README.md

---
base_model: SG161222/Realistic_Vision_V6.0_B1_noVAE
library_name: diffusers
pipeline_tag: text-to-image

tags:
- lora
- diffusers
- text-to-image
- template:diffusion-lora

license: openrail
---

# Seb Realistic Avatar LoRA

LoRA trained on:

SG161222/Realistic_Vision_V6.0_B1_noVAE

## Files

- adapter_model.safetensors
- adapter_config.json

## Example

```python
from diffusers import StableDiffusionPipeline
import torch

pipe = StableDiffusionPipeline.from_pretrained(
    "SG161222/Realistic_Vision_V6.0_B1_noVAE",
    torch_dtype=torch.float16
)

pipe.load_lora_weights("seb2oo/seb_realistic_avatar_lora")

image = pipe(
    "portrait photo of a person"
).images[0]

image.save("result.png")