菜单
Use "aigc-cli image" with OpenRouter to generate images via the Responses API. Supports text-to-image with aspect ratio control. Automatically detects OpenRouter from --api-base / OPENAI_BASE_URL and uses POST /v1/responses with image output modalities.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Use "aigc-cli midjourney" (alias "mj") to generate and edit images via Midjourney on APIMart. Supports imagine, blend, describe, edits, upscale, variation, reroll, zoom, pan, inpaint, modal, video, remix. All async task-based. Automatically polls task and downloads results.
Use "aigc-cli image" to generate images via OpenAI-compatible APIs (APIMart, OpenAI, OpenRouter). Supports text-to-image, image-to-image, inpainting, Grok Imagine Edit (--edit), local file upload, dry-run, proxy, sync/async mode detect. Automatically polls task and downloads images.
Use "aigc-cli video" to generate videos via the APIMart API (doubao-seedance-2.0, VEO3). Supports text-to-video, image-to-video, first/last frame, reference video/audio, audio-enabled video, VEO3 Remix (--remix), seed, web_search tool, and return-last-frame for continuation. Automatically polls task and downloads videos.
Use "aigc-cli video" with OpenRouter to generate videos via the dedicated video API. Supports text-to-video, image-to-video (first frame), aspect ratio, resolution, and duration control. Uses async submit → poll → download pattern.
| name | aigc-cli-openrouter-images |
| description | Use "aigc-cli image" with OpenRouter to generate images via the Responses API. Supports text-to-image with aspect ratio control. Automatically detects OpenRouter from --api-base / OPENAI_BASE_URL and uses POST /v1/responses with image output modalities. |
通过 aigc-cli image 调用 OpenRouter 的 Responses API（POST /v1/responses）生成图片。支持 google/gemini-3.1-flash-image-preview 等原生图片输出模型。
自动兼容：当 --api-base 或 OPENAI_BASE_URL 指向 openrouter.ai 时，工具自动使用 Responses API（而不是标准 OpenAI /v1/images/generations 端点）。
aigc-cli（go install 或 make build）export OPENAI_API_KEY="sk-or-xxx"
export OPENAI_BASE_URL="https://openrouter.ai/api/v1"
~/.config/aigc-cli/config.yaml 中配置：
api_key: "sk-or-xxx"
base_url: "https://openrouter.ai/api/v1"
google/gemini-3.1-flash-image-preview 等原生图片输出模型# 设置 OpenRouter
export OPENAI_API_KEY="sk-or-xxx"
export OPENAI_BASE_URL="https://openrouter.ai/api/v1"
# 生成图片（自动识别 OpenRouter，使用 Responses API）
aigc-cli image --prompt "A red panda wearing sunglasses" \
--model "google/gemini-3.1-flash-image-preview"
aigc-cli image --prompt "Futuristic cityscape at night" \
--model "google/gemini-3.1-flash-image-preview" \
--size "16:9"
支持 --size（宽高比，如 16:9、1:1、4:3）和 --resolution（如 1k、2k）。
虽然 DALL-E 模型走标准 /v1/images/generations 端点，但 OpenRouter 也支持：
# DALL-E 3（标准 OpenAI 兼容路径）
aigc-cli image --prompt "a cat" \
--model "openai/dall-e-3" \
--size "1024x1024"
当模型是 openai/dall-e-* 时，可以强制走同步模式：
aigc-cli image --prompt "a cat" \
--model "openai/dall-e-3" \
--mode sync
注意：Responses API 和标准 generations 端点会自动路由。OpenRouter 域名下默认使用 Responses API。
aigc-cli image \
--prompt "提示词" \
--model "google/gemini-3.1-flash-image-preview" \
--size "16:9" \
--resolution "2k"
aigc-cli image --json '{
"model": "google/gemini-3.1-flash-image-preview",
"prompt": "your prompt",
"size": "16:9",
"resolution": "2k"
}'
| 模型 ID | 说明 |
|---|---|
google/gemini-3.1-flash-image-preview | Gemini 原生图片输出（默认推荐） |
google/gemini-2.5-flash-image | Gemini 图片输出（旧版） |
openai/dall-e-3 | DALL-E 3（走同步模式） |
openai/dall-e-2 | DALL-E 2（走同步模式） |
使用 aigc-cli models 查看完整模型列表。
# 查看请求详情
aigc-cli image --prompt "test" -v
# Dry-run 查看 curl
aigc-cli image --prompt "test" --dry-run
# 指定输出目录
aigc-cli image --prompt "test" --output ./downloads
--size/--resolution 参数--dry-run 确认请求参数