> For clean Markdown of any page, append .md to the page URL. > For a complete documentation index, see https://docs-dev.ltx.io/llms.txt. > For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs-dev.ltx.io/_mcp/server. # Quick Start > Generate your first LTX-2.5 video locally with ComfyUI templates or native Python pipelines. Let's get started generating video with LTX-2.5. ## Choose a Workflow There are two ways to run LTX-2.5 locally. We recommend ComfyUI for the fastest way to go from zero to a generated clip using ready-made LTX-2.5 templates. If you're integrating LTX into code or an automated pipeline, use the **Python pipelines** instead. #### [ComfyUI](#comfyui-quick-start) Node-based editor with ready-made LTX-2.5 templates. The best place to start. #### [Python Pipelines](#pipeline-quick-start) Run LTX-2.5 from the command line or your own code. If you already have a plan in mind, start with the row that matches your input and goal. The Open Source guides describe local workflows; check the [API documentation](/quickstart) for hosted API requests. | You have or want to... | Start here | Scope | | ----------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | Generate video from a text prompt | [Text-to-Video](/open-source-model/usage-guides/text-to-video) | LTX-2.5 ComfyUI template; generates synchronized video and audio. | | Animate one source image, or generate motion between a first and last frame | [Image-to-Video](/open-source-model/usage-guides/image-to-video) | LTX-2.5 ComfyUI template; an image supplies the opening state. | | Generate video timed to an input audio clip | [Audio-to-Video](/open-source-model/usage-guides/audio-to-video) | LTX-2.5 ComfyUI workflow; audio is held fixed and a first image is optional. | | Generate audio only from a text prompt | [Text-to-Audio](/open-source-model/usage-guides/text-to-audio) | LTX-2.5 ComfyUI workflow; no video branch. | | Control, transform, restore, or edit video with a reference input or control signal | [IC-LoRA](/open-source-model/usage-guides/ic-lo-ra) | Use the adapter card and task-specific workflow; see [Workflow & Asset Compatibility](/open-source-model/reference/workflow-asset-compatibility) for starting points. | | Add a prompt-driven style or learned behavior | [LoRAs](/open-source-model/usage-guides/lo-ra) | Standard LoRA path. No general-purpose LTX-2.5 standard-LoRA workflow is currently published. | | Generate Foley for a muted video, or replace dialogue with lip-synced speech | [Foley](/open-source-model/feature-guides/audio/video-to-audio-foley) or [Dub-It](/open-source-model/feature-guides/audio/dub-it-beta) | LTX-2.3 specialized workflows; do not substitute LTX-2.5 assets without compatible-workflow evidence. | | Generate programmatically or fine-tune the model | [PyTorch API](/open-source-model/integration-tools/pytorch-api) or [LTX Trainer](/open-source-model/ltx-trainer/ltx-training) | Native Python / Diffusers, or local training. | --- ## ComfyUI Quick Start ComfyUI provides an intuitive node-based interface with ready-made LTX-2.5 templates. If you haven't installed ComfyUI yet, download it from [comfy.org/download](https://www.comfy.org/download). ### 1. Install the LTX nodes **Recommended: ComfyUI Manager** 1. Launch ComfyUI and open **ComfyUI Manager** 2. Search for **"LTXVideo"** 3. Click **Install** on the `ComfyUI-LTXVideo` node pack 4. Restart ComfyUI **Alternative: Manual installation** ```bash git clone https://github.com/Lightricks/ComfyUI-LTXVideo.git cd ComfyUI-LTXVideo uv sync --frozen source .venv/bin/activate ``` For portable/embedded installations: ```bash .\python_embeded\python.exe -m pip install -r .\ComfyUI\custom_nodes\ComfyUI-LTXVideo\requirements.txt ``` ### 2. Generate your first video 1. Open ComfyUI's **template browser** and pick an LTX-2.5 template (start with Text-to-Video if you're new): * **[Text-to-Video](https://github.com/Comfy-Org/workflow_templates/blob/main/templates/video_ltx2_5_t2v.json)** — generate from a text prompt. * **[Image-to-Video](https://github.com/Comfy-Org/workflow_templates/blob/main/templates/video_ltx2_5_i2v.json)** — animate from a starting image. * **[First-Frame / Last-Frame](https://github.com/Comfy-Org/workflow_templates/blob/main/templates/video_ltx2_5_flf2v.json)** — generate the motion between a start and end frame. 2. When prompted, download the model files the template needs. The **Workflow Overview** panel (or ComfyUI Manager) fetches anything missing. 3. Enter your prompt or add your references image(s). 4. Click **Queue Prompt** to generate. Generation time depends on your GPU and VRAM. #### [ComfyUI Guide](/open-source-model/integration-tools/comfy-ui) Full guide to nodes, workflows, models, and advanced features #### [Text-to-Video](/open-source-model/usage-guides/text-to-video) Walk through the default text-to-video template --- ## Pipeline Quick Start For programmatic use, run LTX-2.5 through the native `ltx-pipelines` package. ### 1. Install ```bash git clone https://github.com/Lightricks/LTX-2.git cd LTX-2 uv sync source .venv/bin/activate ``` ### 2. Download the models LTX-2.5 ships as a **split pack** — one file per component. Grab the files needed; click **Agree and Access** on the [model page](https://huggingface.co/Lightricks/LTX-2.5) on first download: ```bash hf auth login hf download Lightricks/LTX-2.5 \ diffusion_models/ltx-2.5-22b-distilled-transformer-bf16.safetensors \ text_encoders/gemma4-12b-with-proj-ltx-2.5-bf16.safetensors \ vae/ltx-2.5-video-vae-bf16.safetensors \ vae/ltx-2.5-audio-vae-bf16.safetensors \ model_patches/ltx-2.5-duration-head-bf16.safetensors \ latent_upscale_models/ltx-2.5-latent-spatial-upscaler-x2-bf16-1.0.safetensors \ --local-dir models/ltx-2.5 ``` ### 3. Generate ```bash uv run python -m ltx_pipelines.distilled \ --transformer-path models/ltx-2.5/diffusion_models/ltx-2.5-22b-distilled-transformer-bf16.safetensors \ --text-encoder-path models/ltx-2.5/text_encoders/gemma4-12b-with-proj-ltx-2.5-bf16.safetensors \ --video-vae-path models/ltx-2.5/vae/ltx-2.5-video-vae-bf16.safetensors \ --audio-vae-path models/ltx-2.5/vae/ltx-2.5-audio-vae-bf16.safetensors \ --duration-head-path models/ltx-2.5/model_patches/ltx-2.5-duration-head-bf16.safetensors \ --spatial-upsampler-path models/ltx-2.5/latent_upscale_models/ltx-2.5-latent-spatial-upscaler-x2-bf16-1.0.safetensors \ --prompt "A golden retriever running through a sunlit meadow" \ --seed 42 \ --output-path output.mp4 ``` Every pipeline runs the same way from the command line — add `--help` to any module to see its options. #### [PyTorch API](/open-source-model/integration-tools/pytorch-api) All pipelines, parameters, and memory-optimization options --- ## What's Next? Now that you have LTX-2.5 running, explore these guides to get the most out of the model: #### [Prompt Engineering](/open-source-model/usage-guides/prompting-guide) Learn to write prompts that generate exactly what you want #### [Text-to-Video](/open-source-model/usage-guides/text-to-video) Create videos from text descriptions #### [Image-to-Video](/open-source-model/usage-guides/image-to-video) Prompting with images --- ## Getting Help #### [LTX Discord](https://discord.gg/ltxplatform) Get help from the team and community #### [Report Issues](https://github.com/Lightricks/ComfyUI-LTXVideo/issues) Found a bug? Let us know!