We've enhanced Grok's image generation abilities with a new model, code-named Aurora. Aurora is an autoregressive mixture-of-experts network trained to predict the next token from interleaved text and image data. We trained the model on billions of examples from the internet, giving it a deep understanding of the world. As a result, it excels at photorealistic rendering and precisely following text instructions. Beyond text, the model also has native support for multimodal input, allowing it to take inspiration from or directly edit user-provided images.

Grok's new capabilities are now available on the 𝕏 platform in select countries and will roll out to all users within a week.

Lockheed SR-71 Blackbird in an abstract style
Lockheed SR-71 Blackbird in an abstract style
Optimus wearing a Xmas costume in a Xmas scene
Optimus wearing a Xmas costume in a Xmas scene
Generate a creative logo for "GROK" with a golden color and sunglasses
Generate a creative logo for "GROK" with a golden color and sunglasses
Cherry blossom
Cherry blossom
An origami Cybertruck
An origami Cybertruck
A superposition of a cat in a hyperbolic time chamber in the style of Van Gogh
A superposition of a cat in a hyperbolic time chamber in the style of Van Gogh
Jackie Chan in Donald Trump’s hairstyle
Jackie Chan in Donald Trump’s hairstyle
Dog drinking a tea
Dog drinking a tea
A comic of a young man standing by the sea, looking back and saying "Make it happen yesterday."
A comic of a young man standing by the sea, looking back and saying "Make it happen yesterday."
Crude crayon drawing of a Tesla driving through a fiery meadow
Crude crayon drawing of a Tesla driving through a fiery meadow
A castle in the clouds
A castle in the clouds
Elon Musk as a Ghibli character
Elon Musk as a Ghibli character
A rock hyrax
A rock hyrax
A close-up of a female warrior with a sword
A close-up of a female warrior with a sword

Image Generation

Grok can now generate high-quality images across several domains where other image generation models often struggle. It can render precise visual details of real-world entities, text, logos, and can create realistic portraits of humans.

Prompt

Cybertruck under an aurora

Cybertruck under an aurora
Grok
Cybertruck under an aurora - imagen
Imagen 3
Cybertruck under an aurora - flux
Flux.1 Pro
Cybertruck under an aurora - ideogram
Ideogram 2.0
Cybertruck under an aurora - dalle
Dall-E 3

Image Editing

Our new image generation model can now take images as input, giving users greater creative control and flexibility. We will release this capability to users on the 𝕏 platform soon.

Prompt

Make the cat anime style

Make the cat anime style: Before
Input image
Make the cat anime style: After
Output image

Looking Forward

At xAI, we are advancing the frontier of multimodal understanding and generation. If this goal inspires you, we invite you to join us on this journey — we are hiring!