feat: 增加skill

This commit is contained in:
2026-04-18 20:02:26 +08:00
parent 9bc28e852c
commit 2723adf2d2
7 changed files with 1557 additions and 0 deletions
+67
View File
@@ -0,0 +1,67 @@
---
name: image-generation
description: Generate images using MiniMax API with support for custom prompts, aspect ratios, and multiple image generation.
metadata: {"clawdbot":{"emoji":"🎨","os":["linux","darwin","win32"]}}
---
# MiniMax Image Generation SKILL
## Description
Generate images using MiniMax API. Supports custom prompts, aspect ratios, generation count, and more.
## Usage
```bash
python scripts/run.py --api-key "your-api-key" --prompt "your-prompt" [options]
```
## Arguments
| Argument | Type | Required | Default | Description |
|----------|------|----------|---------|-------------|
| `--api-key` | string | Yes | - | MiniMax API key (can also be set via `MINIMAX_API_KEY` env var) |
| `--prompt` | string | Yes | - | Image generation prompt |
| `--model` | string | No | `image-01` | Image generation model |
| `--aspect-ratio` | string | No | `1:1` | Image aspect ratio (e.g., 16:9, 1:1, 9:16) |
| `--response-format` | string | No | `url` | Response format (`url` or `base64`) |
| `--n` | int | No | `1` | Number of images to generate (1-3) |
| `--prompt-optimizer` | bool | No | `false` | Enable prompt optimizer |
| `--subject-reference` | string | No | - | Reference image URL or local file path for image-to-image generation |
| `--subject-type` | string | No | `character` | Subject reference type (character, product, logo, video_subject, other) |
| `--seed` | int | No | - | Random seed for reproducible generation |
| `--output-dir` | string | No | `./output` | Output directory for images |
## API Reference
- **Endpoint**: `POST https://api.minimaxi.com/v1/image_generation`
- **Auth**: Bearer Token
## Examples
```bash
python scripts/run.py --api-key "sk-xxx" --prompt "A sunset over the ocean"
# Generate multiple images
python scripts/run.py --api-key "sk-xxx" --prompt "A man in a white t-shirt, full-body, standing front view, outdoors" --n 3 --aspect-ratio "16:9"
# Enable prompt optimizer
python scripts/run.py --api-key "sk-xxx" --prompt "sunset ocean" --prompt-optimizer true
# Image-to-image generation with reference image URL
python scripts/run.py --api-key "sk-xxx" --prompt "A girl looking into the distance from a library window" --subject-reference "https://example.com/reference.jpg" --subject-type "character" --n 2
# Image-to-image with local file
python scripts/run.py --api-key "sk-xxx" --prompt "A girl looking into the distance from a library window" --subject-reference "./my_character.jpg" --subject-type "character"
# Image-to-image with product reference
python scripts/run.py --api-key "sk-xxx" --prompt "A beautiful product shot" --subject-reference "https://example.com/product.jpg" --subject-type "product"
# Use seed for reproducible generation
python scripts/run.py --api-key "sk-xxx" --prompt "A sunset over the ocean" --seed 42
```
## Output
Images are saved to the specified output directory with the naming format: `generated_image_{index}_{timestamp}.{ext}`.
+287
View File
@@ -0,0 +1,287 @@
#!/usr/bin/env python3
# @skill: image-generation
"""
MiniMax Image Generation Script
Generate images using MiniMax API
"""
import argparse
import os
import time
import requests
from urllib.parse import urlparse
def parse_args():
"""Parse command line arguments"""
parser = argparse.ArgumentParser(
description="Generate images using MiniMax API",
formatter_class=argparse.RawDescriptionHelpFormatter
)
parser.add_argument(
"--api-key",
type=str,
required=False,
help="MiniMax API key (can also be set via MINIMAX_API_KEY environment variable)"
)
parser.add_argument(
"--prompt",
type=str,
required=True,
help="Image generation prompt"
)
parser.add_argument(
"--model",
type=str,
default="image-01",
help="Image generation model (default: image-01)"
)
parser.add_argument(
"--aspect-ratio",
type=str,
default="1:1",
help="Image aspect ratio (default: 1:1, options: 16:9, 9:16, etc.)"
)
parser.add_argument(
"--response-format",
type=str,
default="url",
choices=["url", "base64"],
help="Response format (default: url)"
)
parser.add_argument(
"--n",
type=int,
default=1,
choices=[1, 2, 3],
help="Number of images to generate (default: 1, max: 3)"
)
parser.add_argument(
"--prompt-optimizer",
type=lambda x: x.lower() == "true",
default=False,
help="Enable prompt optimizer (default: false)"
)
# Image-to-image (subject reference) parameters
parser.add_argument(
"--subject-reference",
type=str,
default=None,
help="Reference image URL or local file path for image-to-image generation"
)
parser.add_argument(
"--subject-type",
type=str,
default="character",
choices=["character", "product", "logo", "video_subject", "other"],
help="Subject reference type (default: character)"
)
parser.add_argument(
"--seed",
type=int,
default=None,
help="Random seed for reproducible generation (optional)"
)
parser.add_argument(
"--output-dir",
type=str,
default="./output",
help="Output directory for images (default: ./output)"
)
parser.add_argument(
"--api-base",
type=str,
default="https://api.minimaxi.com",
help="API base URL (default: https://api.minimaxi.com)"
)
return parser.parse_args()
def download_image(url: str, output_path: str) -> bool:
"""Download image to local file"""
try:
response = requests.get(url, timeout=30)
response.raise_for_status()
with open(output_path, "wb") as f:
f.write(response.content)
print(f" [OK] Saved: {output_path}")
return True
except Exception as e:
print(f" [FAIL] Download failed: {e}")
return False
def read_local_image(file_path: str) -> str:
"""
Read local image file and return as base64 encoded string.
Returns the base64 string or None if failed.
"""
try:
with open(file_path, "rb") as f:
image_data = f.read()
import base64
return base64.b64encode(image_data).decode("utf-8")
except Exception as e:
print(f" [FAIL] Failed to read local image: {e}")
return None
def build_subject_reference(subject_ref: str, subject_type: str) -> dict:
"""
Build subject_reference object from URL or local file path.
Args:
subject_ref: URL or local file path
subject_type: Type of subject (character, product, logo, etc.)
Returns:
dict with subject_reference structure
"""
# Check if it's a URL or local file
if subject_ref.startswith(("http://", "https://")):
# It's a URL
return {
"type": subject_type,
"image_file": subject_ref
}
else:
# It's a local file - convert to base64
print(f" Processing local image: {subject_ref}")
base64_data = read_local_image(subject_ref)
if base64_data:
return {
"type": subject_type,
"image_file": f"data:image/jpeg;base64,{base64_data}"
}
else:
return None
def generate_images(args):
"""Call MiniMax API to generate images"""
url = f"{args.api_base}/v1/image_generation"
headers = {
"Authorization": f"Bearer {args.api_key}",
"Content-Type": "application/json"
}
payload = {
"model": args.model,
"prompt": args.prompt,
"aspect_ratio": args.aspect_ratio,
"response_format": args.response_format,
"n": args.n,
"prompt_optimizer": args.prompt_optimizer
}
# Add seed if provided
if args.seed is not None:
payload["seed"] = args.seed
# Add subject_reference for image-to-image generation
if args.subject_reference:
subject_ref = build_subject_reference(args.subject_reference, args.subject_type)
if subject_ref:
payload["subject_reference"] = [subject_ref]
else:
print("Warning: Failed to process subject reference, continuing without it.")
print(f"\n{'='*60}")
print(f"MiniMax Image Generation")
print(f"{'='*60}")
print(f"Model: {args.model}")
print(f"Prompt: {args.prompt}")
print(f"Aspect Ratio: {args.aspect_ratio}")
print(f"Number: {args.n}")
print(f"Prompt Optimizer: {'Enabled' if args.prompt_optimizer else 'Disabled'}")
if args.seed is not None:
print(f"Seed: {args.seed}")
if args.subject_reference:
print(f"Subject Reference: {args.subject_type} - {args.subject_reference}")
print(f"{'='*60}\n")
try:
print("Generating images...")
response = requests.post(url, headers=headers, json=payload, timeout=60)
response.raise_for_status()
result = response.json()
if result.get("base_resp", {}).get("status_code") != 0:
error_msg = result.get("base_resp", {}).get("status_msg", "Unknown error")
print(f"API Error: {error_msg}")
return False
# Create output directory
os.makedirs(args.output_dir, exist_ok=True)
# Process returned images
image_urls = result.get("data", {}).get("image_urls", [])
metadata = result.get("metadata", {})
print(f"\nSuccessfully generated {metadata.get('success_count', len(image_urls))} images:")
timestamp = int(time.time())
saved_count = 0
for i, image_url in enumerate(image_urls, 1):
# Extract file extension from URL
parsed = urlparse(image_url)
path = parsed.path
ext = os.path.splitext(path)[1] if "." in path else ".jpeg"
filename = f"generated_image_{i}_{timestamp}{ext}"
output_path = os.path.join(args.output_dir, filename)
if download_image(image_url, output_path):
saved_count += 1
print(f"\n{'='*60}")
print(f"Done! Successfully saved {saved_count}/{len(image_urls)} images")
print(f"Output directory: {os.path.abspath(args.output_dir)}")
print(f"{'='*60}\n")
return saved_count > 0
except requests.exceptions.RequestException as e:
print(f"\nRequest Error: {e}")
return False
except Exception as e:
print(f"\nUnexpected Error: {e}")
return False
def main():
"""Main function"""
args = parse_args()
# Get API key from argument or environment variable (optional)
if not args.api_key:
args.api_key = os.environ.get("MINIMAX_API_KEY", "")
# If still no API key, prompt user to enter it
if not args.api_key:
print("Error: API key not int ENV, and it is required.")
else:
generate_images(args)
if __name__ == "__main__":
main()