Grok Imagine Image in ComfyUI: AI Image Generation and Editing

Generate and edit images with the Grok Imagine Image model in ComfyUI: text-to-image and natural-language image editing

Grok Image is xAI’s image generation model, available in ComfyUI through the Grok partner nodes. It generates images from text prompts and edits uploaded images with natural-language instructions, supporting 13 aspect ratios and 1K or 2K output.

What Grok Imagine Image is good at

• Text-to-image generation: creates single images from a text prompt describing the scene and style
• Natural-language image editing: edits an uploaded image based on your prompt while keeping the original composition, changing the scene, lighting, or style
• Flexible aspect ratios: supports 13 aspect ratios, including 1:1, 16:9, and 9:16
• Resolution options: outputs at 1K or 2K

Example outputs

Text-to-image generation from a single prompt:

Image editing with natural-language instructions, keeping the original composition:

Use it in ComfyUI

Grok Imagine Image workflows

Run the text-to-image and image edit workflows in ComfyUI, locally or on Comfy Cloud