Instructions to use coder119/Vectorartz_Diffusion with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use coder119/Vectorartz_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("coder119/Vectorartz_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
How to get actual, scalable vector images?
#9
by lordmuggins - opened
I love what this is able to produce but I'd like to get them exported as actual vectors so as to be scalable. Any ideas how I would go about this? Using Stable Difussion. (Note, that extensions using Potrace do not allow color)
I think what you need to do is use an image editor tool such as Illustrator, Inkscape etc. This will allow you to trace the vectors using functions present in those tools. I am not totally sure how to do that. You may need to check online tutorials. I think there are ways to trace vectors efficiently.
This model produces images that are vector-like but that is still a raster image. So, tracing is the only option I believe to get a vector out of these images.