combined pipeline running function

3d-generation-pipeline/start_pipeline.py

@@ -0,0 +1,75 @@
+import os
+import base64
+import requests
+from datetime import datetime
+from dotenv import load_dotenv
+
+load_dotenv()
+
+ACCOUNT_ID = os.environ["CF_ACCOUNT_ID"]
+API_TOKEN = os.environ["CF_API_TOKEN"]
+
+
+def get_timestamp():
+    return datetime.now().strftime("%Y-%m-%d-%H-%M-%S")
+
+
+def text_to_image(prompt, output_name):
+    MODEL = "@cf/black-forest-labs/flux-1-schnell"
+    URL = f"https://api.cloudflare.com/client/v4/accounts/{ACCOUNT_ID}/ai/run/{MODEL}"
+
+    payload = {
+        "prompt": prompt,
+    }
+
+    headers = {
+        "Authorization": f"Bearer {API_TOKEN}",
+        "Content-Type": "application/json",
+    }
+
+    resp = requests.post(URL, json=payload, headers=headers, timeout=60)
+    resp.raise_for_status()
+
+    data = resp.json()
+    b64 = data["result"]["image"]
+    if not b64:
+        raise RuntimeError(f"Unexpected response structure: {data}")
+
+    img_bytes = base64.b64decode(b64)
+
+    out_path = f"images/{output_name}.jpg"
+    with open(out_path, "wb") as f:
+        f.write(img_bytes)
+
+    return out_path
+
+def refine_text_prompt(prompt):
+    MODEL = "@cf/meta/llama-3.2-3b-instruct"
+    URL = f"https://api.cloudflare.com/client/v4/accounts/{ACCOUNT_ID}/ai/run/{MODEL}"
+
+    instructions = """
+    User is talking about some object. Your task is to generate a short and concise description of it. Use only user's own words, keep it as short as possible.
+    Example:
+    User: 'Umm, okay, I would like a really cool sword, with for example a bright orange crossguard. And also it should be slightly curved.'
+    You: 'a slightly curved sword with bright orange crossguard'
+    """
+
+    response = requests.post(URL,
+    headers={"Authorization": f"Bearer {API_TOKEN}"},
+    json={
+        "messages": [
+        {"role": "system", "content": instructions},
+        {"role": "user", "content": prompt}
+        ]
+    }
+    )
+    data = response.json()
+    return data["result"]["response"]
+
+def main():
+    user_prompt = "Give epic sword"
+    print(f"User prompt: {user_prompt}")
+    refined_prompt = refine_text_prompt(user_prompt)
+    print(f"Refined prompt: {refined_prompt}")
+    image_path = text_to_image(refined_prompt, get_timestamp())
+    print(f"Generated image file: {image_path}")