Instructions to use jadechoghari/spad with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use jadechoghari/spad with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("jadechoghari/spad", 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
Update unet/mv_attention.py
Browse files- unet/mv_attention.py +2 -2
unet/mv_attention.py
CHANGED
|
@@ -18,7 +18,7 @@ def conv_nd(dims, *args, **kwargs):
|
|
| 18 |
raise ValueError(f"unsupported dimensions: {dims}")
|
| 19 |
|
| 20 |
|
| 21 |
-
from
|
| 22 |
|
| 23 |
try:
|
| 24 |
import xformers
|
|
@@ -364,4 +364,4 @@ if __name__ == "__main__":
|
|
| 364 |
).cuda(),
|
| 365 |
torch.randn(n_objects, n_views, 6, 32, 32).cuda(),
|
| 366 |
]
|
| 367 |
-
x_post = spt_post(x, context=context)
|
|
|
|
| 18 |
raise ValueError(f"unsupported dimensions: {dims}")
|
| 19 |
|
| 20 |
|
| 21 |
+
from attention import *
|
| 22 |
|
| 23 |
try:
|
| 24 |
import xformers
|
|
|
|
| 364 |
).cuda(),
|
| 365 |
torch.randn(n_objects, n_views, 6, 32, 32).cuda(),
|
| 366 |
]
|
| 367 |
+
x_post = spt_post(x, context=context)
|