|
--- |
|
license: creativeml-openrail-m |
|
library_name: diffusers |
|
tags: |
|
- Safetensors |
|
- stable-diffusion |
|
- stable-diffusion-diffusers |
|
- text-to-image |
|
pipeline_tag: text-to-image |
|
--- |
|
|
|
# Hyper |
|
## v2 |
|
|
|
 |
|
|
|
### Description: |
|
|
|
> <p>-Better faces, eyes, teeth, hands, lighting, prompt creativity and complexity.... Pretty much a massive improvement over v1 in all areas.</p><p>I mainly focussed on added prompt creativity, anatomy, and how well it does faces at a distance.</p> |
|
|
|
### Creator: Reiver_ |
|
### Civitai Page: https://civitai.com/models/32027 |
|
|
|
You can use this with the [🧨Diffusers library](https://github.com/huggingface/diffusers) |
|
|
|
### Diffusers |
|
```py |
|
from diffusers import StableDiffusionPipeline |
|
import torch |
|
|
|
model_id = "sam749/Hyper-v2" |
|
pipe = StableDiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16) |
|
pipe = pipe.to("cuda") |
|
|
|
prompt = "masterpiece, best quality, 1girl, (colorful),(delicate eyes and face), volumatic light, ray tracing, bust shot ,extremely detailed CG unity 8k wallpaper,solo,smile" |
|
image = pipe(prompt).images[0] |
|
|
|
image.save("result.png") |
|
``` |
|
|
