Instructions to use Linaqruf/anything-v3.0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Linaqruf/anything-v3.0 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("Linaqruf/anything-v3.0", 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 Settings
- Draw Things
- DiffusionBee
What happened
I want to continue using anything v3 but today i found out it's gone? I used to use the diffusion branch of this repo but when I came to this repo today (with the README empty and only a couple commits) , I'm not getting the same results from the main branch of this repo. Can anyone explain to me what happened and if there's a way to get back the old anything v3 (like the one a week back)
files are already there @starwarrior
yeah but why doesn't it work like it did?
yeah but why doesn't it work like it did?
what is not working? i tested and it works
Hello @starwarrior ,
Other versions of the model were preserved on this older commit of the Anything-Preservation repo, https://huggingface.co/AdamOswald1/Anything-Preservation/tree/acc67d36406e41252aa936c43248c4ad988db33f.
Oops yea it works fine, I think I wasn't using a VAE or something so it was looking a little weird. Sorry for the scare!