|
--- |
|
license: creativeml-openrail-m |
|
inference: true |
|
tags: |
|
- stable-diffusion |
|
- stable-diffusion-diffusers |
|
- text-to-image |
|
- diffusers |
|
--- |
|
|
|
# Plat Diffusion v1.2.1 |
|
|
|
Plat Diffusion is a fine-tuned model based on [Waifu Diffusion v1.3](https://huggingface.co/hakurei/waifu-diffusion) with images generated with niji・journey. |
|
|
|
 |
|
|
|
``` |
|
masterpiece, 1girl, flower, sunflower, solo, smile, earrings, shirt, jewelry, holding, blurry, bangs, petals, blush, long hair, looking at viewer, holding flower, brown hair, white shirt, collared shirt, yellow flower, blurry background, closed mouth, blue eyes, upper body, depth of field |
|
``` |
|
|
|
### Recomended Negative Prompt |
|
Same as NAI's "Low Quality + Bad Anatomy" |
|
|
|
``` |
|
lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry |
|
``` |
|
|
|
## Special Tags |
|
|
|
In version 1.2.1, the following special tags can be used |
|
|
|
- masterpiece: high quality illustrations are classified as `masterpiece`. |
|
|
|
|
|
|
|
# 🧨 Diffusers |
|
|
|
```py |
|
from diffusers import StableDiffusionPipeline |
|
import torch |
|
|
|
model_id = "p1atdev/plat-diffusion" |
|
pipe = StableDiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16) |
|
pipe = pipe.to("cuda") |
|
|
|
prompt = "masterpiece, 1girl, surrounded by many flowers" |
|
image = pipe(prompt).images[0] |
|
|
|
image.save("girl.png") |
|
``` |
