Instructions to use nitrosocke/Arcane-Diffusion with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use nitrosocke/Arcane-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/Arcane-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
Version 3
#1
by Norby - opened
Heya!
I saw the announcement for V3 was removed. Is it still coming, or is it discontinued? Thx!:)
Heya!
I saw the announcement for V3 was removed. Is it still coming, or is it discontinued? Thx!:)
Hi there!
It is still planned and technically already finished, but the improvements over the version 2 were very minimal. I wanted to collect a larger dataset to make it more versatile first and I will upload the results once it's finished, so it is worthwhile to download. Right now version 3 would be about the same results.
Thank you for your question!
Great! Thank you for the quick reply!
nitrosocke changed discussion status to closed