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
File size: 816 Bytes
0f78d9d | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 | {
"resolution": 512,
"patch_size": 2,
"mlp_ratio": 4,
"use_qknorm": true,
"use_swiglu": true,
"use_rope": true,
"use_rmsnorm": true,
"wo_shift": false,
"dim": 1536,
"depth": 36,
"num_heads": 24,
"ae_type": "qwen",
"ae_path": "preset/ckpts/Qwen-Image-vae-2d",
"time_dist": [
"lognorm",
0,
1.0
],
"cfg_ratio": 0.1,
"cfg_scale": 1.5,
"dinov2_size": 448,
"enc_type": "dinov2l",
"enc_dim": 1024,
"layer_dinov2b_list": [
17
],
"interp_type": "lin",
"encdim_ratio": 3,
"weak_cond_strength_aelq_list": [
0,
0
],
"cond_strength_aelq_list": [
5,
1
],
"t_start": 0,
"t_end": 1,
"auxiliary_time_cond": false,
"distill_type": "onestep"
} |