Instructions to use fal/SeedVR2-7B-FlashPack with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use fal/SeedVR2-7B-FlashPack with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("fal/SeedVR2-7B-FlashPack", 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 dit/config.json
Browse files- dit/config.json +1 -1
dit/config.json
CHANGED
|
@@ -40,7 +40,7 @@
|
|
| 40 |
"mmdit_sr",
|
| 41 |
"mmdit_sr"
|
| 42 |
],
|
| 43 |
-
"dtype": "
|
| 44 |
"emb_dim": 18432,
|
| 45 |
"expand_ratio": 4,
|
| 46 |
"head_dim": 128,
|
|
|
|
| 40 |
"mmdit_sr",
|
| 41 |
"mmdit_sr"
|
| 42 |
],
|
| 43 |
+
"dtype": "bfloat16",
|
| 44 |
"emb_dim": 18432,
|
| 45 |
"expand_ratio": 4,
|
| 46 |
"head_dim": 128,
|