> ## Documentation Index
> Fetch the complete documentation index at: https://docs.ag2.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# autogen.agentchat.contrib.capabilities.generate_images.ImageGeneration

<h2 id="autogen.agentchat.contrib.capabilities.generate_images.ImageGeneration" class="doc doc-heading">
  <code class="doc-symbol doc-symbol-heading doc-symbol-class" />

  <span class="doc doc-object-name doc-class-name">ImageGeneration</span>
</h2>

```python theme={null}
ImageGeneration(
    image_generator: ImageGenerator,
    cache: AbstractCache | None = None,
    text_analyzer_llm_config: LLMConfig | dict[str, Any] | None = None,
    text_analyzer_instructions: str = 'In detail, please summarize the provided prompt to generate the image described in the TEXT.\nDO NOT include any advice. RESPOND like the following example:\nEXAMPLE: Blue background, 3D shapes, ...\n',
    verbosity: int = 0,
    register_reply_position: int = 2
)
```

This capability allows a ConversableAgent to generate images based on the message received from other Agents.<br />1. Utilizes a TextAnalyzerAgent to analyze incoming messages to identify requests for image generation and
extract relevant details.<br />2. Leverages the provided ImageGenerator (e.g., DalleImageGenerator) to create the image.<br />3. Optionally caches generated images for faster retrieval in future conversations.<br />NOTE: This capability increases the token usage of the agent, as it uses TextAnalyzerAgent to analyze every
message received by the agent.<br />Example: <br />    \`\`\`python
import autogen
from autogen.agentchat.contrib.capabilities.image\_generation import ImageGeneration

# Assuming you have llm configs configured for the LLMs you want to use and Dalle.<br />    # Create the agent

agent = autogen.ConversableAgent(
name="dalle", llm\_config=\{...}, max\_consecutive\_auto\_reply=3, human\_input\_mode="NEVER"
)

# Create an ImageGenerator with desired settings

dalle\_gen = generate\_images.DalleImageGenerator(llm\_config=\{...})

# Add the ImageGeneration capability to the agent

agent.add\_capability(ImageGeneration(image\_generator=dalle\_gen))

````

<b>Parameters:</b>
| Name | Description |
|--|--|
| `image_generator` | **Type:** [ImageGenerator](/docs/api-reference/autogen/agentchat/contrib/capabilities/generate_images/ImageGenerator) |
| `cache` | **Type:** [AbstractCache](/docs/api-reference/autogen/cache/AbstractCache) \| None<br/><br/>**Default:** None |
| `text_analyzer_llm_config` | **Type:** [LLMConfig](/docs/api-reference/autogen/llm_config/LLMConfig) \| dict[str, typing.Any] \| None<br/><br/>**Default:** None |
| `text_analyzer_instructions` | **Type:** str<br/><br/>**Default:** 'In detail, please summarize the provided prompt to generate the image described in the TEXT.\nDO NOT include any advice. RESPOND like the following example |
| `verbosity` | The verbosity level.<br/><br/>Defaults to 0 and must be greater than or equal to 0. The text analyzer llm calls will be silent if verbosity is less than 2.br/>register_reply_position (int): The position of the reply function in the agent's list of reply functions.br/> This capability registers a new reply function to handle messages with image generation requests.br/> Defaults to 2 to place it after the check termination and human reply for a ConversableAgent.<br/><br/>**Type:** int<br/><br/>**Default:** 0 |
| `register_reply_position` | **Type:** int<br/><br/>**Default:** 2 |

### Instance Methods

<code class="doc-symbol doc-symbol-heading doc-symbol-method"></code>
#### add_to_agent

```python
add_to_agent(self, agent: ConversableAgent) -> 
````

Adds the Image Generation capability to the specified ConversableAgent.<br />This function performs the following modifications to the agent: <br />1. Registers a reply function: A new reply function is registered with the agent to handle messages that
potentially request image generation. This function analyzes the message and triggers image generation if
necessary.<br />2. Creates an Agent (TextAnalyzerAgent): This is used to analyze messages for image generation requirements.<br />3. Updates System Message: The agent's system message is updated to include a message indicating the
capability to generate images has been added.<br />4. Updates Description: The agent's description is updated to reflect the addition of the Image Generation
capability. This might be helpful in certain use cases, like group chats.<br />

<b>Parameters:</b>

| Name    | Description                                                                                                                          |
| ------- | ------------------------------------------------------------------------------------------------------------------------------------ |
| `agent` | The ConversableAgent to add the capability to.<br /><br />**Type:** [ConversableAgent](/docs/api-reference/autogen/ConversableAgent) |

<br />