sam749/Hyper-v2

1---2license: creativeml-openrail-m3library_name: diffusers4tags:5- Safetensors6- stable-diffusion7- stable-diffusion-diffusers8- text-to-image9pipeline_tag: text-to-image10---11 12  # Hyper13  ## v214 15  ![Generated Sample](preview.jpeg)16 17  ### Description:18 19  > <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>20 21  ### Creator: Reiver_22  ### Civitai Page: https://civitai.com/models/3202723 24  You can use this with the [🧨Diffusers library](https://github.com/huggingface/diffusers)25 26  ### Diffusers27  ```py28  from diffusers import StableDiffusionPipeline29  import torch30 31  model_id = "sam749/Hyper-v2"32  pipe = StableDiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16)33  pipe = pipe.to("cuda")34 35  prompt = "masterpiece, best quality, 1girl, (colorful),(delicate eyes and face), volumatic light, ray tracing, bust shot ,extremely detailed CG unity 8k wallpaper,solo,smile"36  image = pipe(prompt).images[0]37 38  image.save("result.png")39  ```40