Add model card
Browse files
README.md
ADDED
|
@@ -0,0 +1,53 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- lora
|
| 5 |
+
- virtual-try-on
|
| 6 |
+
- diffusion
|
| 7 |
+
- text-to-image
|
| 8 |
+
- fabric-generation
|
| 9 |
+
base_model: stabilityai/stable-diffusion-xl-base-1.0
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
# Virtual Try-On LoRA - Pattern2
|
| 13 |
+
|
| 14 |
+
This is a LoRA (Low-Rank Adaptation) model trained for virtual try-on fabric generation.
|
| 15 |
+
|
| 16 |
+
## Model Details
|
| 17 |
+
|
| 18 |
+
- **Fabric Type**: pattern2
|
| 19 |
+
- **Base Model**: Stable Diffusion XL
|
| 20 |
+
- **Training Checkpoints**: 1 checkpoint(s)
|
| 21 |
+
- **Model Type**: LoRA weights
|
| 22 |
+
|
| 23 |
+
## Usage
|
| 24 |
+
|
| 25 |
+
```python
|
| 26 |
+
from diffusers import DiffusionPipeline
|
| 27 |
+
import torch
|
| 28 |
+
|
| 29 |
+
# Load base model
|
| 30 |
+
pipe = DiffusionPipeline.from_pretrained(
|
| 31 |
+
"stabilityai/stable-diffusion-xl-base-1.0",
|
| 32 |
+
torch_dtype=torch.float16
|
| 33 |
+
)
|
| 34 |
+
|
| 35 |
+
# Load LoRA weights
|
| 36 |
+
pipe.load_lora_weights("zyuzuguldu/vton-lora-pattern2", weight_name="pytorch_lora_weights.safetensors")
|
| 37 |
+
pipe.to("cuda")
|
| 38 |
+
|
| 39 |
+
# Generate image
|
| 40 |
+
prompt = "a garment with pattern2 fabric texture"
|
| 41 |
+
image = pipe(prompt).images[0]
|
| 42 |
+
image.save("output.png")
|
| 43 |
+
```
|
| 44 |
+
|
| 45 |
+
## Training Info
|
| 46 |
+
|
| 47 |
+
This model was trained as part of a Virtual Try-On system to generate realistic fabric textures
|
| 48 |
+
for garment visualization.
|
| 49 |
+
|
| 50 |
+
## Files
|
| 51 |
+
|
| 52 |
+
- `pytorch_lora_weights.safetensors`: The main LoRA weights
|
| 53 |
+
- Additional training artifacts may be included depending on upload settings
|