# Grok Imagine Image 2.0 Guide: Prompts, Editing and Settings Canonical page: https://fuser.studio/articles/grok-imagine-image-guide How to prompt and edit with xAI's Grok Imagine Image 2.0: text in images, multi-image edits with tags, quality and resolution settings, tested outputs. [All guides](/articles) · [Grok Imagine Image in Fuser](/models/grok-imagine-image) **Quick answer:** Grok Imagine Image 2.0 is xAI's image model for both generation and editing. Describe the scene in plain sentences, put any words you want rendered in quotation marks and say where they go, and pick **quality: medium** for final images. To edit, connect one or more images: the same prompt field becomes an instruction, and with several inputs you can name each one as , and so on, the convention in [xAI's API reference](https://docs.x.ai/developers/rest-api-reference/inference/images). In Fuser this is a single node, [Grok Imagine Image](/models/grok-imagine-image), which switches from text-to-image to edit as soon as an image is connected. ## What the model is and how Fuser runs it xAI's current image model is grok-imagine-image-2.0, which it documents for generation and for editing with up to five source images ([xAI Imagine overview](https://docs.x.ai/developers/model-capabilities/imagine)). Fuser runs it through fal on two endpoints: xai/grok-imagine-image/v2.0/text-to-image and xai/grok-imagine-image/v2.0/edit ([fal model page](https://fal.ai/models/xai/grok-imagine-image/v2.0/text-to-image)). You never choose between them. With the **Images** input empty the node generates from text; with one or more images connected it calls the edit endpoint ([Fuser docs](https://docs.fuser.studio/docs/nodes/image/grok-imagine-image)). The name is shared with xAI's video models, so check which node you are on. This guide covers stills only. The video nodes have their own pages: [Grok Imagine video](/models/grok-imagine) and [Grok Imagine video edit](/models/grok-imagine-edit). ## How to write a Grok Imagine Image prompt A prompt can run to 8,000 characters ([fal schema](https://fal.ai/models/xai/grok-imagine-image/v2.0/text-to-image/api)), so there is no need to compress it into a list of tags. What worked in our runs was a short brief in this order: 1. **Subject and medium.** "Studio product photo of a matte sage-green ceramic coffee mug", or "Minimal gig poster for a jazz night". 2. **Setting and props.** "On a pale oak table, a single sprig of rosemary beside it." 3. **Light and lens.** "Soft window light from the left, shallow depth of field." 4. **Exact text, in quotes, with a position.** "The mug has the word "SLOW" printed in small black serif capitals." 5. **Style or layout.** "Swiss poster layout, subtle paper grain." xAI lists the styles the model covers as "ultra-realistic photography to anime, oil paintings, and pencil sketches" ([xAI image editing docs](https://docs.x.ai/developers/model-capabilities/images/editing)), so name the medium in the first few words rather than leaving it to chance. ## Text in images Text is where this model earns a place in a workflow. Our poster prompt split the layout into regions: "Top third: the headline "LATE NIGHT BLUE" in tall condensed white sans-serif letters... Bottom: "FRI 14 NOV · 9PM · THE CELLAR" in small white caps." Both the 1k and 2k runs rendered every word and the middots correctly and kept the three-band layout. ![A Grok Imagine Image v2.0 jazz gig poster reading LATE NIGHT BLUE and FRI 14 NOV, 9PM, THE CELLAR, generated at 1k (832 by 1248) and 2k (1664 by 2496).](https://statics.fuser.studio/cms/1a860261-c557-46d8-ba40-86cf9023c825) _Same poster prompt at 1k and 2k. Both runs spelled every word correctly, including the date line. Generated 28 September 2026._ Two habits made the difference. Quote the exact string, and describe the type (condensed sans, small serif caps) as well as where it sits. Our tests used one headline and one info line per image; we did not test paragraphs of copy. For body copy or anything with many lines, generate the image with space for it and set the type afterwards in Fuser's Compositor. ## Settings that matter The Fuser node exposes four controls besides the prompt and images. - **Aspect ratio.** 13 fixed ratios from 2:1 to 1:2, including 20:9, 19.5:9, 9:19.5 and 9:20 for phone screens, plus **Auto**. In text-to-image, Auto gives 1:1; in edit mode it keeps the ratio of the first input image ([fal edit schema](https://fal.ai/models/xai/grok-imagine-image/v2.0/edit/api)). - **Resolution.** 1K (default) or 2K. In our runs a 16:9 image at 1k came back at 1280 × 720, a 2:3 image at 1k at 832 × 1248, and the same 2:3 prompt at 2k at 1664 × 2496. - **Quality.** Low or medium, default medium in Fuser. Note that xAI's own API defaults to "auto", which it says currently means low for generation and medium for editing ([xAI image generation docs](https://docs.x.ai/developers/model-capabilities/images/generation)), so results from other tools that call the API directly may have been made at low. - **Images.** Optional inputs that switch the node into edit mode. ![The same Grok Imagine Image v2.0 prompt for a sage-green mug printed with SLOW, rendered at quality low and quality medium, both 1280 by 720.](https://statics.fuser.studio/cms/e76599a7-d03e-407f-bbb8-b151dac4fe3b) _Quality low (left) and medium (right), same prompt, 16:9 at 1k. Both are 1280 × 720; the difference is in rendering, not pixel count._ In our side-by-side the gap was small: both settings kept the composition idea and rendered SLOW cleanly, and medium gave slightly smoother surface detail. fal lists 1k at $0.04 per image on low and $0.06 on medium, and 2k at $0.06 and $0.08; edits add $0.01 per input image ([fal edit pricing](https://fal.ai/models/xai/grok-imagine-image/v2.0/edit)). Use low for exploring layouts and medium for anything you keep. ## Editing a single image Connect an image and write the change as an instruction. Say what should change and, just as clearly, what must stay: "Move the mug outdoors onto a mossy granite rock beside a misty mountain lake at sunrise. Keep the mug's shape, sage-green colour and the word "SLOW" exactly as they are. Replace the rosemary with a small pine cone." The result kept the mug, its colour and the printed word, and swapped the prop as asked. ![A sage-green SLOW mug and two Grok Imagine Image v2.0 edits of it: moved onto a mossy rock by a mountain lake, and redrawn as a pencil sketch.](https://statics.fuser.studio/cms/3c815188-023d-4df8-b45a-f10c2886a7f8) _One input, two edit instructions. The mug's shape and the word SLOW survived both. Generated 28 September 2026._ Style changes work the same way. "Redraw this image as a loose graphite pencil sketch on off-white paper, visible hatching, no colour except a light sage wash on the mug" kept the composition and the lettering while changing the medium entirely. For a sequence of changes, xAI recommends chaining: use each output as the input for the next edit ([xAI image editing docs](https://docs.x.ai/developers/model-capabilities/images/editing)). On a Fuser canvas that is a row of Grok Imagine Image nodes, each wired to the one before, so you can go back and change step two without redoing step one. ## Combining several images The edit endpoint accepts up to five images ([fal edit schema](https://fal.ai/models/xai/grok-imagine-image/v2.0/edit/api)). xAI's API reference says that when several images are provided you refer to them as , and so on in the prompt. We tested that convention through fal with the mug as the first image and the poster as the second: "A cosy jazz bar at night. The poster from hangs framed on the brick wall. In the foreground on a dark wooden bar counter sits the mug from , unchanged, with steam rising." ![Two input images, the SLOW mug and the LATE NIGHT BLUE poster, combined by Grok Imagine Image v2.0 into a jazz-bar scene with the poster on a brick wall and the mug on the counter.](https://statics.fuser.studio/cms/95bb048c-e6aa-48a9-a66f-817e93d14a3e) _Two references addressed as and in one edit prompt, with the aspect ratio set to 3:2._ Both references landed where the prompt put them, and the poster's text stayed readable in the new scene. Because we set the aspect ratio to 3:2, the output came back at 1248 × 832 rather than matching the first input. In Fuser, the node sends the images on its **Images** input to the model as one ordered list. If a result swaps two references, swap the tags in the prompt or reconnect the images. ## Fix what goes wrong - **Misspelled text:** quote the exact string, shorten it, and say where it goes and what type it uses. - **The edit changed things you wanted kept:** list them explicitly with "keep ... exactly as they are", as in the mug edit above. - **Wrong image used in a multi-image edit:** use the tags rather than "the first photo", and check the input order. - **Edit output has the wrong shape:** Auto follows the first input image. Pick a fixed aspect ratio if you need a different frame. - **Drafts look rougher than expected:** check the quality setting. xAI's API defaults generation to low; the Fuser node defaults to medium. ## Build it as a workflow The hero image above is the whole pattern on one canvas: two text-to-image nodes make the product and the poster, and a third node combines them. From there the still can go to an upscaler such as [Topaz](/models/topaz-image-upscale), into the Compositor for final type, or into an image-to-video model like [Kling 3.0](/models/kling-3-0-video). To see how Grok Imagine Image compares with other editors, read [the best AI image editing models](/articles/best-ai-image-editing-models) and [the best AI models for text in images](/articles/best-ai-models-for-text-in-images). ## Grok Imagine Image 2.0 at a glance. What each setting does on the Fuser node, from the fal schema and our runs. ### Node settings | Setting | Options | What to know | | --- | --- | --- | | Mode | Text-to-image or edit | Chosen automatically: edit as soon as an image is connected. | | Images | 0 to 5 inputs | Refer to several inputs as , ; the first is . | | Aspect ratio | Auto plus 13 ratios, 2:1 to 1:2 | Auto is 1:1 for text-to-image and follows the first input when editing. | | Resolution | 1K (default) or 2K | 2:3 measured 832 × 1248 at 1k and 1664 × 2496 at 2k. | | Quality | Low or Medium (default) | Low is cheaper for drafts; medium for finals. | | Prompt | Up to 8,000 characters | Full sentences; quote any text you want rendered. | ## Questions, answered. ### What is Grok Imagine Image 2.0? It is xAI's current image model, grok-imagine-image-2.0, for text-to-image generation and image editing with up to five source images. In Fuser it runs as the Grok Imagine Image node. ### Can Grok Imagine Image edit photos? Yes. Connect one or more images to the node and write the change as an instruction. The node switches to xAI's edit endpoint automatically, and Auto aspect ratio keeps the shape of the first input. ### How do I reference multiple images in a Grok Imagine prompt? Name them , and so on, as xAI's API reference describes; the first image is . In our test, a mug as and a poster as were placed exactly as the prompt described. ### Is Grok Imagine Image good at text? In our runs it rendered a headline, a date line with middots and a word printed on a product without errors, at both 1k and 2k. Quote the exact text and say where it should sit. ### What resolution does Grok Imagine Image output? 1K or 2K. In our tests 16:9 at 1k was 1280 × 720, and 2:3 was 832 × 1248 at 1k and 1664 × 2496 at 2k. ### Should I use low or medium quality? Use low to explore layouts cheaply and medium for images you keep. Fuser defaults to medium; xAI's own API defaults to low for generation. ## Generate, edit and combine on one canvas. Wire Grok Imagine Image into upscalers, video models and the Compositor. [Open Grok Imagine Image in Fuser](https://fuser.studio/models/grok-imagine-image) · [Explore all guides](https://fuser.studio/articles) ## More articles - [Seedream 5.0 Lite Prompt Guide: Multi-Reference, Text and 4K, Tested](https://fuser.studio/articles/seedream-prompt-guide.md) - [Nano Banana Prompt Guide: Generate, Edit and Combine Images with Gemini](https://fuser.studio/articles/nano-banana-prompt-guide.md) - [GPT Image Prompt Guide: Structure, Text, Edits and Sizes (GPT Image 2.5)](https://fuser.studio/articles/gpt-image-prompt-guide.md)