Instructions to use Lightricks/ltxv-spatial-upscaler-0.9.7 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Lightricks/ltxv-spatial-upscaler-0.9.7 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("Lightricks/ltxv-spatial-upscaler-0.9.7", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
Add the Temporal upscaler
#2
by TheBigBlockPC - opened
For real time AI video generation, a temporal upscaler is very useful to render in 12 FPS but get the results in 24 fps
The model is available here: https://huggingface.co/Lightricks/LTX-Video/blob/main/ltxv-temporal-upscaler-0.9.7.safetensors
I used diffusers and the upscaler pipeline doesn't support loading from a single file