Instructions to use digitalartdynamics/facadelab-diffusion with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use digitalartdynamics/facadelab-diffusion with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("digitalartdynamics/facadelab-diffusion", 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
Ctrl+K
LTX 2.3 transformer-less bundle (B1234): vae+audio_vae+vocoder+text_projection+embeddings_connectors extracted from the vendor 43GB distilled single-file. sha256 14ed39d22ce77350ffdab7d6f31888c0bcbff85201565a2ffe31fd5e61c62611. Serves the FacadeLab q4 GGUF lane (transformer comes from QuantStack). LTX-2 Community License flows down.
031a1b3 verified