Instructions to use nitrosocke/spider-verse-diffusion with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use nitrosocke/spider-verse-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("nitrosocke/spider-verse-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
- Local Apps
- Draw Things
- DiffusionBee
Question about the ckpt file
#9
by milyiyo - opened
Hi @nitrosocke :)
I want to ask why is common to provide the .ckpt file?
I was thinking that the .ckpt file was like a compressed version that could be loaded for faster inferences.
But every time I search how to do that, the .ckpt file is uncompressed and then are obtained folders like 'unet', 'vae', 'scheduler', etc.
And those folders are used to initiate the pipeline.
Is it only for have a compressed version and allow faster transfers?
Thanks in advance.