12 lines
688 B
Plaintext
12 lines
688 B
Plaintext
|
# Text to Image Generation
|
||
|
|
|
||
|
|
<Image
|
||
|
|
alt={'Text to Image Generation'}
|
||
|
|
src={
|
||
|
|
'https://github-production-user-asset-6210df.s3.amazonaws.com/17870709/297746445-0ff762b9-aa08-4337-afb7-12f932b6efbb.png'
|
||
|
|
}
|
||
|
|
cover
|
||
|
|
/>
|
||
|
|
|
||
|
|
Supporting the latest text-to-image generation technology, LobeChat now enables users to directly utilize the Text to Image tool during conversations with the assistant. By harnessing the capabilities of AI tools such as [DALL-E 3](https://openai.com/dall-e-3), [MidJourney](https://www.midjourney.com/), and [Pollinations](https://pollinations.ai/), assistants can now transform your ideas into images. This allows for a more private and immersive creative process.
|