Instructions to use jplumail/matthieu-v2-pipe with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use jplumail/matthieu-v2-pipe with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("jplumail/matthieu-v2-pipe", 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
Commit History
end of training. runwayml/stable-diffusion-v1-5. vae from stabilityai/sd-vae-ft-mse. lr=5e-7. 4000 steps. batch size=2. mixed precision. trained text encoder. 1k reg images. 50 instance images. 4b77f27
jplumail commited on