Instructions to use CompVis/stable-diffusion-v1-4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use CompVis/stable-diffusion-v1-4 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("CompVis/stable-diffusion-v1-4", dtype=torch.bfloat16, device_map="cuda") prompt = "A high tech solarpunk utopia in the Amazon rainforest" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps
- Draw Things
- DiffusionBee
Add non_ema checkpoints
Hey CompVis 👋,
Your model repository seems to contain a non-ema branch to load the unet non-ema checkpoint. Loading non-ema versions from a branch instead of the main branch is deprecated and will eventually be forbidden. Instead, we strongly recommend to save non-ema versions of the model under .non-ema. version files directly on the 'main' branch as enabled through this PR.This PR makes sure that your model repository allows the user to correctly download non-ema unet model weights by adding non-ema unet model weights in both safetensors and PyTorch bin format:
pipe = DiffusionPipeline.from_pretrained("CompVis/stable-diffusion-v1-4", torch_dtype=torch.float16, variant='non_ema')
For more information please have a look at: https://huggingface.co/docs/diffusers/using-diffusers/loading#checkpoint-variants.
We made sure you that you can safely merge this pull request.
Best, the 🧨 Diffusers team.