Downloads · 30 days
55
16% of all-time downloads
graizelle/graizelle_pony_mix
graizelle_pony_mix is a text-to-image model from graizelle. Use it when you need an image from a text prompt. It is set up for diffusers. The card lists the license as creativeml-openrail-m.
Downloads · 30 days
55
16% of all-time downloads
All-time downloads
347
Public
Repo size
7.1 GB
Likes
0
Public
Click a slice to open those files.
.safetensors7.1 GB · 100%
From the Hugging Face model README
Graizelle's GRLE PonyXL Mix is a custom Stable Diffusion XL checkpoint merge built on top of Pony Diffusion V6 XL.
It is designed for stylized character art with expressive details, vibrant colors, and clean rendering.
This model is optimized for single-character portraits, fantasy themes, and stylized NSFW art.
It merges elements from GRLE and PonyXL to create unique stylized outputs with crisp details and dynamic composition.
The gallery above shows 3 showcase examples of what the model can generate.
You can replace the images in images/preview1.png, preview2.png, preview3.png with your own renders to update the gallery.
Released under the CreativeML OpenRAIL-M License:
Full license: OpenRAIL-M License
from diffusers import StableDiffusionXLPipeline
import torch
model_id = "graizelle/ponyxl_merge"
pipe = StableDiffusionXLPipeline.from_pretrained(
model_id,
torch_dtype=torch.float16
).to("cuda") # or "mps" on Mac
prompt = "a stunning anime girl with silver hair and glowing sword, masterpiece, highly detailed"
image = pipe(prompt).images[0]
image.save("ponyxl_merge.png")