Update README.md

9a5c22b over 2 years ago

1.49 kB

license: creativeml-openrail-m
tags:
  - safetensors
  - onnx
  - text-to-image
  - open-diffusion
  - od-v1
  - openskyml
language:
  - en
  - fr
  - ru
pipeline_tag: text-to-image

Open Diffusion V1

Generate cool images with OpenDiffusion V1 (OD-v1)

Model Details

Model Description

Developed by: OpenSkyML
Model type: Multimodal (Text-to-Image)
License: CreativeML-Openrail-m

Model Sources

Repository: click
Demo:
- demo with Gradio
- demo with Docker

Uses

In Free Inference API:

import requests
HF_READ_TOKEN = "..."
API_URL = "https://api-inference.huggingface.co/models/openskyml/open-diffusion-v1"
headers = {"Authorization": f"Bearer {HF_READ_TOKEN}"}

def query(payload):
    response = requests.post(API_URL, headers=headers, json=payload)
    return response.content
image_bytes = query({
    "inputs": "Astronaut riding a horse",
})
# You can access the image with PIL.Image for example
import io
from PIL import Image
image = Image.open(io.BytesIO(image_bytes))

In Spaces:

import gradio as gr

gr.load("models/openskyml/open-diffusion-v1").launch()