README.md

---
license: creativeml-openrail-m
tags:
- stable-diffusion
- text-to-image
---

Update of James Cameron's Avatar Movie Model, with Stable Diffusion 2.1. This model can generate the faces of the people indicated in the prompt with avatar features.

### Sample images Will Smith:   prompt= photorealistic headshot of Will Smith, avatar style
![output Samples v3](https://huggingface.co/Jersonm89/SD2.1_Avatar/resolve/main/will.png)


### Sample images Angelina Jolie:   prompt= photorealistic headshot of Angelina Jolie, avatar style
![output Samples v3](https://huggingface.co/Jersonm89/SD2.1_Avatar/resolve/main/jolie.png)

### Sample images Mila Kunis:   prompt= photorealistic headshot of Mila Kunis, avatar style
![output Samples v3](https://huggingface.co/Jersonm89/SD2.1_Avatar/resolve/main/mila.png)

### Sample images Jenna Ortega:   prompt= photorealistic headshot of Jenna Ortega, avatar style
![output Samples v3](https://huggingface.co/Jersonm89/SD2.1_Avatar/resolve/main/Jenna.png)


A standard negative prompt was used 
Negative Prompt: blender, cropped, lowres, poorly drawn face, out of frame, poorly drawn hands, blurry, bad art, 
blurred, text, watermark, disfigured, deformed, closed eyes : -2