Instructions to use REPA-E/sit-repae-vavae with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use REPA-E/sit-repae-vavae with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline from diffusers.utils import load_image # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("REPA-E/sit-repae-vavae", dtype=torch.bfloat16, device_map="cuda") prompt = "Turn this cat into a dog" input_image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/cat.png") image = pipe(image=input_image, prompt=prompt).images[0] - Notebooks
- Google Colab
- Kaggle
Update args.json
Browse files
args.json
CHANGED
|
@@ -38,8 +38,8 @@
|
|
| 38 |
"proj_coeff": 0.5,
|
| 39 |
"weighting": "uniform",
|
| 40 |
"vae": "f16d32",
|
| 41 |
-
"vae_ckpt": "pretrained/vavae
|
| 42 |
-
"disc_pretrained_ckpt": "pretrained/vavae
|
| 43 |
"loss_cfg_path": "configs/l1_lpips_kl_gan.yaml",
|
| 44 |
"vae_learning_rate": 0.0001,
|
| 45 |
"disc_learning_rate": 0.0001,
|
|
|
|
| 38 |
"proj_coeff": 0.5,
|
| 39 |
"weighting": "uniform",
|
| 40 |
"vae": "f16d32",
|
| 41 |
+
"vae_ckpt": "pretrained/vavae/vavae-f16d32.pt",
|
| 42 |
+
"disc_pretrained_ckpt": "pretrained/vavae/vavae-f16d32-discriminator-ckpt.pt",
|
| 43 |
"loss_cfg_path": "configs/l1_lpips_kl_gan.yaml",
|
| 44 |
"vae_learning_rate": 0.0001,
|
| 45 |
"disc_learning_rate": 0.0001,
|