Instructions to use harmonai/unlocked-250k with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use harmonai/unlocked-250k with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("harmonai/unlocked-250k", 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
Commit ·
c2d1cfe
1
Parent(s): a96589b
Update unet/config.json
Browse files- unet/config.json +1 -1
unet/config.json
CHANGED
|
@@ -35,7 +35,7 @@
|
|
| 35 |
"freq_shift": 0,
|
| 36 |
"in_channels": 2,
|
| 37 |
"mid_block_type": "UNetMidBlock1D",
|
| 38 |
-
"
|
| 39 |
"out_channels": 2,
|
| 40 |
"sample_rate": 16000,
|
| 41 |
"sample_size": 65536,
|
|
|
|
| 35 |
"freq_shift": 0,
|
| 36 |
"in_channels": 2,
|
| 37 |
"mid_block_type": "UNetMidBlock1D",
|
| 38 |
+
"extra_in_channels": 16,
|
| 39 |
"out_channels": 2,
|
| 40 |
"sample_rate": 16000,
|
| 41 |
"sample_size": 65536,
|