Lightricks/LTX-2.3

1---2language:3- en4- de5- es6- fr7- ja8- ko9- zh10- it11- pt12library_name: diffusers13license: other14license_name: ltx-2-community-license-agreement15license_link: https://github.com/Lightricks/LTX-2/blob/main/LICENSE-216pipeline_tag: image-to-video17arxiv: 2601.0323318tags:19- image-to-video20- text-to-video21- video-to-video22- image-text-to-video23- audio-to-video24- text-to-audio25- video-to-audio26- audio-to-audio27- text-to-audio-video28- image-to-audio-video29- image-text-to-audio-video30- ltx-231- ltx-video32- ltxv33- lightricks34- ltx35- ltx-2.336pinned: true37demo: https://app.ltx.studio/ltx-2-playground/i2v38---39 40# LTX-2.3 Model Card41 42This model card focuses on the LTX-2.3 model, which is a significant update to the [LTX-2 model](https://huggingface.co/Lightricks/LTX-2) with improved audio and visual quality as well as enhanced prompt adherence.43LTX-2 was presented in the paper [LTX-2: Efficient Joint Audio-Visual Foundation Model](https://huggingface.co/papers/2601.03233).44 45💻💻 **If you want to dive in right to the code - it is available [here](https://github.com/Lightricks/LTX-2).** 💾💾46 47LTX-2.3 is a DiT-based audio-video foundation model designed to generate synchronized video and audio within a single model. It brings together the core building blocks of modern video generation, with open weights and a focus on practical, local execution. 48 49[![LTX-2 Open Source](ltx2.3-open.png)](https://youtu.be/o-7us-BR_gQ)50 51# Model Checkpoints52 53| Name                               | Notes                                                                                                              |54|------------------------------------|--------------------------------------------------------------------------------------------------------------------|55| ltx-2.3-22b-dev                    | The full model, flexible and trainable in bf16                                                                     |56| ltx-2.3-22b-distilled              | The distilled version of the full model, 8 steps, CFG=1                                                            |57| ltx-2.3-22b-distilled-1.1              | The distilled v1.1 version of the full model, 8 steps, CFG=1 - A different aesthetic experience and improved audio compared to v1.0                                                           |58| ltx-2.3-22b-distilled-lora-384     | A LoRA version of the distilled model applicable to the full model                                                 |59| ltx-2.3-22b-distilled-lora-384-1.1     | A LoRA version of the v1.1 distilled model applicable to the full model                                                 |60| ltx-2.3-spatial-upscaler-x2-1.1    | An x2 spatial upscaler for the ltx-2.3 latents, used in multi stage (multiscale) pipelines for higher resolution   |61| ltx-2.3-spatial-upscaler-x1.5-1.0  | An x1.5 spatial upscaler for the ltx-2.3 latents, used in multi stage (multiscale) pipelines for higher resolution |62| ltx-2.3-temporal-upscaler-x2-1.0   | An x2 temporal upscaler for the ltx-2.3 latents, used in multi stage (multiscale) pipelines for higher FPS         |63 64## Model Details65- **Developed by:** Lightricks66- **Model type:** Diffusion-based audio-video foundation model67- **Language(s):** English68 69# Online demo70LTX-2.3 is accessible right away via the [API Playground](https://console.ltx.video/playground/).71 72# Run locally73 74## Direct use license75You can use the models - full, distilled, upscalers and any derivatives of the models - for purposes under the [license](https://github.com/Lightricks/LTX-2/blob/main/LICENSE).76 77## ComfyUI78We recommend you use the built-in LTXVideo nodes that can be found in the ComfyUI Manager. 79For manual installation information, please refer to our [documentation site](https://docs.ltx.video/open-source-model/integration-tools/comfy-ui).80 81## PyTorch codebase82 83The [LTX-2 codebase](https://github.com/Lightricks/LTX-2) is a monorepo with several packages. From model definition in 'ltx-core' to pipelines in 'ltx-pipelines' and training capabilities in 'ltx-trainer'.84The codebase was tested with Python >=3.12, CUDA version >12.7, and supports PyTorch ~= 2.7.85 86### Installation87 88```bash89git clone https://github.com/Lightricks/LTX-2.git90cd LTX-291 92# From the repository root93uv sync94source .venv/bin/activate95```96 97### Inference98 99To use our model, please follow the instructions in our [ltx-pipelines](https://github.com/Lightricks/LTX-2/blob/main/packages/ltx-pipelines/README.md) package.100 101## Diffusers 🧨102 103LTX-2.3 support in the [Diffusers Python library](https://huggingface.co/docs/diffusers/main/en/index) is coming soon!104 105## General tips:106* Width & height settings must be divisible by 32. Frame count must be divisible by 8 + 1. 107* In case the resolution or number of frames are not divisible by 32 or 8 + 1, the input should be padded with -1 and then cropped to the desired resolution and number of frames.108* For tips on writing effective prompts, please visit our [Prompting guide](https://ltx.video/blog/how-to-prompt-for-ltx-2) 109 110### Limitations111- This model is not intended or able to provide factual information.112- As a statistical model this checkpoint might amplify existing societal biases.113- The model may fail to generate videos that matches the prompts perfectly.114- Prompt following is heavily influenced by the prompting-style.115- The model may generate content that is inappropriate or offensive.116- When generating audio without speech, the audio may be of lower quality.117 118# Train the model119 120The base (dev) model is fully trainable.121 122It's extremely easy to reproduce the LoRAs and IC-LoRAs we publish with the model by following the instructions on the [LTX-2 Trainer Readme](https://github.com/Lightricks/LTX-2/blob/main/packages/ltx-trainer/README.md).123 124Training for motion, style or likeness (sound+appearance) can take less than an hour in many settings.125 126## Citation127 128```bibtex129@article{hacohen2025ltx2,130  title={LTX-2: Efficient Joint Audio-Visual Foundation Model},131  author={HaCohen, Yoav and Brazowski, Benny and Chiprut, Nisan and Bitterman, Yaki and Kvochko, Andrew and Berkowitz, Avishai and Shalem, Daniel and Lifschitz, Daphna and Moshe, Dudu and Porat, Eitan and Richardson, Eitan and Guy Shiran and Itay Chachy and Jonathan Chetboun and Michael Finkelson and Michael Kupchick and Nir Zabari and Nitzan Guetta and Noa Kotler and Ofir Bibi and Ori Gordon and Poriya Panet and Roi Benita and Shahar Armon and Victor Kulikov and Yaron Inger and Yonatan Shiftan and Zeev Melumian and Zeev Farbman},132  journal={arXiv preprint arXiv:2601.03233},133  year={2025}134}135```