How to use from the
Use from the
Diffusers library
pip install -U diffusers transformers accelerate
import torch
from diffusers import DiffusionPipeline

# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("cocktailpeanut/pony-diffusion-v6-xl", dtype=torch.bfloat16, device_map="cuda")
pipe.load_lora_weights("Muapi/pokemon-may-oras-multiple-outfits")

prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]

Pokemon - May - ORAS Multiple Outfits

preview

Base model: Pony Trained words: Mayoras, grey eyes, 1default1, red hairband, bow hairband, red shirt, sleeveless, white shorts, bike shorts under shorts, yellow footwear, fanny pack, yellow bag, 2spring2, pink dress, yellow pantyhose, pink choker, pink footwear, yellow hairband, rabbit ears, wrist cuffs, 3anniversary3, red dress, black gloves, black footwear, high heels, hair ornament, 4sygna4, twintails, orange shirt, orange skirt, hair ornament, orange wristband, red footwear, Contest outfit, idol, hair tuft, white shirt, hair bow, pink bow, pink skirt, tutu, pink footwear, high heels

๐Ÿง  Usage (Python)

๐Ÿ”‘ Get your MUAPI key from muapi.ai/access-keys

import requests, os
url = "https://api.muapi.ai/api/v1/sdxl-lora-image"
headers = {"Content-Type": "application/json", "x-api-key": os.getenv("MUAPIAPP_API_KEY")}
payload = {
    "prompt": "masterpiece, best quality",
    "lora_model": "pokemon-may-oras-multiple-outfits",
    "lora_strength": 1.0,
    "width": 1024,
    "height": 1024,
    "num_images": 1
}
print(requests.post(url, headers=headers, json=payload).json())
Downloads last month
15
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support