Instructions to use waifu-diffusion/wd-1-5-beta with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use waifu-diffusion/wd-1-5-beta with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("waifu-diffusion/wd-1-5-beta", 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
.Bin format for embedding
#4
by afshin2098 - opened
Hi, I can't realize how I should use .bin format. Automatic's webui won't recognize it. I changed the format to .pt and .safetensors but nothing changed. Can I even use these in the web ui?
use it as normal embedding .. .bin is already supported in webui from og era.
Actually the latest diffusers library will ignore all safetensors model if bin model exists.
if is_safetensors_compatible(info):
ignore_patterns.append("*.bin")
else:
# as a safety mechanism we also don't download safetensors if
# not all safetensors files are there
ignore_patterns.append("*.safetensors")