Instructions to use Fictiverse/Stable_Diffusion_PaperCut_Model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Fictiverse/Stable_Diffusion_PaperCut_Model with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("Fictiverse/Stable_Diffusion_PaperCut_Model", 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
Upscaling
#15
by Omsk13 - opened
This model is fantastic, I'm speechless!
However, it seems to me that the upscaling process does not do justice to the PaperCut creations . I'm creating a video, using deforum, and the upscaling I'm using (realesr-animevideov3) seems to ruin the results a bit. Do you have any advice how to properly upscale the PaperCut creations?
UPDATE: here are the finished results: https://www.youtube.com/watch?v=BCZOD2AQCFg