local_gpu_recommend_models
Selects a confirmed local GPU model and alternatives for image generation tasks, matching your operation, profile, and VRAM constraints, then presents the route for confirmation.
Instructions
Recommend one exact confirmed-capability route and at most two alternatives. preferred_model_id must be an exact catalog ID. Display the selected route and start_run_boundary, then wait for later user confirmation before local_gpu_start_run.
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"authorization_scope": "<authorization_scope>",
"operation": "<operation>",
"profile": "<profile>",
"style": "<style>",
"width": "<width>",
"height": "<height>",
"affinity_tags": "<affinity_tags>",
"required_vram_gb": "<required_vram_gb>",
"preferred_model_id": "<preferred_model_id>"
},
"name": "local_gpu_recommend_models"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| style | Yes | ||
| width | Yes | ||
| height | Yes | ||
| profile | Yes | ||
| operation | Yes | ||
| affinity_tags | Yes | ||
| regional_layout | No | ||
| required_vram_gb | Yes | ||
| two_stage_layout | No | ||
| preferred_model_id | Yes | ||
| authorization_scope | Yes |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||