import requests
import time

def generate_image(prompt, api_key, api_type="community"):
    """Generate an image from text.

    Args:
        prompt: Text description of the image
        api_key: Your ModelsLab API key
        api_type: "realtime" (fast) or "community" (quality)
    """
    if api_type == "realtime":
        url = "https://modelslab.com/api/v6/realtime/text2img"
        payload = {
            "key": api_key,
            "prompt": prompt,
            "negative_prompt": "blurry, low quality",
            "width": 512,
            "height": 512,
            "num_inference_steps": 20,
            "guidance_scale": 7.5
        }
    else:  # community
        url = "https://modelslab.com/api/v6/images/text2img"
        payload = {
            "key": api_key,
            "model_id": "midjourney",  # or any model
            "prompt": prompt,
            "negative_prompt": "blurry, low quality, distorted",
            "width": 768,
            "height": 768,
            "samples": 1,
            "num_inference_steps": 30,
            "guidance_scale": 7.5,
            "safety_checker": "yes"
        }

    response = requests.post(url, json=payload)
    data = response.json()

    if data["status"] == "success":
        return data["output"][0]
    elif data["status"] == "processing":
        # Poll for results (community API may be async)
        return poll_result(data["id"], api_key)
    else:
        raise Exception(f"Error: {data.get('message')}")

def poll_result(request_id, api_key, timeout=300):
    """Poll for async generation results."""
    start = time.time()
    while time.time() - start < timeout:
        resp = requests.post(
            f"https://modelslab.com/api/v6/images/fetch/{request_id}",
            json={"key": api_key}
        )
        data = resp.json()

        if data["status"] == "success":
            return data["output"][0]
        elif data["status"] == "failed":
            raise Exception(data.get("message", "Failed"))

        time.sleep(5)
    raise Exception("Timeout")

undefined

def transform_image(init_image, prompt, api_key, strength=0.7):
    """Transform an existing image based on a prompt.

    Args:
        init_image: URL of the input image
        prompt: How to transform the image
        strength: 0.0-1.0, higher = more change
    """
    response = requests.post(
        "https://modelslab.com/api/v6/images/img2img",
        json={
            "key": api_key,
            "model_id": "midjourney",
            "prompt": prompt,
            "init_image": init_image,
            "strength": strength,
            "width": 512,
            "height": 512,
            "num_inference_steps": 30,
            "guidance_scale": 7.5
        }
    )

    data = response.json()
    if data["status"] == "success":
        return data["output"][0]
    elif data["status"] == "processing":
        return poll_result(data["id"], api_key)

undefined

def inpaint_image(image_url, mask_url, prompt, api_key):
    """Fill in masked parts of an image.

    Args:
        image_url: Original image URL
        mask_url: Mask image URL (white = inpaint, black = keep)
        prompt: What to generate in masked area
    """
    response = requests.post(
        "https://modelslab.com/api/v6/images/inpaint",
        json={
            "key": api_key,
            "model_id": "midjourney",
            "init_image": image_url,
            "mask_image": mask_url,
            "prompt": prompt,
            "negative_prompt": "blurry, low quality",
            "width": 512,
            "height": 512,
            "num_inference_steps": 30
        }
    )

    data = response.json()
    if data["status"] == "success":
        return data["output"][0]
    elif data["status"] == "processing":
        return poll_result(data["id"], api_key)

undefined

def generate_with_controlnet(image_url, prompt, controlnet_type, api_key):
    """Use ControlNet for precise composition control.

    ControlNet Types:
        - canny: Edge detection
        - depth: Depth map
        - pose: Human pose
        - scribble: Sketch-based
        - normal: Surface normals
        - seg: Semantic segmentation
    """
    response = requests.post(
        "https://modelslab.com/api/v6/images/controlnet",
        json={
            "key": api_key,
            "model_id": "midjourney",
            "controlnet_model": controlnet_type,
            "controlnet_type": controlnet_type,
            "init_image": image_url,
            "prompt": prompt,
            "width": 512,
            "height": 512,
            "num_inference_steps": 30
        }
    )

    data = response.json()
    if data["status"] == "success":
        return data["output"][0]
    elif data["status"] == "processing":
        return poll_result(data["id"], api_key)

undefined

✗ Bad: "a car"
✓ Good: "A red Ferrari sports car, studio lighting, highly detailed, 4k, photorealistic"

Include: Subject, style, lighting, quality descriptors

negative_prompt = "blurry, low quality, distorted, deformed, ugly, bad anatomy, extra limbs"

undefined

undefined

payload = {
    "key": api_key,
    "prompt": "...",
    "webhook": "https://yourserver.com/webhook",
    "track_id": "unique-identifier"
}

image = generate_image(
    "Professional product photo of wireless headphones, white background, studio lighting, commercial photography",
    api_key,
    negative_prompt="shadows, cluttered background, low quality"
)

image = generate_image(
    "Modern tech startup office, collaborative workspace, bright and airy, professional photography, 8k",
    api_key
)

image = generate_image(
    "A serene Japanese garden at sunset, cherry blossoms, koi pond, peaceful atmosphere, oil painting style",
    api_key,
    api_type="community"
)

seed = 12345
for i in range(4):
    image = generate_image(
        f"A cozy coffee shop interior, variation {i+1}",
        api_key,
        seed=seed
    )

try:
    image = generate_image(prompt, api_key)
    print(f"Success: {image}")
except Exception as e:
    print(f"Generation failed: {e}")
    # Log error, retry, or notify user