#!/usr/bin/env python3 import os import sys import argparse import time import base64 from pathlib import Path import requests def load_env(): env_path = Path(__file__).parent / ".env" if env_path.exists(): for line in env_path.read_text().splitlines(): line = line.strip() if line and not line.startswith("#") and "=" in line: k, v = line.split("=", 1) os.environ.setdefault(k.strip(), v.strip().strip("\"'")) load_env() API_TOKEN = os.environ.get("CHUTES_API_TOKEN") API_URL = "https://chutes-qwen-image-edit-2511.chutes.ai/generate" def image_to_base64(image_path): if not os.path.exists(image_path): raise FileNotFoundError(f"Image file not found: {image_path}") with open(image_path, "rb") as f: image_bytes = f.read() return base64.b64encode(image_bytes).decode("utf-8") def edit_image( prompt, image_path, width=1024, height=1024, steps=40, seed=None, cfg_scale=4, negative_prompt="", ): if not API_TOKEN: print("Error: CHUTES_API_TOKEN not set in environment", file=sys.stderr) sys.exit(1) if not os.path.exists(image_path): print(f"Error: Image file not found: {image_path}", file=sys.stderr) sys.exit(1) if not prompt: print("Error: Prompt cannot be empty", file=sys.stderr) sys.exit(1) image_b64 = image_to_base64(image_path) payload = { "seed": seed, "width": width, "height": height, "prompt": prompt, "image_b64s": [image_b64], "true_cfg_scale": cfg_scale, "negative_prompt": negative_prompt, "num_inference_steps": steps, } try: headers = { "Authorization": f"Bearer {API_TOKEN}", "Content-Type": "application/json", } response = requests.post(API_URL, headers=headers, json=payload, timeout=300) response.raise_for_status() content_type = response.headers.get("Content-Type", "") if "image/" in content_type: image_bytes = response.content else: result = response.json() if isinstance(result, list) and len(result) > 0: item = result[0] image_data = item.get("data", "") if image_data.startswith("data:image"): image_bytes = base64.b64decode(image_data.split(",", 1)[1]) else: image_bytes = base64.b64decode(image_data) else: print("Error: Invalid response format", file=sys.stderr) sys.exit(1) timestamp = int(time.time()) filename = f"edited_{timestamp}.jpg" with open(filename, "wb") as f: f.write(image_bytes) print(f"Image saved: {filename} [{timestamp}]") except requests.exceptions.RequestException as e: print(f"Error: API request failed - {e}", file=sys.stderr) sys.exit(1) except Exception as e: print(f"Error: {e}", file=sys.stderr) sys.exit(1) def main(): parser = argparse.ArgumentParser(description="Edit images with AI") parser.add_argument("prompt", help="Text prompt describing the edit") parser.add_argument("image_path", help="Path to input image file") parser.add_argument( "--width", type=int, default=1024, help="Output width (128-2048)" ) parser.add_argument( "--height", type=int, default=1024, help="Output height (128-2048)" ) parser.add_argument("--steps", type=int, default=40, help="Inference steps (5-100)") parser.add_argument("--seed", type=int, default=None, help="Random seed") parser.add_argument( "--cfg-scale", type=float, default=4, help="True CFG scale (0-10)" ) parser.add_argument( "--negative-prompt", type=str, default="", help="Negative prompt" ) args = parser.parse_args() if not (128 <= args.width <= 2048): print("Error: width must be between 128 and 2048", file=sys.stderr) sys.exit(1) if not (128 <= args.height <= 2048): print("Error: height must be between 128 and 2048", file=sys.stderr) sys.exit(1) if not (5 <= args.steps <= 100): print("Error: steps must be between 5 and 100", file=sys.stderr) sys.exit(1) if args.seed is not None and not (0 <= args.seed <= 4294967295): print("Error: seed must be between 0 and 4294967295", file=sys.stderr) sys.exit(1) if not (0 <= args.cfg_scale <= 10): print("Error: cfg-scale must be between 0 and 10", file=sys.stderr) sys.exit(1) edit_image( prompt=args.prompt, image_path=args.image_path, width=args.width, height=args.height, steps=args.steps, seed=args.seed, cfg_scale=args.cfg_scale, negative_prompt=args.negative_prompt, ) if __name__ == "__main__": main()