Instructions to use Hippotes/LTX-2.3-quants with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Hippotes/LTX-2.3-quants with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("Hippotes/LTX-2.3-quants", torch_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
If you want it.
#4
by MrReclusive - opened
Hey, I have a fp4 mixed distilled on civitai.
https://civitai.com/models/2445970?modelVersionId=2751189
If you want to grab it, its the dist fp4 extreme. when i made it only a few things remained at bf16, most was quantized down to fp4, with the few things that fail at fp4 set to fp8 (first and last block also at fp8), it sits at 13gb on gpu while idle.