`ltx_video` model family

Tasks

Text-to-Video

Supported architectures and task heads

The Hugging Face values below are copied from checkpoint metadata at the recorded revision. The TRTMC task contract comes from the exact E2E recipe. Architecture identity selects or describes a source graph; it does not imply that TRTMC reproduces every Hugging Face head with the same model_type. For example, an encoder recipe may consume the base model and intentionally return hidden states instead of the checkpoint's pretraining or classification logits.

HF `model_type`	HF architecture / pipeline class	TRTMC task contract	Exact recipe profiles
—	`LTXPipeline` Source: `model_index._class_name` Metadata: `model_index.json` at `8984fa25007f`	`diffusion_media_generation`	`ltx-video-l0`

Declared recipes

Each row comes from a model-owned E2E manifest. It declares a test recipe; it is not a live pass receipt for every hardware target.

Recipe	Exact Hugging Face checkpoint	Task	Build configuration	Declared E2E cases	Manifest
`ltx-video-l0`	`Lightricks/LTX-Video`	Text-to-Video	fp16; single device FP32 layers: 24	ltx-video-l0	`tests/e2e/models/ltx_video/manifests/ltx-video-l0.json`

Family-owned configuration

This family does not declare a family-owned --set namespace. Use the explicit CLI options shown below and the shared configuration namespaces documented in Configure Runtime Behavior.

Family-specific CLI contracts

Inputs and options below are filtered by the declared E2E task and the methods and configuration fields used by that family's native runtime implementation. The global CLI parser accepts a wider union of flags; flags absent here are not declared for this family.

`trtmc generate-video`

Generate video frames from a text prompt.

Declared recipes: ltx-video-l0

trtmc generate-video <bundle.bundle> --prompt "<text>" --output <output-dir> [generation options]

Supported input or option	Requirement	Runtime behavior
`--prompt <TEXT>`	Required	Text conditioning input.
`--output <DIR>`	Optional	Directory for generated PNG frames.
`--seed <N>`	Optional	Set the sampling or diffusion seed.
`--num-steps <N>`	Optional	Set the number of diffusion or flow-matching steps.
`--guidance-scale <F>`	Optional	Set classifier-free guidance strength.
`--initial-latents-raw <PATH>`	Optional	Load packed float32 initial latents.

Code basis

Runtime provider: ltx_video

src/cli/main.cpp
include/trtmc/pipeline.h
tests/e2e/models/ltx_video/manifests/ltx-video-l0.json
src/runtime/models/ltx_video/pipeline.cpp
src/runtime/models/ltx_video/pipeline.h

Bundle lifecycle commands

These commands apply to every declared recipe in this family; they do not add task inputs or model capabilities.

`trtmc build`

Build one exact checkpoint into a TensorRT-Model-Connect bundle.

trtmc build <hf-id> --output <bundle.bundle>

`trtmc inspect`

Inspect bundle metadata, runtime identity, and packaged sections.

trtmc inspect <bundle.bundle>

See the CLI Reference for all options and limitations.

ltx_video model family