Instructions to use glowforge-dev/stable-diffusion-2-1-base-custom with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use glowforge-dev/stable-diffusion-2-1-base-custom with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("glowforge-dev/stable-diffusion-2-1-base-custom", 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
Commit History
-
Don't pass image to text pipeline
c4216a4 -
Add the get back in
b566466 -
a paren
62afbc9 -
Change how we read the png image
e1f2a46 -
Update handler for img2img
e757853
-
Add random seeding if specified and train pipeline on base model
9c175fd
-
Remove unnecessary Image imports
e30d596 -
Update handler for testing
418fd63 -
Update prompt handling
19d79cd -
Add encoding logic and remove image decoding logic
1828bb0 -
Adjust base64 encoding logic
0ece009 -
Switch to PIL image processing
fb68c01
-
Add custom handler for GF model
fe706b1 -
Duplicate from stabilityai/stable-diffusion-2-1-base
Co-authored-by: Robin Rombach <rromb@users.noreply.huggingface.co>6931adf