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
Zooming in
HI,
Anyone have idea how to stop zooming in, every single clip is zooming in long or short.
Thanks
Same problem, specify in the prompt "No camera movement" or something like that, doesn't really help
I did try all type of prompt " tripod locked-off static camera, zero camera movement", in comfyui and also in desktop app. I did try this CINEMAGRAPH_MOTION lora as well in app. To be honest from like 50 different testes i have maybe 2 clip where there no zoom in. Any advice will be really appreciate it.
I don't usually opt for static shots, but when I do, I always state it as the first descriptor in the prompt and it seems to work.. ex.. "A static shot of a ------... ect.".... haven't tried it with 2.5 yet though.
I don't usually opt for static shots, but when I do, I always state it as the first descriptor in the prompt and it seems to work.. ex.. "A static shot of a ------... ect.".... haven't tried it with 2.5 yet though.
i fif try and still zooming, this are my prompt
"A static shot of Pip standing behind the kitchen worktop, locked-off camera, zero camera movement. Pip looks happily toward the camera and gives a small cheerful wave with one hand. Pip smiles and blinks naturally with subtle breathing and gentle body movement. Keep Pip's appearance, proportions, colors, orange scarf, orange pouch, face, wings and tail consistent. Keep the kitchen, worktop, lighting, framing and background stable and consistent. Smooth natural character animation, polished stylized 3D children's animated-film quality, warm cozy lighting."
input picture and result
Locked Medium Shot, Locked Wide Shot, Camera doesn't move. Add zoom in your negatives and use the static camera lora. https://huggingface.co/Lightricks/LTX-2-19b-LoRA-Camera-Control-Static
It seemed impossible with 2.3, 2.5 works much better. It's almost like these models have never looked across a field or a room to see anything. Everyone is right in your face all the time. Could you imagine if they start making movies this way.