Image-to-Image
Diffusers
Safetensors
virtual-try-on
image-editing
multi-view
human
vton360
cvpr-2025
Instructions to use nielsr/VTON360-MVHumanNet with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use nielsr/VTON360-MVHumanNet 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("nielsr/VTON360-MVHumanNet", 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
Add VTON360 model card and provenance
Browse files
README.md
ADDED
|
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: creativeml-openrail-m
|
| 3 |
+
library_name: diffusers
|
| 4 |
+
pipeline_tag: image-to-image
|
| 5 |
+
base_model: stable-diffusion-v1-5/stable-diffusion-v1-5
|
| 6 |
+
tags:
|
| 7 |
+
- virtual-try-on
|
| 8 |
+
- image-editing
|
| 9 |
+
- multi-view
|
| 10 |
+
- human
|
| 11 |
+
- vton360
|
| 12 |
+
- cvpr-2025
|
| 13 |
+
- arxiv:2503.12165
|
| 14 |
+
---
|
| 15 |
+
|
| 16 |
+
# VTON360 checkpoint for MVHumanNet
|
| 17 |
+
|
| 18 |
+
This repository contains the `checkpoint-40000` model bundle for the
|
| 19 |
+
MVHumanNet experiment released with **VTON 360: High-Fidelity Virtual Try-On
|
| 20 |
+
from Any Viewing Direction** (CVPR 2025).
|
| 21 |
+
|
| 22 |
+
Use it with the custom implementation in the
|
| 23 |
+
[official VTON360 repository](https://github.com/scnuhealthy/VTON360). The
|
| 24 |
+
repository README instructs users to place this checkpoint under
|
| 25 |
+
`src/multiview_consist_edit/checkpoints` and run
|
| 26 |
+
`src/multiview_consist_edit/infer_tryon_multi.py`.
|
| 27 |
+
|
| 28 |
+
```python
|
| 29 |
+
from huggingface_hub import snapshot_download
|
| 30 |
+
|
| 31 |
+
snapshot_download(
|
| 32 |
+
repo_id="nielsr/VTON360-MVHumanNet",
|
| 33 |
+
local_dir="src/multiview_consist_edit/checkpoints/mvhumannet_tryon_mvattn_multi",
|
| 34 |
+
)
|
| 35 |
+
```
|
| 36 |
+
|
| 37 |
+
The released configuration also expects:
|
| 38 |
+
|
| 39 |
+
- [`stable-diffusion-v1-5/stable-diffusion-v1-5`](https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5)
|
| 40 |
+
- [`stabilityai/sd-vae-ft-mse`](https://huggingface.co/stabilityai/sd-vae-ft-mse)
|
| 41 |
+
- [`openai/clip-vit-base-patch32`](https://huggingface.co/openai/clip-vit-base-patch32)
|
| 42 |
+
|
| 43 |
+
## Provenance and attribution
|
| 44 |
+
|
| 45 |
+
- Official code: https://github.com/scnuhealthy/VTON360
|
| 46 |
+
- Project page: https://scnuhealthy.github.io/VTON360/
|
| 47 |
+
- Paper: https://huggingface.co/papers/2503.12165
|
| 48 |
+
- arXiv: https://arxiv.org/abs/2503.12165
|
| 49 |
+
- Original Baidu release: https://pan.baidu.com/s/1Onu7BIFzOppRSzO97ZmlmQ (code `mahx`)
|
| 50 |
+
- Community Hub source used for this mirror: https://huggingface.co/NTUST-DDRC/mvhumannet_tryon_mvattn_multi
|
| 51 |
+
|
| 52 |
+
The checkpoint is a derivative of Stable Diffusion v1.5 and retains the
|
| 53 |
+
CreativeML Open RAIL-M license. Users must also follow the licenses and terms
|
| 54 |
+
of VTON360, its code dependencies, and the underlying MVHumanNet data.
|
| 55 |
+
|