Instructions to use nitrosocke/Future-Diffusion with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use nitrosocke/Future-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/Future-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
Using the new update from AUTO1111
#6
by KC01 - opened
I can generate images with the new update, but it just don't seem to change the style with or without "future style". Also thank you for all your hard work.
I experienced the same issue. Working on it right now and will update the page or model when i can find the issue.
to use the sd2.0 model in the new automatic you have to have a json file that matches it (see the wikki for the link etc)
Wonder if its a case we need one for future style to work?