Commit
•
a64d466
1
Parent(s):
16b08e9
Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,30 @@
|
|
| 1 |
---
|
|
|
|
|
|
|
|
|
|
| 2 |
license: creativeml-openrail-m
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
+
language:
|
| 3 |
+
- en
|
| 4 |
+
thumbnail: "https://huggingface.co/wavymulder/portraitplus/resolve/main/imgs/page1.jpg"
|
| 5 |
license: creativeml-openrail-m
|
| 6 |
+
tags:
|
| 7 |
+
- stable-diffusion
|
| 8 |
+
- stable-diffusion-diffusers
|
| 9 |
+
- text-to-image
|
| 10 |
+
- safetensors
|
| 11 |
+
- diffusers
|
| 12 |
+
inference: true
|
| 13 |
---
|
| 14 |
+
|
| 15 |
+
|
| 16 |
+
|
| 17 |
+
**Portrait+**
|
| 18 |
+
|
| 19 |
+
[*CKPT DOWNLOAD LINK*](https://huggingface.co/wavymulder/portraitplus/resolve/main/portrait%2B1.0.ckpt) - this is a dreambooth model trained on a diverse set of close to medium range portraits of people.
|
| 20 |
+
|
| 21 |
+
Use `portrait+ style` in your prompt (I recommend at the start)
|
| 22 |
+
|
| 23 |
+
This model can do several styles, so you want to guide it along depending on your target style. Note below in the document that prompting celebrities works a bit differently than prompting generic characters, since real people have a more photoreal presence in the base 1.5 model.
|
| 24 |
+
|
| 25 |
+
Portrait+ works best at a 1:1 aspect ratio, though I've had success with tall aspect ratios as well.
|
| 26 |
+
|
| 27 |
+
Please see [this document where I share the parameters (prompt, sampler, seed, etc.) used for all example images above.](https://huggingface.co/wavymulder/portraitplus/resolve/main/parameters_for_samples.txt)
|
| 28 |
+
|
| 29 |
+
|
| 30 |
+
|