Instructions to use noguchis/viewdiff_train_teddybear with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use noguchis/viewdiff_train_teddybear with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("noguchis/viewdiff_train_teddybear", torch_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 README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,17 @@
|
|
| 1 |
---
|
| 2 |
license: cc-by-nc-sa-4.0
|
| 3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
license: cc-by-nc-sa-4.0
|
| 3 |
---
|
| 4 |
+
|
| 5 |
+
```bash
|
| 6 |
+
export CO3DV2_DATASET_ROOT=$(pwd)/co3d/dataset
|
| 7 |
+
CUDA_VISIBLE_DEVICES=1 python -m viewdiff.convert_checkpoint_to_model
|
| 8 |
+
--checkpoint-path outputs/train/teddybear/50_sequences/subset_all/input_3/train/train_teddybear/checkpoint-1061000
|
| 9 |
+
|
| 10 |
+
CUDA_VISIBLE_DEVICES=0 ./viewdiff/scripts/test/test_spherical_360_256x256.sh
|
| 11 |
+
${CO3DV2_DATASET_ROOT}
|
| 12 |
+
outputs/train/teddybear/50_sequences/subset_all/input_3/train/train_teddybear/saved_model_from_checkpoint-1061000/
|
| 13 |
+
outputs/single-batch-uncond-generation
|
| 14 |
+
10
|
| 15 |
+
teddybear
|
| 16 |
+
50
|
| 17 |
+
```
|