Not sure how to generate good-looking images? Read our dedicated guide!
What Is Image Generation/Text To Image?
Thanks to the Stable Diffusion model, released by Stability AI, it is now possible to generate an image out of a simple text instruction, and get results equivalent to OpenAI DALL-E 2. You can even generate impressive art images with this text to image model.
Simply write a short text instruction and let the model generate an image out of it.
Stable Diffusion is the most advanced open-source text to image model as of this writing, and it is the best DALL-E 2 alternative!
Why Use Image Generation?
Automatic image generation is still a very recent AI field, so new use cases are being discovered everyday! Here are a couple of examples.
It is now possible to generate genuine art, following a specific style. For example you can generate a painting that is following Claude Monet's or Edgar Degas' style!
Blog Article Illustration
Finding the right illustration for a blog post often is a challenge. Thanks to text to image, you can now easily generate an image that perfectly illustrates the content you are writing, without facing any copyright issue!
Control whether you want to use the model on a GPU. Machine learning models run much faster on GPUs.
NLP has a critical weakness: it doesn't work well with non-English languages.
We do our best to add non-English models when it's possible. See for example Fine-tuned GPT-NeoX 20B, XLM Roberta Large XNLI, Paraphrase Multilingual Mpnet Base V2, or spaCy. Unfortunately few models are available so it's not possible to cover all the NLP use cases with that method.
In order to solve this challenge, we developed a multilingual AI that automatically translates your input into English, performs the actual NLP operation, and then translates the result back to your original language. It makes your requests a bit slower but returns impressive results.
Simply select your language in the list, and from now on you can write the input text in your own language!
This multilingual add-on is a paid feature. It is included by default in the pay-as-you-go plan. If you are on another plan, please contact the support team so they can upgrade your plan.