The image-generation skill handles text-to-image, image-to-image and multi-image fusion across OpenAI, Gemini, Seedream, Qwen, MiniMax and more, with automatic routing and fallback between providers.
A general-purpose image generation and editing skill supporting seven providers: OpenAI, Gemini, Seedream (Volcengine Ark), Qwen (DashScope), MiniMax, CowAgent, and LinkAI. Configure any one provider’s key to start using it; configure multiple to enable automatic fallback.
It is recommended to configure providers from the “Model Management” page in the Web console. Chat model keys configured there are automatically reused by the image generation skill — no need to set them twice. You can also edit the configuration file manually or temporarily set keys in a conversation using the env_config tool.
Credentials are shared with the main model providers:
Field
Provider
openai_api_key
OpenAI
gemini_api_key
Gemini
ark_api_key
Volcengine Ark (Seedream)
dashscope_api_key
Alibaba DashScope (Qwen)
minimax_api_key
MiniMax
cowagent_api_key
CowAgent (Global keys also need cowagent_api_base set to https://api.cowagent.ai/v1; the default is the China site)
linkai_api_key
LinkAI
Enabling and Disabling
The skill automatically adjusts its status based on API keys:
Key configured: the Agent calls the skill directly when it receives a drawing request
Key not configured: the skill still appears in context (marked as “needs configuration”) — the Agent will guide the user to set up a key
Higher quality and larger size cost more and take longer. The gpt-image-2.6 series defaults to high quality. For faster or cheaper results, pass quality=low + size=1K — about 20 seconds per image; quality=high + size=2K/4K may take 1–5 minutes.
Common Use Cases
Text-to-image: generate illustrations, posters, icons, avatars, storyboards, etc. from a description
Image-to-image: change styles, swap elements, add decorations or text on an existing image
Multi-image fusion: combine multiple reference images into one (outfit swaps, character group photos, etc.)
Bash timeout should be set to 600 seconds: each provider has a 300-second HTTP timeout, and the script may try multiple providers sequentially
Input images are automatically compressed to ≤ 4 MB with the longest edge ≤ 4096 px
Gemini / Seedream / Qwen / MiniMax do not support the quality parameter
Seedream defaults to 2K; seedream-5.0-lite supports up to 3K; seedream-4.5 supports up to 4K