ImageGeneration
Generate images with LLMs using a natural language prompt.

Generate an image with LLMs

Generate images with LLMs using a natural language prompt.

yaml
type: "io.kestra.plugin.ai.completion.ImageGeneration"

Examples

Generate an image using OpenAI (DALL-E 3)

yaml
id: image_generation
namespace: company.ai

tasks:
  - id: image_generation
    type: io.kestra.plugin.ai.completion.ImageGeneration
    prompt: >
      Four-panel comic page about a data engineer shipping a workflow.
      Clean modern line art with soft colors and ample white space.
      Panel 1: Early morning desk setup with dual monitors, coffee, and a workflow DAG on screen; calm focused mood.
      Panel 2: Debugging a failing task; close-up of terminal and error icon; speech bubble: "hmm…"
      Panel 3: Fix applied; green checks ripple through the pipeline; small celebratory detail (cat paw, fist pump).
      Panel 4: Deployed dashboard showing metrics trending up; sticky note says "ship it".
      Include subtle tech props (cloud icons, database cylinder) but no logos.
      Minimal readable text only in tiny bubbles/notes; no large paragraphs of text.
    provider:
      type: io.kestra.plugin.ai.provider.OpenAI
      apiKey: "{{ kv('OPENAI_API_KEY') }}"
      modelName: dall-e-3

Properties

prompt*string

Image prompt

The input prompt for the image generation model

provider*

Language Model Provider

Definitions

Amazon Bedrock Model Provider

accessKeyId*string

AWS Access Key ID

modelName*string

secretAccessKey*string

AWS Secret Access Key

type*object

baseUrlstring

caPemstring

clientPemstring

modelTypestring

DefaultCOHERE

Possible Values

COHERETITAN

Amazon Bedrock Embedding Model Type

Anthropic AI Model Provider

apiKey*string

modelName*string

type*object

baseUrlstring

caPemstring

clientPemstring

maxTokensintegerstring

Maximum Tokens

Specifies the maximum number of tokens that the model is allowed to generate in its response.

Azure OpenAI Model Provider

endpoint*string

API endpoint

The Azure OpenAI endpoint in the format: https://{resource}.openai.azure.com/

modelName*string

type*object

apiKeystring

baseUrlstring

caPemstring

clientIdstring

Client ID

clientPemstring

clientSecretstring

Client secret

serviceVersionstring

API version

tenantIdstring

Tenant ID

DashScope (Qwen) Model Provider from Alibaba Cloud

apiKey*string

modelName*string

type*object

baseUrlstring

Defaulthttps://dashscope-intl.aliyuncs.com/api/v1

text

If you use a model in the China (Beijing) region, you need to replace the URL with: https://dashscope.aliyuncs.com/api/v1,
otherwise use the Singapore region of: "https://dashscope-intl.aliyuncs.com/api/v1.
The default value is computed based on the system timezone.

caPemstring

clientPemstring

enableSearchbooleanstring

Whether the model uses Internet search results for reference when generating text or not

maxTokensintegerstring

repetitionPenaltynumberstring

Repetition in a continuous sequence during model generation

text

Increasing repetition_penalty reduces the repetition in model generation,
1.0 means no penalty. Value range: (0, +inf)

Deepseek Model Provider

apiKey*string

modelName*string

type*object

baseUrlstring

Defaulthttps://api.deepseek.com/v1

caPemstring

clientPemstring

GitHub Models AI Model Provider

gitHubToken*string

GitHub Token

Personal Access Token (PAT) used to access GitHub Models.

modelName*string

type*object

baseUrlstring

caPemstring

clientPemstring

Google Gemini Model Provider

apiKey*string

modelName*string

type*object

baseUrlstring

caPemstring

clientPemstring

Google VertexAI Model Provider

endpoint*string

Endpoint URL

location*string

Project location

modelName*string

project*string

Project ID

type*object

baseUrlstring

caPemstring

clientPemstring

HuggingFace Model Provider

apiKey*string

modelName*string

type*object

baseUrlstring

Defaulthttps://router.huggingface.co/v1

caPemstring

clientPemstring

LocalAI Model Provider

baseUrl*string

modelName*string

type*object

caPemstring

clientPemstring

Mistral AI Model Provider

apiKey*string

modelName*string

type*object

baseUrlstring

caPemstring

clientPemstring

OciGenAI Model Provider

compartmentId*string

OCID of OCI Compartment with the model

modelName*string

region*string

OCI Region to connect the client to

type*object

authProviderstring

OCI SDK Authentication provider

baseUrlstring

caPemstring

clientPemstring

Ollama Model Provider

endpoint*string

Model endpoint

modelName*string

type*object

baseUrlstring

caPemstring

clientPemstring

OpenAI Model Provider

apiKey*string

modelName*string

type*object

baseUrlstring

Defaulthttps://api.openai.com/v1

caPemstring

clientPemstring

OpenRouter Model Provider

apiKey*string

modelName*string

type*object

baseUrlstring

caPemstring

clientPemstring

WorkersAI Model Provider

accountId*string

Account Identifier

Unique identifier assigned to an account

apiKey*string

modelName*string

type*object

baseUrlstring

Base URL

Custom base URL to override the default endpoint (useful for local tests, WireMock, or enterprise gateways).

caPemstring

clientPemstring

ZhiPu AI Model Provider

apiKey*string

API Key

modelName*string

Model name

type*object

baseUrlstring

Defaulthttps://open.bigmodel.cn/

API base URL

The base URL for ZhiPu API (defaults to https://open.bigmodel.cn/)

caPemstring

CA PEM certificate content

CA certificate as text, used to verify SSL/TLS connections when using custom endpoints.

clientPemstring

Client PEM certificate content

PEM client certificate as text, used to authenticate the connection to enterprise AI endpoints.

maxRetriesintegerstring

The maximum retry times to request

maxTokenintegerstring

The maximum number of tokens returned by this request

stopsarray

SubTypestring

With the stop parameter, the model will automatically stop generating text when it is about to contain the specified string or token_id

Outputs

finishReasonstring

Possible Values

STOPLENGTHTOOL_EXECUTIONCONTENT_FILTEROTHER

Finish reason

imageUrlstring

Generated image URL

The URL of the generated image

tokenUsage

Token usage

Definitions

io.kestra.plugin.ai.domain.TokenUsage

inputTokenCountinteger

outputTokenCountinteger

totalTokenCountinteger

Metrics

input.token.countcounter

Unittoken

Large Language Model (LLM) input token count

output.token.countcounter

Unittoken

Large Language Model (LLM) output token count

total.token.countcounter

Unittoken

Large Language Model (LLM) total token count

Opensearch (EE)

This sub-group of plugins contains tasks for using Opensearch EE. Opensearch is a distributed, RESTful search and analytics engine capable of addressing a growing number of use cases.

Database

OpenSearch

This sub-group of plugins contains tasks for using Opensearch. Opensearch is a distributed, RESTful search and analytics engine capable of addressing a growing number of use cases.

Database