Instructions to use hakurei/waifu-diffusion with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use hakurei/waifu-diffusion with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("hakurei/waifu-diffusion", 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
Commit ·
b5f06b8
1
Parent(s): b8e2b62
Add `steps_offset=1` to config to suppress deprecation warning
Browse filesHey Waifu-Diffusion!
We have introduced a `steps_offset` variable to scheduler configs to have a cleaner API and now want to incentivize SD schedulers to add this to the config as otherwise it'll eventually lead to silent errors.
See: https://github.com/huggingface/diffusers/blob/7258dc4943e73b8799003771e86a44424afb996d/src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion.py#L60
Best,
Diffusers Team!
scheduler/scheduler_config.json
CHANGED
|
@@ -8,5 +8,6 @@
|
|
| 8 |
"num_train_timesteps": 1000,
|
| 9 |
"set_alpha_to_one": false,
|
| 10 |
"timestep_values": null,
|
| 11 |
-
"trained_betas": null
|
|
|
|
| 12 |
}
|
|
|
|
| 8 |
"num_train_timesteps": 1000,
|
| 9 |
"set_alpha_to_one": false,
|
| 10 |
"timestep_values": null,
|
| 11 |
+
"trained_betas": null,
|
| 12 |
+
"steps_offset": 1
|
| 13 |
}
|