Grayscale/nanobot
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

docs(image-generation): add MiniMax to docs and skill

Browse Source 
Updates docs/image-generation.md and skills/image-generation/SKILL.md to
include MiniMax configuration examples, supported aspect ratios, and
troubleshooting references. Also updates the supported provider list to
include minimax alongside openrouter, aihubmix, and gemini.
This commit is contained in:
chengyongru
2026-05-19 15:35:19 +08:00
committed by Xubin Ren
parent c588d56a77
commit 99e4d25d4c
2 changed files with 44 additions and 69 deletions
Download Patch File Download Diff File Expand all files Collapse all files
nanobot/skills/image-generation/SKILL.md
-67
View File
@@ -42,73 +42,6 @@ For follow-up edits, pass the prior artifact `path` to `reference_images`. If th
Do not include internal replay markers such as `[Message Time: ...]`, `[image: /local/path]`, `generate_image(...)`, or `message(...)` in user-facing replies.
## Provider Notes
Do not ask users to paste API keys into chat. If configuration is needed, describe the fields; LLM provider and BYOK changes are hot-reloaded for new turns.
For OpenRouter, the image tool expects:
```json
{
"providers": {
"openrouter": {
"apiKey": "sk-or-..."
}
},
"tools": {
"imageGeneration": {
"enabled": true,
"provider": "openrouter",
"model": "openai/gpt-5.4-image-2"
}
}
}
```
For AIHubMix, the image tool expects:
```json
{
"providers": {
"aihubmix": {
"apiKey": "sk-..."
}
},
"tools": {
"imageGeneration": {
"enabled": true,
"provider": "aihubmix",
"model": "gpt-image-2-free"
}
}
}
```
AIHubMix `gpt-image-2-free` uses AIHubMix's unified predictions endpoint internally (`/v1/models/openai/gpt-image-2-free/predictions`), not the OpenAI Images `/v1/images/generations` endpoint. If it fails with "Incorrect model ID", do not assume the key lacks permission until the provider config, model name, and gateway restart have been checked.
`providers.aihubmix.extraBody` can be used for provider-specific options. For example, `"extraBody": {"quality": "low"}` is optional but can make `gpt-image-2-free` faster and less likely to time out.
For Gemini, the image tool supports two model families. Imagen 4 (`imagen-4.0-generate-001`) supports text-to-image only. Gemini Flash (`gemini-2.5-flash-image`) also supports reference-image edits. Configuration:
```json
{
"providers": {
"gemini": {
"apiKey": "AIza..."
}
},
"tools": {
"imageGeneration": {
"enabled": true,
"provider": "gemini",
"model": "imagen-4.0-generate-001"
}
}
}
```
For Gemini models, `defaultImageSize` has no effect; use `defaultAspectRatio` instead. Imagen 4 supports `1:1`, `9:16`, `16:9`, `3:4`, and `4:3`.
## Examples
Generate a new image: