Instructions to use jasonshen8848/StudioDiffusion-ip-adapter with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use jasonshen8848/StudioDiffusion-ip-adapter with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("jasonshen8848/StudioDiffusion-ip-adapter", 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
Initial release: 3-platform IP-Adapter weights (Shopify / Etsy / eBay final + Etsy checkpoint-500)
3f45a19 verified | step=250 val_loss=0.058868 wall=97.6s n=65 | |
| step=500 val_loss=0.057593 wall=93.6s n=65 | |
| step=750 val_loss=0.057233 wall=105.5s n=65 | |
| step=1000 val_loss=0.056896 wall=94.4s n=65 | |
| step=1250 val_loss=0.056795 wall=91.6s n=65 | |
| step=1500 val_loss=0.056590 wall=100.5s n=65 | |
| step=1750 val_loss=0.056386 wall=91.5s n=65 | |
| step=2000 val_loss=0.056207 wall=95.1s n=65 | |
| step=2250 val_loss=0.056036 wall=91.6s n=65 | |
| step=2500 val_loss=0.055956 wall=93.9s n=65 | |
| step=2750 val_loss=0.055930 wall=98.3s n=65 | |
| step=3000 val_loss=0.055920 wall=95.7s n=65 | |
| step=3000 val_loss=0.055920 wall=94.2s n=65 | |