Instructions to use stabilityai/sd-x2-latent-upscaler with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use stabilityai/sd-x2-latent-upscaler with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("stabilityai/sd-x2-latent-upscaler", 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 ·
12f0a89
1
Parent(s): f27ea45
correct config
Browse files- unet/config.json +1 -1
unet/config.json
CHANGED
|
@@ -38,7 +38,7 @@
|
|
| 38 |
"sample_size": null,
|
| 39 |
"time_cond_proj_dim": 896,
|
| 40 |
"time_embedding_type": "fourier",
|
| 41 |
-
"
|
| 42 |
"up_block_types": [
|
| 43 |
"KCrossAttnUpBlock2D",
|
| 44 |
"KCrossAttnUpBlock2D",
|
|
|
|
| 38 |
"sample_size": null,
|
| 39 |
"time_cond_proj_dim": 896,
|
| 40 |
"time_embedding_type": "fourier",
|
| 41 |
+
"timestep_post_act": "gelu",
|
| 42 |
"up_block_types": [
|
| 43 |
"KCrossAttnUpBlock2D",
|
| 44 |
"KCrossAttnUpBlock2D",
|