CRAWNiiK/sdxl-emoji-img2img

sdxl-emoji LoRA by CRAWNiiK

An SDXL fine-tune based on Apple Emojis

Inference API

To use this model with the Hugging Face Inference API, you need to pass the following inputs:

• prompt: The text prompt to guide the image generation.
• image: The input image for img2img transformation.
• strength: Controls how much the input image is altered (0.0 to 1.0).
• guidance_scale: Controls how closely the output follows the prompt.

Example API call:

import requests

API_URL = "https://api-inference.huggingface.co/models/CRAWNiiK/sdxl-emoji-img2img"
headers = {"Authorization": "Bearer YOUR_API_TOKEN"}

def query(payload):
    response = requests.post(API_URL, headers=headers, json=payload)
    return response.content

# Load your input image as a base64 string or URL
image_path = "input_image.jpg"

# Define the payload
payload = {
    "inputs": {
        "prompt": "A <s0><s1> emoji of a man",
        "image": image_path,
        "strength": 0.75,
        "guidance_scale": 7.5
    }
}

# Make the API request
image_bytes = query(payload)

# Save the output image
with open("output.png", "wb") as f:
    f.write(image_bytes)