| --- |
| base_model: |
| - PrunaAI/PrunaVAED |
| library_name: diffusers |
| license: other |
| tags: |
| - modular_diffusers |
| - vae |
| - ltx2.3 |
| - text-to-video |
| - lightricks |
| - video-to-video |
| - text-to-audio |
| pipeline_tag: text-to-video |
| --- |
| |
| --- |
|
|
| # Pruna VAE for Modular Diffusers |
|
|
| This repository provides a **[Modular Diffusers](https://huggingface.co/docs/diffusers/modular_diffusers/pipeline_block)** implementation of [PrunaVAED](https://huggingface.co/PrunaAI/PrunaVAED). It packages the optimized video decoder implementation together with the custom loading mechanism required to use |
| the model as a reusable Modular Diffusers component. |
|
|
| The repository exposes a custom `LoadPrunaVAE` block that downloads and instantiates `PrunaAutoencoderKLLTX2Video`, making it available as `components.vae` within a Modular Diffusers pipeline. |
|
|
| ## Installation |
|
|
| Be sure to install pruna, accelerate and diffusers before trying out the model, you can do so with: |
|
|
| ``` |
| pip install pruna accelerate diffusers |
| ``` |
| ## Features |
|
|
| * Custom `PrunaAutoencoderKLLTX2Video` implementation |
| * Compatible with `trust_remote_code=True` |
| * Self-contained repository containing both the implementation and model weights |
| * Intended for composition inside Modular Diffusers pipelines |
|
|
| ## Intended Use |
|
|
| This repository is designed to be consumed by Modular Diffusers pipelines and reusable pipeline blocks. It is particularly useful for: |
|
|
| * Video inference |
| * Modular Diffusers experimentation |
| * Custom video generation pipelines |
| * Research on pruned video VAEs |
|
|
| ## Usage |
|
|
| ```python |
| from diffusers.modular_pipelines import ModularPipelineBlocks |
| |
| blocks = ModularPipelineBlocks.from_pretrained( |
| "AINovice2005/pruna-vaed-modular-diffusers", |
| trust_remote_code=True, |
| ) |
| |
| pipeline = blocks.init_pipeline() |
| pipeline.load_components() |
| |
| vae = pipeline.vae |
| ``` |
|
|
| The loaded component is an instance of: |
|
|
| ```python |
| PrunaAutoencoderKLLTX2Video |
| ``` |
| and can be used anywhere a compatible LTX-2 Video VAE is expected. |
|
|
|
|
| > [!WARNING] |
| > The VAE decoder reconstructs frames from compressed latent representations. |
| > Depending on the downstream workflow, applying a dedicated image or video upscaler after decoding can noticeably improve perceived sharpness and fine detail, particularly for outputs intended for display at higher resolutions. |
|
|
|
|
| ## Acknowledgements |
|
|
| This work builds upon the Pruna VAE implementation released by **[PrunaAI](https://github.com/PrunaAI/pruna)** and adapts it for use as a reusable Modular Diffusers component. |
