Skip to content

AI turns documents or topics into real, native PowerPoint decks—with native shapes, transitions and animations, data-backed charts and tables on demand, audio narration from speaker notes, and support for your own .pptx templates. · by Hugo He

feat: add openrouter backend (#57)

scientificworld767a53629f12
diff --git a/.env.example b/.env.example
index 6e3ac7ab..920c6f88 100644
--- a/.env.example
+++ b/.env.example
@@ -101,6 +101,10 @@
# REPLICATE_API_TOKEN=r8_xxx
# REPLICATE_MODEL=black-forest-labs/flux-1.1-pro
# REPLICATE_BASE_URL=https://api.replicate.com/v1/predictions
+#
+# OPENROUTER_API_KEY=sk-or-v1-xxx
+# OPENROUTER_MODEL=google/gemini-3.1-flash-image-preview
+# OPENROUTER_BASE_URL=https://openrouter.ai/api/v1
# ─────────────────────────────────────────────────────────────
# Multi-provider example / 多提供商共存示例
diff --git a/skills/ppt-master/scripts/image_backends/backend_openrouter.py b/skills/ppt-master/scripts/image_backends/backend_openrouter.py
new file mode 100644
index 00000000..875bb037
--- /dev/null
+++ b/skills/ppt-master/scripts/image_backends/backend_openrouter.py
@@ -0,0 +1,183 @@
+#!/usr/bin/env python3
+"""
+OpenRouter image generation backend.
+
+Configuration keys:
+ OPENROUTER_API_KEY (required)
+ OPENROUTER_BASE_URL (optional)
+ OPENROUTER_MODEL (optional)
+"""
+
+import base64
+import os
+import time
+import threading
+import requests
+
+from image_backends.backend_common import (
+ MAX_RETRIES,
+ is_rate_limit_error,
+ normalize_image_size,
+ resolve_output_path,
+ retry_delay,
+ save_image_bytes,
+)
+
+
+# ╔══════════════════════════════════════════════════════════════════╗
+# ║ Constants ║
+# ╚══════════════════════════════════════════════════════════════════╝
+
+VALID_ASPECT_RATIOS = [
+ "1:1", "1:4", "1:8",
+ "2:3", "3:2", "3:4", "4:1", "4:3",
+ "4:5", "5:4", "8:1", "9:16", "16:9", "21:9"
+]
+
+VALID_IMAGE_SIZES = ["1K", "2K", "4K", "0.5K"]
+
+DEFAULT_MODEL = "google/gemini-3.1-flash-image-preview"
+DEFAULT_ENDPOINT = "https://openrouter.ai/api/v1"
+
+# ╔══════════════════════════════════════════════════════════════════╗
+# ║ Image Generation ║
+# ╚══════════════════════════════════════════════════════════════════╝
+
+def _resolve_url(base_url: str) -> str:
+ """Resolve the OpenRouter generation endpoint."""
+ return base_url.rstrip("/") + "/chat/completions"
+
+def _generate_image(api_key: str, prompt: str, negative_prompt: str = None,
+ aspect_ratio: str = "1:1", image_size: str = "1K",
+ output_dir: str = None, filename: str = None,
+ model: str = DEFAULT_MODEL, base_url: str = DEFAULT_ENDPOINT) -> str:
+ """
+ Image generation via OpenRouter's API.
+ """
+
+ url = _resolve_url(base_url)
+
+ final_prompt = prompt
+ if negative_prompt:
+ final_prompt += f"\n\nAvoid the following: {negative_prompt}"
+
+ headers = {
+ "Authorization": f"Bearer {api_key}",
+ "Content-Type": "application/json"
+ }
+
+ payload = {
+ "model": model,
+ "messages": [
+ {
+ "role": "user",
+ "content": final_prompt
+ }
+ ],
+ "modalities": ["image", "text"],
+ "image_config": {
+ "aspect_ratio": aspect_ratio,
+ "image_size": image_size
+ }
+ }
+
+ print(f"[OpenRouter]")
+ print(f" Model: {model}")
+ print(f" Prompt: {final_prompt[:120]}{'...' if len(final_prompt) > 120 else ''}")
+ print(f" Aspect Ratio: {aspect_ratio}")
+ print(f" Image Size: {image_size}")
+ print()
+
+ start_time = time.time()
+ print(f" [..] Generating...", end="", flush=True)
+
+ # Heartbeat thread
+ heartbeat_stop = threading.Event()
+
+ def _heartbeat():
+ while not heartbeat_stop.is_set():
+ heartbeat_stop.wait(5)
+ if not heartbeat_stop.is_set():
+ elapsed = time.time() - start_time
+ print(f" {elapsed:.0f}s...", end="", flush=True)
+
+ hb_thread = threading.Thread(target=_heartbeat, daemon=True)
+ hb_thread.start()
+
+ try:
+ result = requests.post(url, headers=headers, json=payload, timeout=300).json()
+ finally:
+ heartbeat_stop.set()
+ hb_thread.join(timeout=1)
+
+ elapsed = time.time() - start_time
+ print(f"\n [DONE] Image generated ({elapsed:.1f}s)")
+
+ if result.get("choices"):
+ message = result["choices"][0]["message"]
+ if message.get("images"):
+ path = resolve_output_path(prompt, output_dir, filename, ".png")
+ # strip "data:image/png;base64,"
+ image_data = base64.urlsafe_b64decode(message["images"][0]["image_url"]["url"][22:])
+ return save_image_bytes(image_data, path)
+
+ raise RuntimeError("No image was generated. The server may have refused the request.")
+
+
+# ╔══════════════════════════════════════════════════════════════════╗
+# ║ Public Entry Point ║
+# ╚══════════════════════════════════════════════════════════════════╝
+
+def generate(prompt: str, negative_prompt: str = None,
+ aspect_ratio: str = "1:1", image_size: str = "1K",
+ output_dir: str = None, filename: str = None,
+ model: str = None, max_retries: int = MAX_RETRIES) -> str:
+ """
+ OpenRouter image generation with automatic retry.
+
+ Reads credentials from the current process environment or the project-root `.env`:
+ OPENROUTER_API_KEY
+ OPENROUTER_BASE_URL
+ OPENROUTER_MODEL (optional override)
+ """
+ api_key = os.environ.get("OPENROUTER_API_KEY")
+ base_url = os.environ.get("OPENROUTER_BASE_URL")
+
+ if not api_key:
+ raise ValueError(
+ "No API key found. Set OPENROUTER_API_KEY in the current environment or the project-root .env."
+ )
+
+ if model is None:
+ model = os.environ.get("OPENROUTER_MODEL") or DEFAULT_MODEL
+
+ image_size = normalize_image_size(image_size)
+
+ if aspect_ratio not in VALID_ASPECT_RATIOS:
+ raise ValueError(f"Invalid aspect ratio '{aspect_ratio}'. Valid: {VALID_ASPECT_RATIOS}")
+
+ if image_size not in VALID_IMAGE_SIZES:
+ raise ValueError(f"Invalid image size '{image_size}'. Valid: {VALID_IMAGE_SIZES}")
+
+ last_error = None
+ for attempt in range(max_retries + 1):
+ try:
+ return _generate_image(api_key, prompt, negative_prompt,
+ aspect_ratio, image_size, output_dir,
+ filename, model, base_url)
+ except Exception as e:
+ last_error = e
+ if attempt < max_retries and is_rate_limit_error(e):
+ delay = retry_delay(attempt, rate_limited=True)
+ print(f"\n [WARN] Rate limit hit (attempt {attempt + 1}/{max_retries + 1}). "
+ f"Waiting {delay}s before retry...")
+ time.sleep(delay)
+ elif attempt < max_retries:
+ delay = retry_delay(attempt, rate_limited=False)
+ print(f"\n [WARN] Error (attempt {attempt + 1}/{max_retries + 1}): {e}. "
+ f"Retrying in {delay}s...")
+ time.sleep(delay)
+ else:
+ break
+
+ raise RuntimeError(f"Failed after {max_retries + 1} attempts. Last error: {last_error}")
diff --git a/skills/ppt-master/scripts/image_gen.py b/skills/ppt-master/scripts/image_gen.py
index 21f087d8..e2213ce6 100644
--- a/skills/ppt-master/scripts/image_gen.py
+++ b/skills/ppt-master/scripts/image_gen.py
@@ -5,18 +5,19 @@ Unified Image Generation Tool
Dispatches to the appropriate backend based on explicit provider configuration.
Backend selection (`IMAGE_BACKEND` in `.env` or the current process environment):
- IMAGE_BACKEND=gemini -> Gemini backend (google-genai SDK)
- IMAGE_BACKEND=openai -> OpenAI-compatible backend (openai SDK)
- IMAGE_BACKEND=minimax -> MiniMax image backend
- IMAGE_BACKEND=stability -> Stability AI backend
- IMAGE_BACKEND=bfl -> Black Forest Labs FLUX backend
- IMAGE_BACKEND=ideogram -> Ideogram backend
- IMAGE_BACKEND=qwen -> Alibaba Qwen image backend
- IMAGE_BACKEND=zhipu -> Zhipu GLM-Image backend
- IMAGE_BACKEND=volcengine -> Volcengine Seedream backend
+ IMAGE_BACKEND=gemini -> Gemini backend (google-genai SDK)
+ IMAGE_BACKEND=openai -> OpenAI-compatible backend (openai SDK)
+ IMAGE_BACKEND=minimax -> MiniMax image backend
+ IMAGE_BACKEND=stability -> Stability AI backend
+ IMAGE_BACKEND=bfl -> Black Forest Labs FLUX backend
+ IMAGE_BACKEND=ideogram -> Ideogram backend
+ IMAGE_BACKEND=qwen -> Alibaba Qwen image backend
+ IMAGE_BACKEND=zhipu -> Zhipu GLM-Image backend
+ IMAGE_BACKEND=volcengine -> Volcengine Seedream backend
IMAGE_BACKEND=siliconflow -> SiliconFlow backend
- IMAGE_BACKEND=fal -> fal.ai backend
- IMAGE_BACKEND=replicate -> Replicate backend
+ IMAGE_BACKEND=fal -> fal.ai backend
+ IMAGE_BACKEND=replicate -> Replicate backend
+ IMAGE_BACKEND=openrouter -> OpenRouter backend
Configuration source:
1. Current process environment variables
@@ -59,6 +60,7 @@ IMAGE_ENV_PREFIXES = (
"SILICONFLOW_",
"FAL_",
"REPLICATE_",
+ "OPENROUTER_",
)
DEPRECATED_IMAGE_KEYS = {
"IMAGE_API_KEY",
@@ -171,6 +173,13 @@ BACKEND_REGISTRY = {
"default_model": "black-forest-labs/flux-1.1-pro",
"key_hint": "REPLICATE_API_TOKEN / REPLICATE_API_KEY",
},
+ "openrouter": {
+ "module": "backend_openrouter",
+ "tier": "experimental",
+ "label": "OpenRouter",
+ "default_model": "google/gemini-3.1-flash-image-preview",
+ "key_hint": "OPENROUTER_API_KEY",
+ },
}
TIER_ORDER = {"core": 0, "extended": 1, "experimental": 2}