import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("shangguanyanyan/flux1-fill-dev-custom", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
FLUX.1-Fill-dev Custom Inference Endpoint
This repository is set up to deploy a custom Hugging Face Inference Endpoint using the StableDiffusionInstructPix2PixPipeline, enabling image-to-image transformation with prompt guidance.
How to Use
Send a POST request with base64-encoded image and your prompt to get an enhanced version of the image.
Input example:
{
"inputs": {
"prompt": "高清艺术风格头像",
"image": "<base64-encoded-image>",
"steps": 30,
"guidance_scale": 7.5,
"image_guidance_scale": 1.5
}
}
- Downloads last month
- 30
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support