Instructions to use CSWRY/VOSR with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use CSWRY/VOSR 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("CSWRY/VOSR", 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
Upload 2 files
Browse files- VOSR2/args.json +42 -0
- VOSR2/checkpoints/ema_model.safetensors +3 -0
VOSR2/args.json
ADDED
|
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"resolution": 512,
|
| 3 |
+
"patch_size": 2,
|
| 4 |
+
"mlp_ratio": 4,
|
| 5 |
+
"use_qknorm": true,
|
| 6 |
+
"use_swiglu": true,
|
| 7 |
+
"use_rope": true,
|
| 8 |
+
"use_rmsnorm": true,
|
| 9 |
+
"wo_shift": false,
|
| 10 |
+
"dim": 1536,
|
| 11 |
+
"depth": 36,
|
| 12 |
+
"num_heads": 24,
|
| 13 |
+
"ae_type": "qwen",
|
| 14 |
+
"ae_path": "preset/ckpts/Qwen-Image-vae-2d",
|
| 15 |
+
"time_dist": [
|
| 16 |
+
"lognorm",
|
| 17 |
+
0,
|
| 18 |
+
1.0
|
| 19 |
+
],
|
| 20 |
+
"cfg_ratio": 0.1,
|
| 21 |
+
"cfg_scale": 1.5,
|
| 22 |
+
"dinov2_size": 448,
|
| 23 |
+
"enc_type": "dinov2l",
|
| 24 |
+
"enc_dim": 1024,
|
| 25 |
+
"layer_dinov2b_list": [
|
| 26 |
+
17
|
| 27 |
+
],
|
| 28 |
+
"interp_type": "lin",
|
| 29 |
+
"encdim_ratio": 3,
|
| 30 |
+
"weak_cond_strength_aelq_list": [
|
| 31 |
+
0,
|
| 32 |
+
0
|
| 33 |
+
],
|
| 34 |
+
"cond_strength_aelq_list": [
|
| 35 |
+
5,
|
| 36 |
+
1
|
| 37 |
+
],
|
| 38 |
+
"t_start": 0,
|
| 39 |
+
"t_end": 1,
|
| 40 |
+
"auxiliary_time_cond": false,
|
| 41 |
+
"distill_type": "onestep"
|
| 42 |
+
}
|
VOSR2/checkpoints/ema_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bdcaa81e4c675b6074de643e27daafe73eb8125d4d0264d1bf30a004e9644b71
|
| 3 |
+
size 5576385424
|