Instructions to use patrickvonplaten/test_sd_1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use patrickvonplaten/test_sd_1 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("patrickvonplaten/test_sd_1", 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
Fix deprecated float16/fp16 variant loading through new `version` API.
#14 opened about 3 years ago
by
patrickvonplaten
Fix deprecation warning by changing `CLIPFeatureExtractor` to `CLIPImageProcessor`.
1
#13 opened about 3 years ago
by
patrickvonplaten
Add `scale_factor` to vae config.
#11 opened over 3 years ago
by
valhalla
Add `clip_sample=False` to scheduler to make model compatible with DDIM.
#10 opened over 3 years ago
by
patrickvonplaten
Add `clip_sample=False` to scheduler to make model compatible with DDIM.
#9 opened over 3 years ago
by
patrickvonplaten
Add `clip_sample=False` to scheduler to make model compatible with DDIM.
#8 opened over 3 years ago
by
patrickvonplaten
Add `clip_sample=False` to scheduler to make model compatible with DDIM.
#7 opened over 3 years ago
by
patrickvonplaten
Correct `sample_size` of Stable Diffusion 1's unet to have correct width and height default
#6 opened over 3 years ago
by
patrickvonplaten
Correct `sample_size` of Stable Diffusion 1's unet to have correct width and height default
#5 opened over 3 years ago
by
patrickvonplaten