minimax-image-gen
MiniMax 图像生成 - 使用 image-01 模型,支持文生图和图生图。通过 MiniMax 中国区 API(api.minimaxi.com)。
Instalar com Codex ou Claude Copie este prompt, cole no Codex, Claude ou outro assistente e deixe que ele revise a página da skill e instale para você.
Menu
MiniMax 图像生成 - 使用 image-01 模型,支持文生图和图生图。通过 MiniMax 中国区 API(api.minimaxi.com)。
Instalar com Codex ou Claude Copie este prompt, cole no Codex, Claude ou outro assistente e deixe que ele revise a página da skill e instale para você.
Baseado na classificação ocupacional SOC
🧠 ontology-clawra v5.1 - Local Ontology Reasoning & Learning Engine **USE THIS SKILL WHENEVER** you need structured reasoning, knowledge graph management, logical inference, or learning from interactions. This is your go-to tool for: - Building and querying ontology knowledge graphs (concepts, entities, relationships) - Performing confidence-based reasoning with evidence tracking - Recording insights and patterns from completed tasks - Local memory search and knowledge retrieval **Key Use Cases:** - Before making complex decisions: "Let me use ontology-clawra to reason about this" - After completing tasks: "Record this learning to ontology-clawra" - Building domain expertise: "Create concepts for [domain] in ontology-clawra" - Analyzing patterns: "Query ontology-clawra for similar past cases" **Core Capabilities:** ✅ Local ontology storage in `~/.openclaw/skills/ontology-clawra/memory/` ✅ Confidence calculation (CONFIRMED/ASSUMED/SPECULATIVE) ✅ Learning from user confirmations ✅ Local memory search (no ne
Complete guide to using and extending Hermes Agent — CLI usage, setup, configuration, spawning additional agents, gateway platforms, skills, voice, tools, profiles, and a concise contributor reference. Load this skill when helping users configure Hermes, troubleshoot issues, spawn agent instances, or make code contributions.
Git push to HTTPS remote using token authentication — avoids SSH setup, works in CI/automated environments.
从 GitHub 历史中彻底清除敏感文件的完整流程 — 使用 git filter-repo + force push,适用于清理意外提交的个人文件、工作文件等
清理 GitHub 历史和 ClawHub 中意外泄露的个人/工作文件
Configure WhatsApp and Telegram messaging platforms on Hermes Agent
| name | minimax-image-gen |
| description | MiniMax 图像生成 - 使用 image-01 模型,支持文生图和图生图。通过 MiniMax 中国区 API(api.minimaxi.com)。 |
| metadata | {"openclaw":{"emoji":"🖼️","requires":{"env":["MINIMAX_CN_API_KEY"]},"primaryEnv":"MINIMAX_CN_API_KEY"}} |
使用 MiniMax image-01 模型生成图片,支持文生图(text-to-image)和图生图(image-to-image)。
# 必须:MiniMax 中国区 API Key
export MINIMAX_CN_API_KEY="your-api-key"
# 可选:自定义 base URL(默认已配好)
export MINIMAX_CN_BASE_URL="https://api.minimaxi.com/v1"
https://api.minimaxi.com/v1/image_generationimage-01(MiniMax 官方图像生成模型)MINIMAX_CN_API_KEY 读取)import requests
import os
api_key = os.getenv("MINIMAX_CN_API_KEY")
url = "https://api.minimaxi.com/v1/image_generation"
headers = {
"Authorization": f"Bearer {api_key}",
"Content-Type": "application/json"
}
payload = {
"model": "image-01",
"prompt": "a beautiful Chinese woman, 28 years old, elegant makeup, stylish outfit, full-body shot",
"aspect_ratio": "1:1",
"response_format": "base64"
}
response = requests.post(url, headers=headers, json=payload)
data = response.json()
# 保存图片
import base64
for i, img_b64 in enumerate(data["data"]["image_base64"]):
with open(f"output_{i}.jpg", "wb") as f:
f.write(base64.b64decode(img_b64))
payload = {
"model": "image-01",
"prompt": "change the background to a beach sunset",
"image_file": "https://example.com/input.jpg", # 支持 URL
"aspect_ratio": "16:9",
"response_format": "base64"
}
生成 Clawra 自拍时使用:
A stunningly beautiful young Chinese woman, extremely gorgeous and glamorous like Ada Wong from Resident Evil 4 Remake. Long flowing black hair, signature red lipstick, seductive cat eye makeup, flawless porcelain skin. Taking a full-body mirror selfie wearing an elegant tight black mini dress with black stockings and high heels, holding phone up for selfie shot. Luxury hotel bedroom mirror reflection, soft dramatic lighting, ultra realistic photography, 8K quality, breathtaking beauty, confident and alluring expression
| 参数 | 类型 | 说明 |
|---|---|---|
model | string | 模型名,默认 image-01 |
prompt | string | 图片描述(英文效果更稳定) |
image_file | string | 可选,参考图片 URL,用于图生图 |
aspect_ratio | string | 比例,如 1:1、16:9、9:16、3:4 |
response_format | string | base64 或 url,默认 base64 |
python3 gen.py --prompt "a beautiful Chinese woman, elegant, 28 years old" --aspect_ratio "3:4"
n 参数)