> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs-dev.ltx.io/open-source-model/usage-guides/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs-dev.ltx.io/_mcp/server.

# Usage Guides

## Docs

- [LoRAs](https://docs-dev.ltx.io/open-source-model/usage-guides/lo-ra.md): Apply compatible standard LoRAs to LTX-2.5 ComfyUI templates: choose a workflow, set strength, and combine adapters safely.
- [IC-LoRA](https://docs-dev.ltx.io/open-source-model/usage-guides/ic-lo-ra.md): Run LTX IC-LoRA adapters on LTX-2.5 in ComfyUI — reference-conditioned video-to-video for control, restoration, VFX, and creative transforms.
- [Prompting Guide](https://docs-dev.ltx.io/api-documentation/implementation-guides/prompting-guide.md): LTX prompt-writing guidance: shot, action, camera, and audio structure; LTX-2.5 multi-shot prompts; and local prompt-enhancer guidance.
- [Text-to-Video Workflow for Beginners](https://docs-dev.ltx.io/open-source-model/usage-guides/text-to-video.md): Generate a video with synchronized audio from a text prompt using the built-in LTX-2.5 Text-to-Video ComfyUI template.
- [Image-to-Video Workflow for Beginners](https://docs-dev.ltx.io/open-source-model/usage-guides/image-to-video.md): Animate a source image with the LTX-2.5 Image-to-Video ComfyUI template, including first-and-last-frame generation.
- [Audio-to-Video](https://docs-dev.ltx.io/open-source-model/usage-guides/audio-to-video.md): Generate video timed to an input audio track with the LTX-2.5 Audio-to-Video ComfyUI workflow, with optional first-frame conditioning.
- [Text-to-Audio Workflow](https://docs-dev.ltx.io/open-source-model/usage-guides/text-to-audio.md): Generate audio from a text prompt with the LTX-2.5 audio-only ComfyUI workflow, without a video branch.
- [Two-Stage Generation](https://docs-dev.ltx.io/open-source-model/usage-guides/two-stage-generation.md): Run the advanced LTX-2.5 two-stage ComfyUI workflow: base generation followed by a 2× upscale-and-refine pass.