[None][feat] Add LTX-2 visual generation example

[yibinl-nvidia]

Description

Adds a minimal LTX-2 text-to-video VisualGen example, including:

• examples/visual_gen/models/ltx2.py for running an LTX-2 generation request.
• examples/visual_gen/configs/ltx2.yaml with the default VisualGen settings for the example.
• README usage documentation for the new example.

Test Coverage

• pre-commit run --files examples/visual_gen/README.md examples/visual_gen/configs/ltx2.yaml examples/visual_gen/models/ltx2.py
• L0 CI will be run through /bot run after the lightweight PR checks are clean for the current head.

PR Checklist

Please review the following before submitting your PR:

• PR description clearly explains what and why. If using CodeRabbit's summary, please make sure it makes sense.

• PR Follows TRT-LLM CODING GUIDELINES to the best of your knowledge.

• Test cases are provided for new code paths (see test instructions)

• If PR introduces API changes, an appropriate PR label is added - either api-compatible or api-breaking. For api-breaking, include BREAKING in the PR title.

• Any new dependencies have been scanned for license and vulnerabilities

• CODEOWNERS updated if ownership changes

• Documentation updated as needed

• Update tava architecture diagram if there is a significant design change in PR.

• The reviewers assigned automatically/manually are appropriate for the PR.

• Please check this after reviewing the above items as appropriate for this PR.

GitHub Bot Help

To see a list of available CI bot commands, please comment /bot help.

[coderabbitai]

📝 Walkthrough

Walkthrough

This PR adds a complete LTX-2 text-to-video example to the VisualGen module. It includes a new YAML configuration file defining LTX-2 defaults, a Python example script that parses CLI arguments, loads configuration, and generates video output, and a README update documenting the new example.

Changes

LTX-2 Visual Generation Example

Layer / File(s)	Summary
LTX-2 Configuration examples/visual_gen/configs/ltx2.yaml	Defines LTX-2 pipeline settings: Gemma text encoder path, attention backend, parallelism configuration (cfg_size and ulysses_size), and CUDA graph execution disabled.
LTX-2 Example Script Implementation examples/visual_gen/models/ltx2.py	Executable example with module docstring and usage instructions, CLI argument parsing for model ID, optional YAML-based visual_gen_args config, optional text_encoder_path override, and output path. Loads VisualGenArgs from YAML when provided and applies encoder path overrides. Configures LTX-2 generation parameters (resolution, frames, FPS, inference steps, guidance scale), executes visual_gen.generate() with a fixed prompt, saves output to file, and includes standard script launcher.
Example Usage Documentation examples/visual_gen/README.md	Documents the new ltx2 example command in the Usage section with the YAML configuration file path.

Estimated code review effort

🎯 2 (Simple) | ⏱️ ~10 minutes

Possibly related PRs

• NVIDIA/TensorRT-LLM#14632: Adds a new slim LTX-2 example and YAML config, replacing a previously removed complex CLI wrapper.

Suggested labels

VisualGen, Doc

Suggested reviewers

• karljang
• chang-l
• venkywonka
• nv-guomingz

🚥 Pre-merge checks | ✅ 4 | ❌ 1

❌ Failed checks (1 warning)

Check name	Status	Explanation	Resolution
Docstring Coverage	⚠️ Warning	Docstring coverage is 0.00% which is insufficient. The required threshold is 80.00%.	Write docstrings for the functions missing them to satisfy the coverage threshold.

✅ Passed checks (4 passed)

Check name	Status	Explanation
Title check	✅ Passed	The title clearly summarizes the main change: adding an LTX-2 visual generation example, which is reflected in all three modified files.
Linked Issues check	✅ Passed	Check skipped because no linked issues were found for this pull request.
Out of Scope Changes check	✅ Passed	Check skipped because no linked issues were found for this pull request.
Description check	✅ Passed	The PR description includes required sections (Description, Test Coverage, PR Checklist) and clearly explains what is being added with minimal but adequate detail for a straightforward example addition.

_{✏️ Tip: You can configure your own custom pre-merge checks in the settings.}

✨ Finishing Touches

🧪 Generate unit tests (beta)

• Create PR with unit tests

---

_{Comment @coderabbitai help to get the list of available commands and usage tips.}

[coderabbitai]

Actionable comments posted: 1

🤖 Prompt for all review comments with AI agents

Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.

Inline comments:
In `@examples/visual_gen/models/ltx2.py`:
- Line 28: The function signature for main lacks a return type annotation;
update the definition of main (def main) to include an explicit return type of
-> None (i.e., change to def main() -> None:) so it conforms to the repo typing
rule that all functions must be annotated and use None for no return value.

🪄 Autofix (Beta)

Fix all unresolved CodeRabbit comments on this PR:

• Push a commit to this branch (recommended)
• Create a new PR with the fixes

---

ℹ️ Review info

⚙️ Run configuration

Configuration used: Path: .coderabbit.yaml

Review profile: CHILL

Plan: Enterprise

Run ID: 6e769eea-3562-44c6-a42e-f39894e75fa3

📥 Commits

Reviewing files that changed from the base of the PR and between 8e5d9e2 and 8355673.

📒 Files selected for processing (3)

• examples/visual_gen/README.md
• examples/visual_gen/configs/ltx2.yaml
• examples/visual_gen/models/ltx2.py

[yibinl-nvidia]

/bot run

[tensorrt-cicd]

PR_Github #52202 [ run ] triggered by Bot. Commit: c80be94 Link to invocation

[yibinl-nvidia]

/bot kill

[tensorrt-cicd]

PR_Github #52236 [ kill ] triggered by Bot. Commit: c80be94 Link to invocation

[tensorrt-cicd]

PR_Github #52202 [ run ] completed with state ABORTED. Commit: c80be94

Link to invocation

[tensorrt-cicd]

PR_Github #52236 [ kill ] completed with state SUCCESS. Commit: c80be94
Successfully killed previous jobs for commit c80be94

Link to invocation

[yibinl-nvidia]

/bot run

[tensorrt-cicd]

PR_Github #52240 [ run ] triggered by Bot. Commit: c80be94 Link to invocation

[yibinl-nvidia]

/bot kill

[tensorrt-cicd]

PR_Github #52304 [ kill ] triggered by Bot. Commit: c80be94 Link to invocation

[tensorrt-cicd]

PR_Github #52304 [ kill ] completed with state SUCCESS. Commit: c80be94
Successfully killed previous jobs for commit c80be94

Link to invocation

[yibinl-nvidia]

/bot run

[tensorrt-cicd]

PR_Github #52309 [ run ] triggered by Bot. Commit: c80be94 Link to invocation

[tensorrt-cicd]

PR_Github #52309 [ run ] completed with state SUCCESS. Commit: c80be94
/LLM/main/L0_MergeRequest_PR pipeline #41615 completed with status: 'SUCCESS'
Pipeline passed with automatic retried tests. Check the rerun report for details.

CI Report

Link to invocation