Instructions to use simulationcartridge/ppl with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use simulationcartridge/ppl with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("simulationcartridge/ppl") prompt = "8bit avatar" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
Mirza Učanbarlić commited on
Commit ·
b074d05
1
Parent(s): c058aa4
fix img_str
Browse files- handler.py +1 -1
handler.py
CHANGED
|
@@ -37,7 +37,7 @@ class EndpointHandler():
|
|
| 37 |
# encode image as base 64
|
| 38 |
buffered = BytesIO()
|
| 39 |
image.save(buffered, format="JPEG")
|
| 40 |
-
img_str = base64.b64encode(buffered.getvalue())
|
| 41 |
|
| 42 |
# postprocess the prediction
|
| 43 |
return {"image": img_str}
|
|
|
|
| 37 |
# encode image as base 64
|
| 38 |
buffered = BytesIO()
|
| 39 |
image.save(buffered, format="JPEG")
|
| 40 |
+
img_str = base64.b64encode(buffered.getvalue()).decode('utf-8')
|
| 41 |
|
| 42 |
# postprocess the prediction
|
| 43 |
return {"image": img_str}
|