# LTX Documentation

## Instructions for AI Agents

- For clean Markdown of any page, append `.md` to the page URL
- For section-specific indexes, append `/llms.txt` to any section URL
- For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.ltx.io/_mcp/server

## Docs

- [API Documentation](https://docs.ltx.io/welcome.md): Power your creativity with LTX — an advanced model built for seamless video generation. Access our AI API to create high-quality visual content at scale.
- [Quick Start](https://docs.ltx.io/quickstart.md): Learn how to get started with the LTX API in minutes. This quick start guide walks you through setup, authentication, and your first video generation request.
- [Authentication](https://docs.ltx.io/authentication.md): Understand how to securely authenticate with the LTX API. Follow step-by-step instructions for generating and managing API keys safely.
- [Supported Models](https://docs.ltx.io/models.md): Explore all supported LTX models for text-to-video, image-to-video, and other generation tasks. Learn their capabilities and best use cases.
- [LTX-2.5](https://docs.ltx.io/models/ltx-2-5.md): LTX-2.5 supports text-to-video, image-to-video, and audio-to-video in portrait and landscape — ltx-2-5-fast and ltx-2-5-pro up to 4K.
- [LTX-2.3](https://docs.ltx.io/models/ltx-2-3.md): LTX-2.3 (ltx-2-3-fast, ltx-2-3-pro) supports text-to-video, image-to-video, audio-to-video, retake, and extend at up to 4K.
- [Input Formats](https://docs.ltx.io/input-formats.md): Complete guide to providing image and video inputs to the LTX API. Learn about upload methods, supported formats, codecs, and constraints.
- [Prompting Guide](https://docs.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.
- [Migrate from V1 to V2](https://docs.ltx.io/migrate-v1-to-v2.md): Migrate an LTX API integration from synchronous V1 video generation endpoints to the asynchronous V2 job API.
- [Async Jobs](https://docs.ltx.io/async-jobs.md): Learn how to use the LTX async (V2) API — submit a generation request, poll for status, and retrieve the output. Covers the full job lifecycle, status values, result format, and retention policy.
- [Rate Limits](https://docs.ltx.io/rate-limits.md): Review LTX API rate limits and request quotas. Learn how to optimize your usage and avoid throttling with efficient request management.
- [Error Handling](https://docs.ltx.io/errors.md): Learn how LTX communicates errors and how to handle them gracefully. Includes error codes, response examples, and best practices.
- [Debugging Requests](https://docs.ltx.io/debugging.md): Find out how to debug and troubleshoot API requests in LTX. Includes tips for logging, inspecting responses, and identifying common issues.
- [Pricing](https://docs.ltx.io/pricing.md): Detailed pricing for LTX API video generation endpoints. Understand cost per second based on model, resolution, and endpoint type.
- [Auto Top-Up](https://docs.ltx.io/auto-top-up.md): Configure automatic credit purchases for your organization. Set thresholds and top-up amounts to ensure uninterrupted API usage.
- [LTX Open Source Documentation](https://docs.ltx.io/open-source-model/getting-started/overview.md): Understand LTX-2.5's open-weight local model, its new capabilities, and where to start with local workflows and fine-tuning.
- [Quick Start](https://docs.ltx.io/open-source-model/getting-started/quick-start.md): Generate your first LTX-2.5 video locally with ComfyUI templates or native Python pipelines.
- [System Requirements](https://docs.ltx.io/open-source-model/getting-started/system-requirements.md): Check the GPU, VRAM, CUDA, Python, and disk requirements for running LTX-2.5 locally.
- [Using ComfyUI with LTX](https://docs.ltx.io/open-source-model/integration-tools/comfy-ui.md): Install and run LTX-2.5 in ComfyUI, including LTX nodes, built-in templates, model files, folders, and workflow basics.
- [LTX ComfyUI Nodes](https://docs.ltx.io/open-source-model/integration-tools/ltx-comfy-ui-nodes.md): Reference LTX custom ComfyUI nodes used by LTX-2.3 and LTX-2.5 workflows, including Native HDR, SDR to HDR, Native Resolution tiled sampling, conditioning, audio, and VAE decoding.
- [IC-LoRA Adapters](https://docs.ltx.io/open-source-model/integration-tools/ic-lo-ra-adapters.md): Find LTX's task-specific IC-LoRA adapters for video control, restoration, VFX, and creative transforms, with model cards and compatibility guidance.
- [PyTorch API](https://docs.ltx.io/open-source-model/integration-tools/pytorch-api.md): Integrate LTX-2.5 from Python with native ltx-pipelines or Diffusers, including split model files and generation examples.
- [Overview](https://docs.ltx.io/open-source-model/ltx-trainer/ltx-training.md): Fine-tune LTX with the LTX Trainer, from LoRAs and IC-LoRAs to full multimodal fine-tuning.
- [Quick Start](https://docs.ltx.io/open-source-model/ltx-trainer/quick-start.md): Set up the LTX Trainer and run a first training job, including prerequisites, checkpoint and Gemma encoder setup, and configuration.
- [Training Modes](https://docs.ltx.io/open-source-model/ltx-trainer/training-modes.md): Choose and configure LTX Trainer modes for text, image, video, and audio tasks, including LoRA, IC-LoRA, and full fine-tuning.
- [LoRAs](https://docs.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.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.
- [Text-to-Video Workflow for Beginners](https://docs.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.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.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.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.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.
- [VFX & Post-Production](https://docs.ltx.io/open-source-model/vfx-post-production/overview.md): Choose an LTX VFX and post-production workflow for HDR, refinement, and high-resolution delivery.
- [Working with EXR & HDR](https://docs.ltx.io/open-source-model/vfx-post-production/working-with-exr-hdr.md): Bring production EXR/HDR material through LTX-2.5's Native HDR path in ComfyUI and native Python, and return color-managed EXR and HLG output ready for compositing, grading, and finishing.
- [SDR to HDR](https://docs.ltx.io/open-source-model/vfx-post-production/sdr-to-hdr.md): Convert supported SDR footage into HDR EXR frames and a BT.2020/HLG master with the LTX-2.5 SDR-to-HDR IC-LoRA in ComfyUI or Python.
- [Native Resolution](https://docs.ltx.io/open-source-model/vfx-post-production/native-resolution.md): Use the LTX-2.5 Tiled Fusion workflow in ComfyUI for a full-frame composition pass followed by a tiled pass at the selected output size.
- [Refine & Restore](https://docs.ltx.io/open-source-model/vfx-post-production/refine-and-restore.md): Restore damaged archive footage and rebuild fine detail with LTX IC-LoRAs and the LTX-2.5 Tiled Fusion Upscale workflow in ComfyUI.
- [Video-to-Audio (Foley)](https://docs.ltx.io/open-source-model/feature-guides/audio/video-to-audio-foley.md): Generate synchronized, speech- and music-free Foley for a muted input video, or text-to-audio Foley, with the LTX-2.3 Foley LoRA.
- [Dub-It (IC-LoRA) Beta](https://docs.ltx.io/open-source-model/feature-guides/audio/dub-it-beta.md): Replace dialogue in a source video with lip-synced new speech using the LTX-2.3 Dub-It IC-LoRA beta.
- [Union Control IC-LoRA](https://docs.ltx.io/open-source-model/feature-guides/structural-control/union-control.md): Guide LTX-2.5 video generation with depth, canny, or pose extracted from a reference video via the Union Control IC-LoRA.
- [Motion Control IC-LoRA](https://docs.ltx.io/open-source-model/feature-guides/structural-control/motion-control.md): Direct object motion in LTX-2.5 video generation with sparse motion tracks you draw, using the Motion Control IC-LoRA.
- [Inpainting and Outpainting](https://docs.ltx.io/open-source-model/feature-guides/editing-effects/in-outpainting.md): Fill masked regions or extend the frame of an existing video with the LTX Inpainting and Outpainting IC-LoRA workflows.
- [Relight](https://docs.ltx.io/open-source-model/feature-guides/editing-effects/relight.md): Relight exterior video to a chosen sun direction and hardness with the LTX-2.3 Relight IC-LoRA.
- [Workflow & Asset Compatibility](https://docs.ltx.io/open-source-model/reference/workflow-asset-compatibility.md): Choose a compatible LTX ComfyUI workflow and model stack without mixing LTX-2.3 and LTX-2.5 assets.
- [API Changelog](https://docs.ltx.io/api-changelog/llms.txt)

## API Docs

- API Reference > Video Generation [Generate video from text](https://docs.ltx.io/api-documentation/api-reference/async-video-generation/submit-text-to-video.md)
- API Reference > Video Generation [Generate video from image](https://docs.ltx.io/api-documentation/api-reference/async-video-generation/submit-image-to-video.md)
- API Reference > Video Generation [Generate video from audio](https://docs.ltx.io/api-documentation/api-reference/async-video-generation/submit-audio-to-video.md)
- API Reference > Video Generation [Retake video section](https://docs.ltx.io/api-documentation/api-reference/async-video-generation/submit-retake.md)
- API Reference > Video Generation [Extend video duration](https://docs.ltx.io/api-documentation/api-reference/async-video-generation/submit-extend.md)
- API Reference > Video Generation [Upscale video to HDR](https://docs.ltx.io/api-documentation/api-reference/async-video-generation/submit-video-to-video-hdr.md)
- API Reference > Video Generation [Reframe a video to a new resolution](https://docs.ltx.io/api-documentation/api-reference/async-video-generation/submit-video-to-video-reframe.md)
- API Reference > Video Generation [Get job status](https://docs.ltx.io/api-documentation/api-reference/async-video-generation/get-job-status.md)
- API Reference > Legacy Video Generation [Generate video from text](https://docs.ltx.io/api-documentation/api-reference/video-generation/text-to-video.md)
- API Reference > Legacy Video Generation [Generate video from image](https://docs.ltx.io/api-documentation/api-reference/video-generation/image-to-video.md)
- API Reference > Legacy Video Generation [Generate video from audio](https://docs.ltx.io/api-documentation/api-reference/video-generation/audio-to-video.md)
- API Reference > Legacy Video Generation [Retake video section](https://docs.ltx.io/api-documentation/api-reference/video-generation/retake.md)
- API Reference > Legacy Video Generation [Extend video duration](https://docs.ltx.io/api-documentation/api-reference/video-generation/extend.md)
- API Reference > Upload [Upload file](https://docs.ltx.io/api-documentation/api-reference/upload/create-upload.md)

## OpenAPI Specification

The raw OpenAPI 3.1 specification for this API is available at:
- [OpenAPI JSON](https://docs.ltx.io/openapi.json)
- [OpenAPI YAML](https://docs.ltx.io/openapi.yaml)