Overview • Key Features • API Example • Usage • Download • Emailware • Contributing • License • Contact • Acknowledgments
img2img-api exposes a simple HTTP API to generate images from an input image plus text prompts using Stable Diffusion (model: Anything V5). It accepts an initial URL image with generation parameters and returns generated images as URL.
- FastAPI HTTP API with OpenAPI docs available at
/docs - Img2Img generation using Stable Diffusion (Anything V5) via diffusers' StableDiffusionImg2ImgPipeline
- Accepts an image URL (HTTP/HTTPS); server downloads the input image for processing
- Generated images are uploaded to a configured host and the API returns the hosted image URL
- Configurable via environment variables:
MODEL_PATH,DEVICE,FREEIMAGE_API_KEY,FREEIMAGE_UPLOAD_URL - GPU support (CUDA) with automatic float16 when available; attention slicing enabled for memory efficiency
- Request validation with Pydantic schemas and clear JSON responses on success/error
- CORS enabled for browser-based clients; small, dependency-light service suitable for local or server use
POST /api/generate
Content-Type: application/jsonThis project expects a JSON body with an image_url pointing to a publicly-accessible image. The server will download that image, run img2img using the configured Stable Diffusion model, upload the result to the configured free image host, and return the hosted URL.
Request (JSON example):
{
"image_url": "https://example.com/input.jpg",
"prompt": "A fantasy landscape painting, vibrant colors, highly detailed",
"negative_prompt": "lowres, blurry",
"strength": 0.55,
"guidance_scale": 5.0,
"num_inference_steps": 4
}Response (JSON example):
{
"status": "success",
"image_url": "https://freeimage.host/abcd1234.png"
}Note
image_urlmust be an HTTP(S) URL reachable by the server (no local file paths or data URLs).- The service requires
FREEIMAGE_API_KEYandFREEIMAGE_UPLOAD_URLto be configured so the generated image can be uploaded and hosted.
Run locally (development):
git clone https://github.com/zouari-oss/img2img-api && cd img2img-api/project
chmod u+x setup && ./setup
fastapi runImportant
Base URL (local): http://localhost:8000
curl -X POST "http://localhost:8000/api/generate" \
-H "Content-Type: application/json" \
-d '{
"image_url":"https://example.com/input.jpg",
"prompt":"A fantasy landscape painting, vibrant colors, highly detailed",
"negative_prompt":"lowres, blurry",
"strength":0.55,
"guidance_scale":5.0,
"num_inference_steps":4
}'fetch("http://localhost:8000/api/generate", {
method: "POST",
headers: { "Content-Type": "application/json" },
body: JSON.stringify({
image_url: "https://example.com/input.jpg",
prompt: "A fantasy landscape painting, vibrant colors, highly detailed",
negative_prompt: "lowres, blurry",
strength: 0.55,
guidance_scale: 5.0,
num_inference_steps: 4,
}),
})
.then((res) => res.json())
.then((data) => console.log("Hosted URL:", data.image_url))
.catch(console.error);<?php
$ch = curl_init("http://localhost:8000/api/generate");
$data = json_encode([
"image_url" => "https://example.com/input.jpg",
"prompt" => "A fantasy landscape painting, vibrant colors, highly detailed",
"negative_prompt" => "lowres, blurry",
"strength" => 0.55,
"guidance_scale" => 5.0,
"num_inference_steps" => 4
]);
curl_setopt($ch, CURLOPT_POST, 1);
curl_setopt($ch, CURLOPT_POSTFIELDS, $data);
curl_setopt($ch, CURLOPT_HTTPHEADER, ['Content-Type: application/json']);
curl_setopt($ch, CURLOPT_RETURNTRANSFER, true);
$response = curl_exec($ch);
curl_close($ch);
var_dump(json_decode($response, true));
?>URL url = new URL("http://localhost:8000/api/generate");
HttpURLConnection conn = (HttpURLConnection) url.openConnection();
conn.setRequestMethod("POST");
conn.setRequestProperty("Content-Type", "application/json");
conn.setDoOutput(true);
String jsonInputString = "{"
+ "\"image_url\":\"https://example.com/input.jpg\","
+ "\"prompt\":\"A fantasy landscape painting, vibrant colors, highly detailed\","
+ "\"negative_prompt\":\"lowres, blurry\","
+ "\"strength\":0.55,"
+ "\"guidance_scale\":5.0,"
+ "\"num_inference_steps\":4"
+ "}";
try(OutputStream os = conn.getOutputStream()) {
byte[] input = jsonInputString.getBytes("utf-8");
os.write(input, 0, input.length);
}
try(BufferedReader br = new BufferedReader(
new InputStreamReader(conn.getInputStream(), "utf-8"))) {
StringBuilder response = new StringBuilder();
String responseLine;
while ((responseLine = br.readLine()) != null) {
response.append(responseLine.trim());
}
System.out.println(response.toString());
}#include <stdio.h>
#include <curl/curl.h>
int main(void){
CURL *curl = curl_easy_init();
if(curl) {
struct curl_slist *headers = NULL;
headers = curl_slist_append(headers, "Content-Type: application/json");
const char *data =
"{"
"\"image_url\":\"https://example.com/input.jpg\","
"\"prompt\":\"A fantasy landscape painting, vibrant colors, highly detailed\","
"\"negative_prompt\":\"lowres, blurry\","
"\"strength\":0.55,"
"\"guidance_scale\":5.0,"
"\"num_inference_steps\":4"
"}";
curl_easy_setopt(curl, CURLOPT_URL, "http://localhost:8000/api/generate");
curl_easy_setopt(curl, CURLOPT_HTTPHEADER, headers);
curl_easy_setopt(curl, CURLOPT_POSTFIELDS, data);
CURLcode res = curl_easy_perform(curl);
if(res != CURLE_OK)
fprintf(stderr, "curl_easy_perform() failed: %s\n",
curl_easy_strerror(res));
curl_slist_free_all(headers);
curl_easy_cleanup(curl);
}
return 0;
}You can download the latest installable version of img2img-api for Windows, macOS and Linux.
img2img-api is an emailware. Meaning, if you liked using this app or it has helped you in any way, would like you send as an email at zouariomar20@gmail.com about anything you'd want to say about this software. I'd really appreciate it!
Contributions are welcome! Please feel free to submit a Pull Request.
This repository is licensed under the GPL-3.0 License. You are free to use, modify, and distribute the content. See the LICENSE file for details.
For questions or suggestions, feel free to reach out:
- GitHub: zouari-oss
- Email: zouariomar20@gmail.com
- LinkedIn: zouari-omar
Built with ❤️ for the open-source community.