Instructions to use Lightricks/LTX-2.5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusion Single File
How to use Lightricks/LTX-2.5 with Diffusion Single File:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- LTX-2
How to use Lightricks/LTX-2.5 with LTX-2:
# Install the LTX-2 pipelines git clone https://github.com/Lightricks/LTX-2.git cd LTX-2 uv sync --extra natten
# Download weights from this repo # Substitute filenames from this repo's "Files and versions" if they differ hf download Lightricks/LTX-2.5 \ diffusion_models/<distilled-transformer>.safetensors \ text_encoders/gemma4-12b-with-proj-ltx-2.5-bf16.safetensors \ vae/<video-vae>.safetensors \ vae/<audio-vae>.safetensors \ latent_upscale_models/<spatial-upsampler>.safetensors \ latent_upscale_models/<temporal-upsampler>.safetensors \ --local-dir models/LTX-2.5 # DFR requires the detailing IC-LoRA (separate repo; strength is fixed at 0.5) hf download Lightricks/LTX-2.5-22b-IC-LoRA-Pixel-Spatial-Upscaler --local-dir models/LTX-2.5-22b-IC-LoRA-Pixel-Spatial-Upscaler# Distilled LTX-2.5 pipeline (fast) uv run python -m ltx_pipelines.distilled \ --transformer-path models/LTX-2.5/diffusion_models/<distilled-transformer>.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/<video-vae>.safetensors \ --audio-vae-path models/LTX-2.5/vae/<audio-vae>.safetensors \ --spatial-upsampler-path models/LTX-2.5/latent_upscale_models/<spatial-upsampler>.safetensors \ --num-frames 121 \ --prompt "A beautiful sunset over the ocean" \ --output-path output.mp4 # For image-to-video, add: --image path/to/image.jpg 0 0.8# DFR pipeline (higher detail fidelity; optional temporal 2x/4x) uv run python -m ltx_pipelines.dfr_pipeline \ --transformer-path models/LTX-2.5/diffusion_models/<distilled-transformer>.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/<video-vae>.safetensors \ --audio-vae-path models/LTX-2.5/vae/<audio-vae>.safetensors \ --spatial-upsampler-path models/LTX-2.5/latent_upscale_models/<spatial-upsampler>.safetensors \ --temporal-upsampler-path models/LTX-2.5/latent_upscale_models/<temporal-upsampler>.safetensors \ --detailing-lora models/LTX-2.5-22b-IC-LoRA-Pixel-Spatial-Upscaler/ltx-2.5-22b-ic-lora-pixel-spatial-upscaler-x2-1.0.safetensors \ --spatial-upscalings 1 \ --temporal-upscalings 1 \ --height 1088 \ --width 1920 \ --num-frames 121 \ --prompt "A beautiful sunset over the ocean" \ --output-path output.mp4 # For 4K: --spatial-upscalings 2 --width 3840 --height 2176 # For image-to-video, add: --image path/to/image.jpg 0 0.8 - Notebooks
- Google Colab
- Kaggle
LTX-2.5 community integration proposal: distilled-control boundaries in a Mac video API
Proposing a community deployment note for the distilled LTX-2.5 MLX Q8 path, separate from the card's CUDA, ComfyUI and Diffusers instructions.
Rapid-MLX exposes asynchronous video jobs and a capabilities endpoint. Its LTX-2.5 tests cover the distilled control surface and packaged-runtime integrity. A community example should use those advertised controls, preserve the 8n+1 frame constraint, and avoid copying guidance/negative-prompt parameters that the selected path rejects.
The model card describes an audio/video system; a completed video file alone would not establish the audio behavior. The final acceptance receipt should include both tracks, dimensions, frame count, exact conversion/runtime and measured memory. This proposal does not resolve the separate ComfyUI Apple Silicon error thread or claim parity with its workflow.
Concrete catalog entry: ltx-2.5-mlx-q8 β MrMofer/ltx-2.5-mlx-q8@f1b56e7dc89f71a9af2cddac787b89ed22a8b7fc. This is a conversion/distribution artifact; it is not presented as an official upstream release.
Source references (fixed Rapid commit): catalog, video API guide, LTX-2.5 contracts.
Verification status: this proposal is based on reading the catalog, implementation and the linked documentation/tests. No fresh model inference or test-suite run was performed for this submission; source tests are not an end-to-end qualification. It requests a community documentation scope, not an official endorsement or a performance listing.
Disclosure: I maintain Rapid-MLX. Prepared with AI assistance under my direction. Anonymous usage-metadata telemetry is enabled by default; DO_NOT_TRACK=1 disables it. The original model and conversion terms continue to apply.