBatch, fastvideo_args: FastVideoArgs) -> VerificationResult

fastvideo.pipelines.basic.matrixgame3.matrixgame3_i2v_pipeline.MatrixGame3DenoisingStage.forward

forward(batch: ForwardBatch, fastvideo_args: FastVideoArgs) -> ForwardBatch

fastvideo.pipelines.basic.matrixgame3.matrixgame3_i2v_pipeline.TextEncodingStage

TextEncodingStage(text_encoders, tokenizers)

Stage for encoding text prompts into embeddings for diffusion models.

This stage handles the encoding of text prompts into the embedding space expected by the diffusion model.

Initialize the prompt encoding stage.

Parameters

enable_logging

Whether to enable logging for this stage.

is_secondary

Whether this is a secondary text encoder.

fastvideo.pipelines.basic.matrixgame3.matrixgame3_i2v_pipeline.TextEncodingStage.forward

forward(batch: ForwardBatch, fastvideo_args: FastVideoArgs) -> ForwardBatch

Encode the prompt into text encoder hidden states.

Parameters

batch: ForwardBatch

The current batch information.

fastvideo_args: FastVideoArgs

The inference arguments.

Returns

ForwardBatch

The batch with encoded prompt embeddings.

fastvideo.pipelines.basic.matrixgame3.matrixgame3_i2v_pipeline.TextEncodingStage.verify_input

verify_input(batch: ForwardBatch, fastvideo_args: FastVideoArgs) -> VerificationResult

Verify text encoding stage inputs.

fastvideo.pipelines.basic.matrixgame3.matrixgame3_i2v_pipeline.TextEncodingStage.encode_text

encode_text(text: str | list[str], fastvideo_args: FastVideoArgs, encoder_index: int | list[int] | None = None, return_attention_mask: bool = False, return_type: str = 'list', device: torch.device | str | None = None, dtype: torch.dtype | None = None, max_length: int | Sequence[int | None] | None = None, truncation: bool | None = None, padding: bool | str | None = None)

Encode plain text using selected text encoder(s) and return embeddings.

Parameters

text: str | list[str]

A single string or a list of strings to encode.

fastvideo_args: FastVideoArgs

The inference arguments providing pipeline config, including tokenizer and encoder settings, preprocess and postprocess functions.

encoder_index: int | list[int] | None

Encoder selector by index. Accepts an int or list of ints.

return_attention_mask: bool

If True, also return attention masks for each selected encoder.

return_type: str

"list" (default) returns a list aligned with selection; "dict" returns a dict keyed by encoder index as a string; "stack" stacks along a new first dimension (requires matching shapes).

device: torch.device | str | None

Optional device override for inputs; defaults to local torch device.

dtype: torch.dtype | None

Optional dtype to cast returned embeddings to.

max_length: int | Sequence[int | None] | None

Optional per-call tokenizer override. Either one value applied to every selected encoder (existing behavior), or a sequence with one entry per encoder in encoder_index order -- None at a position falls back to that encoder's own configured default instead of the override.

truncation: bool | None

Optional per-call tokenizer override.

padding: bool | str | None

Optional per-call tokenizer override.

Returns

Depending on return_type and return_attention_mask:

• list: List[Tensor] or (List[Tensor], List[Tensor])

• dict: Dict[str, Tensor] or (Dict[str, Tensor], Dict[str, Tensor])

• stack: Tensor of shape [num_encoders, ...] or a tuple with stacked attention masks

fastvideo.pipelines.basic.matrixgame3.matrixgame3_i2v_pipeline.TextEncodingStage.return_embeds

return_embeds(embeds_list: list[torch.Tensor], attn_masks_list: list[torch.Tensor], return_type: str = 'list', return_attention_mask: bool = False, indices: list[int] | None = None) -> Any

fastvideo.pipelines.basic.matrixgame3.matrixgame3_i2v_pipeline.TextEncodingStage.verify_output

verify_output(batch: ForwardBatch, fastvideo_args: FastVideoArgs) -> VerificationResult

Verify text encoding stage outputs.

fastvideo.pipelines.basic.matrixgame3.matrixgame3_i2v_pipeline.MatrixGame3ImageVAEEncodingStage

MatrixGame3ImageVAEEncodingStage(vae: ParallelTiledVAE)

fastvideo.pipelines.basic.matrixgame3.matrixgame3_i2v_pipeline.MatrixGame3ImageVAEEncodingStage.preprocess

preprocess(image: torch.Tensor | PIL.Image.Image, vae_scale_factor: int, height: int | None = None, width: int | None = None, resize_mode: str = 'crop') -> torch.Tensor

fastvideo.pipelines.basic.matrixgame3.matrixgame3_i2v_pipeline.MatrixGame3ImageVAEEncodingStage.forward

forward(batch: ForwardBatch, fastvideo_args: FastVideoArgs) -> ForwardBatch

fastvideo.pipelines.basic.matrixgame3.matrixgame3_i2v_pipeline.MatrixGame3I2VPipeline

MatrixGame3I2VPipeline(*args, **kwargs)

class MatrixGame3I2VPipeline(LoRAPipeline, ComposedPipelineBase):
    _required_config_modules = ["vae", "transformer", "scheduler", "text_encoder", "tokenizer"]
    _extra_config_module_map = {"vae": "light_vae"}
def initialize_pipeline(self, fastvideo_args: FastVideoArgs):
    self.modules["scheduler"] = FlowUniPCMultistepScheduler(shift=fastvideo_args.pipeline_config.flow_shift)

def create_pipeline_stages(self, fastvideo_args: FastVideoArgs):
    self.add_stage(stage_name="input_validation_stage", stage=InputValidationStage())

    self.add_stage(stage_name="prompt_encoding_stage",
                   stage=TextEncodingStage(
                       text_encoders=[self.get_module("text_encoder")],
                       tokenizers=[self.get_module("tokenizer")],
                   ))

    self.add_stage(stage_name="conditioning_stage", stage=ConditioningStage())

    self.add_stage(stage_name="latent_preparation_stage",
                   stage=LatentPreparationStage(scheduler=self.get_module("scheduler"),
                                                transformer=self.get_module("transformer")))

    self.add_stage(stage_name="image_latent_preparation_stage",
                   stage=MatrixGame3ImageVAEEncodingStage(vae=self.get_module("vae")))

    self.add_stage(stage_name="denoising_stage",
                   stage=MatrixGame3DenoisingStage(transformer=self.get_module("transformer"),
                                                   scheduler=self.get_module("scheduler"),
                                                   pipeline=self,
                                                   vae=self.get_module("vae")))

    self.add_stage(stage_name="decoding_stage", stage=DecodingStage(vae=self.get_module("vae")))

    logger.info(&quot;MatrixGame3I2VPipeline initialized with text, action, and camera support&quot;)</code></pre></details>
fastvideo.pipelines.basic.matrixgame3.matrixgame3_i2v_pipeline.MatrixGame3I2VPipeline.initialize_pipeline
initialize_pipeline(fastvideo_args: FastVideoArgs)
Source
def initialize_pipeline(self, fastvideo_args: FastVideoArgs):
    self.modules["scheduler"] = FlowUniPCMultistepScheduler(shift=fastvideo_args.pipeline_config.flow_shift)
fastvideo.pipelines.basic.matrixgame3.matrixgame3_i2v_pipeline.MatrixGame3I2VPipeline.create_pipeline_stages
create_pipeline_stages(fastvideo_args: FastVideoArgs)
Source
def create_pipeline_stages(self, fastvideo_args: FastVideoArgs):
    self.add_stage(stage_name="input_validation_stage", stage=InputValidationStage())
self.add_stage(stage_name=&quot;prompt_encoding_stage&quot;,
               stage=TextEncodingStage(
                   text_encoders=&#91;self.get_module(&quot;text_encoder&quot;)&#93;,
                   tokenizers=&#91;self.get_module(&quot;tokenizer&quot;)&#93;,
               ))

self.add_stage(stage_name=&quot;conditioning_stage&quot;, stage=ConditioningStage())

self.add_stage(stage_name=&quot;latent_preparation_stage&quot;,
               stage=LatentPreparationStage(scheduler=self.get_module(&quot;scheduler&quot;),
                                            transformer=self.get_module(&quot;transformer&quot;)))

self.add_stage(stage_name=&quot;image_latent_preparation_stage&quot;,
               stage=MatrixGame3ImageVAEEncodingStage(vae=self.get_module(&quot;vae&quot;)))

self.add_stage(stage_name=&quot;denoising_stage&quot;,
               stage=MatrixGame3DenoisingStage(transformer=self.get_module(&quot;transformer&quot;),
                                               scheduler=self.get_module(&quot;scheduler&quot;),
                                               pipeline=self,
                                               vae=self.get_module(&quot;vae&quot;)))

self.add_stage(stage_name=&quot;decoding_stage&quot;, stage=DecodingStage(vae=self.get_module(&quot;vae&quot;)))

logger.info(&quot;MatrixGame3I2VPipeline initialized with text, action, and camera support&quot;)</code></pre></details>