Instructions to use OFA-Sys/small-stable-diffusion-v0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use OFA-Sys/small-stable-diffusion-v0 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("OFA-Sys/small-stable-diffusion-v0", 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
Fix outdated steps_offset in scheduler_config
Browse filesUpdating steps_offset from 0 to 1 to resolve FutureWarning in diffusers v0.36.0+. Alternatively, to allow full output quality capacity with minimal noise diffusion in result for current model usage.
scheduler/scheduler_config.json
CHANGED
|
@@ -13,5 +13,6 @@
|
|
| 13 |
"solver_order": 2,
|
| 14 |
"solver_type": "midpoint",
|
| 15 |
"thresholding": false,
|
| 16 |
-
"trained_betas": null
|
| 17 |
-
|
|
|
|
|
|
| 13 |
"solver_order": 2,
|
| 14 |
"solver_type": "midpoint",
|
| 15 |
"thresholding": false,
|
| 16 |
+
"trained_betas": null,
|
| 17 |
+
"steps_offset": 1
|
| 18 |
+
}
|