Instructions to use Fansy/poison with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Fansy/poison with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("Fansy/poison", 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
Basic qestions.
#2
by Corshi - opened
Is this a trained model or model merge?
If trained model, what was the mode it was trained on?
Was it a Dreambooth or a Native Training?
Those questions help to understand the prompts to use, as also the nature of merging it with other models.
Thanks and it does look amazing. Very nice detail on character faces.
Good suggestion , It's finetuned by Dreambooth from anything model, I'll add this msg to README.
Corshi changed discussion status to closed