Instructions to use Hippotes/NVIDIA-PiD-v1.5-repackages with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Hippotes/NVIDIA-PiD-v1.5-repackages 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/NVIDIA-PiD-v1.5-repackages", 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
PID 1.5 model you converted is the 512_to_2048 version or the 1024_to_4096 version?
#1
by makisekurisu-jp - opened
PID 1.5 model you converted is the 512_to_2048 version or the 1024_to_4096 version?
Nvidia name them "2k to 4k" so you can probably do any res in between
@Hippotes , "2k to 4k" > the input must be 2K, the output must be 4K
No, this is the output resolution. All PiD models are 4x decoder, the v1.5 ones can do anything from 512 -> 2048 to 1024 -> 4096.
see https://huggingface.co/nvidia/PiD#pid-checkpoints.