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

feat(image): support custom image generation provider

Browse Source 
Addresses #4132.

Add CustomImageGenerationClient for any OpenAI-compatible image generation
API (POST {apiBase}/images/generations). Uses the existing providers.custom
config slot. No schema changes required.

Tests: 54 passed, ruff clean.
Signed-off-by: axelray-dev <110029405+axelray-dev@users.noreply.github.com>
This commit is contained in:
axelray-dev
2026-06-05 15:56:03 +08:00
committed by Xubin Ren
parent c574b028c1
commit 748b28da01
3 changed files with 172 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/image-generation.md
+27 -1
View File
@@ -46,7 +46,7 @@ The WebUI hides provider storage details from the user. The agent sees the saved
| Option | Type | Default | Description |
|--------|------|---------|-------------|
| `tools.imageGeneration.enabled` | boolean | `false` | Register the `generate_image` tool |
| `tools.imageGeneration.provider` | string | `"openrouter"` | Image provider name. Supported values: `openrouter`, `aihubmix`, `minimax`, `gemini`, `ollama`, `stepfun`, `zhipu` |
| `tools.imageGeneration.provider` | string | `"openrouter"` | Image provider name. Supported values: `openrouter`, `custom`, `aihubmix`, `minimax`, `gemini`, `ollama`, `stepfun`, `zhipu` |
| `tools.imageGeneration.model` | string | `"openai/gpt-5.4-image-2"` | Provider model name |
| `tools.imageGeneration.defaultAspectRatio` | string | `"1:1"` | Default ratio when the prompt/tool call does not specify one |
| `tools.imageGeneration.defaultImageSize` | string | `"1K"` | Default size hint, for example `1K`, `2K`, `4K`, or `1024x1024` |
@@ -84,6 +84,32 @@ OpenRouter uses a chat-completions style image response. Configure:
Use a model that supports image generation and image editing if you want reference-image edits.
### Custom (OpenAI-compatible)
Any OpenAI-compatible image generation API can be used with the `custom` provider. This includes local Stable Diffusion servers, Replicate, Agnes AI, and similar services that expose the `/v1/images/generations` endpoint.
Configure:
```json
{
"providers": {
"custom": {
"apiKey": "${CUSTOM_IMAGE_API_KEY}",
"apiBase": "https://api.example.com/v1"
}
},
"tools": {
"imageGeneration": {
"enabled": true,
"provider": "custom",
"model": "your-model-name"
}
}
}
```
The `apiBase` is required. The provider sends requests to `{apiBase}/images/generations` using the OpenAI Images API format with `response_format: "b64_json"`.
### AIHubMix
AIHubMix `gpt-image-2-free` is supported through AIHubMix's unified predictions API. Internally nanobot calls: