Instructions to use Envvi/Inkpunk-Diffusion with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Envvi/Inkpunk-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("Envvi/Inkpunk-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
Used `Envvi/Inkpunk-Diffusion` as the $MODEL_NAME, did it use v2 ckpt?
#15
by mike-kim-la - opened
Sorry for the dumb question, but if I used Envvi/Inkpunk-Diffusion as the $MODEL_NAME (not the ckpt filename, just the folder path), did it pick up Inkpunk-Diffusion-v2.ckpt to use and not the v1 ckpt which is also in that folder? I see pretrained_model_name_or_path in the source code has some logic, but not sure what it all means. Just being a little OCD or paranoid or whatever.
Thanks!
mike-kim-la changed discussion status to closed