Instructions to use Fictiverse/Stable_Diffusion_Microscopic_model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Fictiverse/Stable_Diffusion_Microscopic_model with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("Fictiverse/Stable_Diffusion_Microscopic_model", 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
Guide to prompts?
#5
by awefawefa - opened
Are there any guides to prompting with this model besides using the word "microscopic"? I've used it for a bit and it's a very cool model, just hard to get something specific. I'd also be interested to see what else people have created with this model.
Hi, yes it is an old model, i probably overtrained it. Try to merge it with 1.5 to reduce the strength of the "microscopic" token