update LTX-2.3 doc

[Artiprocher]

No description provided.

[gemini-code-assist]

Summary of Changes

Hello, I'm Gemini Code Assist¹! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!

This pull request focuses on updating the LTX-2 documentation to align with the LTX-2.3 model version. The changes involve adjusting VRAM configurations for improved efficiency, migrating model references to the latest LTX-2.3 checkpoints, and refining the example code for video generation to demonstrate the new model's capabilities and best practices.

Highlights

• VRAM Configuration Update: Updated the vram_config to consistently utilize torch.bfloat16 for offload_dtype, onload_dtype, and preparing_dtype, enhancing memory management efficiency.
• Model Version Migration: Migrated all model references within the example code from LTX-2 to the newer LTX-2.3 checkpoints, including the base model, spatial upscaler, and distilled LoRA configuration.
• Example Code Refinement: Revised the example video generation code by introducing a new, more engaging prompt and leveraging the pipeline's default_negative_prompt for LTX-2.3, along with hardcoded video dimensions and dynamic audio sample rate.
• Documentation Cleanup: Streamlined the documentation by removing extensive commented-out sections related to previous model loading options and a lengthy, hardcoded negative prompt string.

🧠 New Feature in Public Preview: You can now enable Memory to help Gemini Code Assist learn from your team's feedback. This makes future code reviews more consistent and personalized to your project's style. Click here to enable Memory in your admin console.

Using Gemini Code Assist

The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.

Invoking Gemini

You can request assistance from Gemini at any point by creating a comment using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.

Feature	Command	Description
Code Review	/gemini review	Performs a code review for the current pull request in its current state.
Pull Request Summary	/gemini summary	Provides a summary of the current pull request in its current state.
Comment	@gemini-code-assist	Responds in comments when explicitly tagged, both in pull request comments and review comments.
Help	/gemini help	Displays a list of available commands.

Customization

To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.

Limitations & Feedback

Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for GitHub and other Google products, sign up here.

Footnotes

1. Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution. ↩

[gemini-code-assist]

Code Review

This pull request updates the documentation for LTX-2.3 in both English and Chinese versions. The changes simplify the quick start example by using the new LTX-2.3 models and removing obsolete information about repackaged models. The code examples are also improved by using dynamic values for negative prompts and audio sample rates.

I've found one issue where the example code contradicts the documentation regarding VRAM management. I've left comments with suggestions to fix this in both markdown files.

[gemini-code-assist]

The documentation states that "VRAM management has been enabled", but the vram_limit parameter is missing from the LTX2AudioVideoPipeline.from_pretrained call. Without this parameter, VRAM management will be disabled, which could lead to out-of-memory errors for users with limited VRAM. Please add the vram_limit parameter to enable automatic VRAM management as described.

Suggested change

	stage2_lora_config=ModelConfig(model_id="Lightricks/LTX-2.3", origin_file_pattern="ltx-2.3-22b-distilled-lora-384.safetensors"),
	stage2_lora_config=ModelConfig(model_id="Lightricks/LTX-2.3", origin_file_pattern="ltx-2.3-22b-distilled-lora-384.safetensors"),
	vram_limit=torch.cuda.mem_get_info("cuda")[1] / (1024 ** 3) - 0.5,

[gemini-code-assist]

The documentation states that "VRAM management has been enabled", but the vram_limit parameter is missing from the LTX2AudioVideoPipeline.from_pretrained call. Without this parameter, VRAM management will be disabled, which could lead to out-of-memory errors for users with limited VRAM. Please add the vram_limit parameter to enable automatic VRAM management as described.

Suggested change

	stage2_lora_config=ModelConfig(model_id="Lightricks/LTX-2.3", origin_file_pattern="ltx-2.3-22b-distilled-lora-384.safetensors"),
	stage2_lora_config=ModelConfig(model_id="Lightricks/LTX-2.3", origin_file_pattern="ltx-2.3-22b-distilled-lora-384.safetensors"),
	vram_limit=torch.cuda.mem_get_info("cuda")[1] / (1024 ** 3) - 0.5,