---
title: "generate_image: Generate image"
description: "Make an image in the user's Kuro account."
canonical_url: "https://meetkuro.com/agents/tools/generate_image/"
updated: 2026-11-03
locale: "en"
tool: "generate_image"
scopes: ["generation.write"]
---

# generate_image

**Generate image**

Make an image in the user's Kuro account. This spends credits, or runs on the user's own key (get_credits), and waits for the image, so a quick one comes back ready in this call.
Search list_recipes and read promising matches with get_recipe before choosing a model. Prefer a close-fitting recipe through generate_with_recipe; use this direct tool when none fits, with parameters from the chosen model's guide.
Only if it comes back still queued or generating, call get_generation once: it waits for the result. Presets from list_presets add Style, Lighting and Framing through the presets map; a guided recipe runs through generate_with_recipe instead. Name the account's Subjects in `subjects` rather than attaching pictures of them. list_models carries each model's full envelope.
To change something about an image that already exists, call edit_image instead. Re-sending an edited prompt here is a fresh roll of the dice — a different composition, different light, a different picture — not an edit of the one on screen.
Models (credits per image at the default setting; reference images):
- seedream-5-lite: ~3, 7 refs
- nano-banana-2.1: ~3, 14 refs
- nano-banana-2: ~6, 7 refs
- gpt-image-2.5-flare: ~11, 7 refs
- gpt-image-2.5-sunburst: ~11, 7 refs
- gpt-image-2: ~11, 7 refs
- nano-banana-2-lite: ~3, 7 refs
- seedream-5-pro: ~4, 7 refs
- flux-schnell: ~0.5, no refs
- flux-2-flex: ~5, 7 refs
- flux-2-pro: ~2.5, 7 refs
- flux-2-max: ~6, 7 refs
- recraft-v4.1-svg: ~3.5, no refs, SVG
- recraft-v4.1-pro-svg: ~21, no refs, SVG
- p-image: ~0.5, no refs
- grok-imagine-image: ~2, 1 refs
- grok-imagine-image-quality: ~6, 1 refs
- krea-3: ~5, 8 refs
- qwen-image-3-pro: ~3.5, 1 refs
- soul-2: ~0.5, no refs

## Scope

- `generation.write` — Makes, edits, imports, shares and deletes media in the account.

## Behaviour

- **Writes**: Creates or changes items in the caller's own account.
- **Adds or updates**: Adds or updates; nothing the caller already has is deleted or overwritten.
- **Stays in the account**: Stays inside the caller's private Kuro account: any media provider it calls acts on Kuro's account, and the result is visible to no one else.

## Credits

What the tool's description says about credits, verbatim:

- This spends credits, or runs on the user's own key (get_credits), and waits for the image, so a quick one comes back ready in this call.

## Inputs

| Name | Type | Required | Details |
| --- | --- | --- | --- |
| `idempotency_key` | string | no | Optional. Pass the same value to retry one operation without spending twice; omit it for a new operation. Different arguments under a reused key are refused. — at least 1 character; at most 128 characters |
| `prompt` | string | no | at most 2000 characters; default "" |
| `model` | string | no | one of "seedream-5-lite", "nano-banana-2.1", "nano-banana-2", "gpt-image-2.5-flare", "gpt-image-2.5-sunburst", "gpt-image-2", "nano-banana-2-lite", "seedream-5-pro", "flux-schnell", "flux-2-flex", "flux-2-pro", "flux-2-max", "recraft-v4.1-svg", "recraft-v4.1-pro-svg", "p-image", "grok-imagine-image", "grok-imagine-image-quality", "krea-3", "qwen-image-3-pro", "soul-2" |
| `aspect_ratio` | string | no | Defaults to 9:16 (vertical). Confirm the shape with the user when the destination is unclear — a feed, a banner and a phone screen want different ones. — one of "1:1", "1:2", "1:4", "1:8", "2:1", "2:3", "3:2", "3:4", "4:1", "4:3", "4:5", "5:4", "8:1", "9:16", "16:9", "21:9" |
| `setting` | string | no | — |
| `presets` | object | no | fields: style, motion, lighting, framing |
| `recreate_of` | string | no | uuid |
| `references` | array of object (type: "upload") or object (type: "generation") | no | The pictures this generation can see — uploads and generations alike, in the shape list_media returns. This is the only field that carries image data into the model. The selected model’s reference capacity applies (list_models). |
| `subjects` | array of string | no | Names or ids of the account's Subjects (list_subjects). The server supplies each one's face and description — seated against the model's capacity — so do not also attach pictures of them. — at most 4 items |
| `refined_from` | string | no | Lineage only — this records that the new image is the next version of that one, and carries NO pixels. Put the same generation in `references` or the model sees no picture. Prefer edit_image, which sets both from one id; reach for this only to hand-assemble a refine edit_image cannot express. — uuid |
| `runs_on` | string | no | Who pays: "credits", or one of the user's own keys by vendor (get_credits lists them). Leave out to follow their payer order; set it only when the user chose. — one of "credits", "replicate", "fal", "siray", "runware", "higgsfield", "sunra", "comfy" |

## Example call

A `tools/call` request with the required arguments only, each a placeholder read off the schema. Replace them before sending.

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "generate_image",
    "arguments": {}
  }
}
```

## Input schema

As the server sends it in `tools/list`:

```json
{
  "type": "object",
  "properties": {
    "idempotency_key": {
      "type": "string",
      "minLength": 1,
      "maxLength": 128,
      "description": "Optional. Pass the same value to retry one operation without spending twice; omit it for a new operation. Different arguments under a reused key are refused."
    },
    "prompt": {
      "type": "string",
      "maxLength": 2000,
      "default": ""
    },
    "model": {
      "type": "string",
      "enum": [
        "seedream-5-lite",
        "nano-banana-2.1",
        "nano-banana-2",
        "gpt-image-2.5-flare",
        "gpt-image-2.5-sunburst",
        "gpt-image-2",
        "nano-banana-2-lite",
        "seedream-5-pro",
        "flux-schnell",
        "flux-2-flex",
        "flux-2-pro",
        "flux-2-max",
        "recraft-v4.1-svg",
        "recraft-v4.1-pro-svg",
        "p-image",
        "grok-imagine-image",
        "grok-imagine-image-quality",
        "krea-3",
        "qwen-image-3-pro",
        "soul-2"
      ]
    },
    "aspect_ratio": {
      "type": "string",
      "enum": [
        "1:1",
        "1:2",
        "1:4",
        "1:8",
        "2:1",
        "2:3",
        "3:2",
        "3:4",
        "4:1",
        "4:3",
        "4:5",
        "5:4",
        "8:1",
        "9:16",
        "16:9",
        "21:9"
      ],
      "description": "Defaults to 9:16 (vertical). Confirm the shape with the user when the destination is unclear — a feed, a banner and a phone screen want different ones."
    },
    "setting": {
      "type": "string"
    },
    "presets": {
      "type": "object",
      "properties": {
        "style": {
          "anyOf": [
            {
              "type": "string",
              "minLength": 1,
              "maxLength": 80
            },
            {
              "type": "null"
            }
          ]
        },
        "motion": {
          "anyOf": [
            {
              "$ref": "#/properties/presets/properties/style/anyOf/0"
            },
            {
              "type": "null"
            }
          ]
        },
        "lighting": {
          "anyOf": [
            {
              "$ref": "#/properties/presets/properties/style/anyOf/0"
            },
            {
              "type": "null"
            }
          ]
        },
        "framing": {
          "anyOf": [
            {
              "$ref": "#/properties/presets/properties/style/anyOf/0"
            },
            {
              "type": "null"
            }
          ]
        }
      },
      "additionalProperties": false
    },
    "recreate_of": {
      "type": "string",
      "format": "uuid"
    },
    "references": {
      "type": "array",
      "items": {
        "anyOf": [
          {
            "type": "object",
            "properties": {
              "type": {
                "type": "string",
                "const": "upload"
              },
              "upload_id": {
                "type": "string",
                "format": "uuid"
              }
            },
            "required": [
              "type",
              "upload_id"
            ],
            "additionalProperties": false
          },
          {
            "type": "object",
            "properties": {
              "type": {
                "type": "string",
                "const": "generation"
              },
              "generation_id": {
                "type": "string",
                "format": "uuid"
              }
            },
            "required": [
              "type",
              "generation_id"
            ],
            "additionalProperties": false
          }
        ]
      },
      "description": "The pictures this generation can see — uploads and generations alike, in the shape list_media returns. This is the only field that carries image data into the model. The selected model’s reference capacity applies (list_models)."
    },
    "subjects": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "maxItems": 4,
      "description": "Names or ids of the account's Subjects (list_subjects). The server supplies each one's face and description — seated against the model's capacity — so do not also attach pictures of them."
    },
    "refined_from": {
      "type": "string",
      "format": "uuid",
      "description": "Lineage only — this records that the new image is the next version of that one, and carries NO pixels. Put the same generation in `references` or the model sees no picture. Prefer edit_image, which sets both from one id; reach for this only to hand-assemble a refine edit_image cannot express."
    },
    "runs_on": {
      "type": "string",
      "enum": [
        "credits",
        "replicate",
        "fal",
        "siray",
        "runware",
        "higgsfield",
        "sunra",
        "comfy"
      ],
      "description": "Who pays: \"credits\", or one of the user's own keys by vendor (get_credits lists them). Leave out to follow their payer order; set it only when the user chose."
    }
  },
  "additionalProperties": false
}
```

## Related tools

- [`get_credits`](https://meetkuro.com/agents/tools/get_credits.md): Use only the account's existing entitlements: when work is unavailable, explain the limit without offering purchases, upgrades, subscriptions or checkout links.
- [`list_recipes`](https://meetkuro.com/agents/tools/list_recipes.md): Search and page through the RECIPE catalog — templates that ask you questions and then make something.
- [`get_recipe`](https://meetkuro.com/agents/tools/get_recipe.md): Get one recipe by id — a look or a guided recipe, with its recommended models, creative guidance, and media slots.
- [`generate_with_recipe`](https://meetkuro.com/agents/tools/generate_with_recipe.md): Create one image or clip with a guided recipe — an arm or reprompt recipe.
- [`get_generation`](https://meetkuro.com/agents/tools/get_generation.md): Get current status and signed media URL for one generation.
- [`list_presets`](https://meetkuro.com/agents/tools/list_presets.md): Search and page through Style, Motion, Lighting and Framing presets.
- [`list_models`](https://meetkuro.com/agents/tools/list_models.md): Read the full capability envelope for the models a room can run: aspect ratios, durations, resolutions, reference capacities, which inputs a model requires, and — for voice — its complete voice roster and the languages it speaks.
- [`edit_image`](https://meetkuro.com/agents/tools/edit_image.md): Change one thing about an image already in the account, keeping everything else.

---

## About Kuro

Kuro is an AI picture studio: prompt-driven images, clips, voice-overs and music, and storyboard-backed films with consistent characters across every scene.

Agents connect over MCP and can generate directly:

```
claude mcp add kuro https://api.meetkuro.com/mcp --transport http
```

The app is at https://app.meetkuro.com and requires an account.

Each guide, model page, comparison and free tool page on this site (not a tool's variants, and not the index pages) has a Markdown twin at its own URL plus `.md`, and so do /benchmarks/, the English /agents/ page (as /agents.md) and the MCP tool reference. Every tool: https://meetkuro.com/agents/tools/