| license: creativeml-openrail-m | |
| library_name: diffusers | |
| tags: | |
| - Safetensors | |
| - stable-diffusion | |
| - stable-diffusion-diffusers | |
| - text-to-image | |
| pipeline_tag: text-to-image | |
| # JernauMix | |
| ## Medusa (v4.0) | |
|  | |
| ### Description: | |
| > <p>I've kept merging and testing until I was satisfied that the results were some sort of improvement over version 3.0 (I think the current version incorporates data from 5 more models compared to Chimera). I reckon some details like the skin, textures, possibly the lighting too, are even better than with Chimera, which in my humble opinion already excelled at some of those points. Enjoy!</p> | |
| ### Creator: JernauGurgeh | |
| ### Civitai Page: https://civitai.com/models/163310 | |
| You can use this with the [🧨Diffusers library](https://github.com/huggingface/diffusers) | |
| ### Diffusers | |
| ```py | |
| from diffusers import StableDiffusionPipeline | |
| import torch | |
| model_id = "sam749/JernauMix-Medusa-v4-0" | |
| 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") | |
| ``` | |