sam749/Hyper-v2

Hyper

v2

Description:

-Better faces, eyes, teeth, hands, lighting, prompt creativity and complexity.... Pretty much a massive improvement over v1 in all areas.

I mainly focussed on added prompt creativity, anatomy, and how well it does faces at a distance.

Creator: Reiver_

Civitai Page: https://civitai.com/models/32027

You can use this with the 🧨Diffusers library

Diffusers

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")