DALL-E Variants
Integrate DALL-E into your flows to generate diverse and creative images from textual descriptions.
Last updated
Integrate DALL-E into your flows to generate diverse and creative images from textual descriptions.
Last updated
The OpenAI component allows you to integrate OpenAI DALL-E image generation into your flows. In particular, the following versions are supported:
DALL-E 2
DALL-E 3
The OpenAI component has the identifier of opa-X, where X represents the instance number of the OpenAI component.
The OpenAI component has the following input connections.
Input Name | Description | Constraints |
---|---|---|
From Data Loaders | This input connection represents the context information for the OpenAI model. | Must originate from a Data Loader component. |
From Input/LLM | This input connection represents the natural language textual description of the desired image. | Must originate from a component that generates a text string as output such as a Python or Text Input component. |
Parameter Name | Description |
---|---|
Credentials | You can specify to use your own OpenAI credentials or alternatively you can use Diaflow's default credentials. |
Model | This parameter specifies the version of OpenAI that the component should use. Available values: - DALL-E 2 - DALL-E 3 |
Quantity | Specifies the number of images to generate. |
Size | Specify the output image dimensions. |
Prompt | Describes how you want the OpenAI model to respond. For example, you can specify the role, manner and rules that OpenAI should adhere to. Also mention the component ID to connect the components. |
This OpenAI component has no advanced configurations.
The OpenAI component has the following output connections.
Output Name | Description | Constraints |
---|---|---|
Image | This output connection contains the graphical result of the OpenAI component. | Can be connected to any component that accepts a string input. |
Here is a simple use case of the OpenAI component, where the OpenAI component is being used with the DALL-E 3 model, in order to generate an image described with natural language.