Text-to-Image
Diffusers
Safetensors
English
StableDiffusionPipeline
stable-diffusion
stable-diffusion-diffusers
Instructions to use wavymulder/portraitplus with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use wavymulder/portraitplus with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("wavymulder/portraitplus", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
Commit ·
eaf89c8
1
Parent(s): a64d466
Update README.md
Browse files
README.md
CHANGED
|
@@ -20,7 +20,7 @@ inference: true
|
|
| 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
|
| 24 |
|
| 25 |
Portrait+ works best at a 1:1 aspect ratio, though I've had success with tall aspect ratios as well.
|
| 26 |
|
|
|
|
| 20 |
|
| 21 |
Use `portrait+ style` in your prompt (I recommend at the start)
|
| 22 |
|
| 23 |
+
The goal was to create a model with a consistent portrait composition and consistent eyes. See the batch example below for the consistency of the model's eyes. This model can do several styles, so you want to guide it along depending on your goals. 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 |
|