# AI image generator Make AI-generated images from any photo or prompt with ready-made Spaces, then build your own workflow in Spacelab so every result stays consistent. Last updated: 2026-11-05 **Key facts** - Any photo or prompt goes in and an AI-generated image comes out. - A Space is a ready-made workflow for one job: pick one, add your input and get the output. - Build your own workflow once in Spacelab and run it again and again, so every output stays consistent. Web page: https://sloosh.ai/docs/ai-image-generator Got an idea? Start with a prompt or any photo and Sloosh turns it into an AI-generated image. Anyone can do it. The quickest way is a Space: pick one for the job, add your input and get the output. ## Make an image with a Space - [Social Media Photo Set](https://sloosh.ai/spaces/social-media-photo-set): upload a photo of a person and get back new photos of the same person in different poses and angles. - [Product Reimagined Fifty Ways](https://sloosh.ai/spaces/product-reimagined-fifty-ways): upload one product photo and get a PDF catalog of your item in dozens of visual styles. - [Image Upscaler](https://sloosh.ai/spaces/image-upscaler): upload any image and get it back 4x larger and sharper. [Spaces](https://sloosh.ai/docs/spaces.md) explains how they work. ## Make an image from a prompt or photo 1. Open [Image](https://sloosh.ai/studio/image) in Studio. 2. Type what you want, for example `A tan leather tote on a marble table, soft window light`. 3. Optional: add a photo from the + menu, or drag it onto the page. 4. Pick a model in the chip under the prompt. The other settings come from that model. 5. Press Generate. The button shows the cost first. You can make up to 4 images at once. [Studio](https://sloosh.ai/docs/studio.md) explains each control. To start from a photo, add it as a reference and give it a job in the prompt, such as "Keep the bag's colour and stitching exactly as they are." [References](https://sloosh.ai/docs/references.md) has the detail. ## Build your own workflow When you have a process that works, build it once in [Spacelab](https://sloosh.ai/docs/spacelab.md) and run it again and again, so every output has the same look. Anyone can build one. ## Check before you publish AI-generated results can get label text and fine details wrong. Check both before you publish. ## Model details Each model has its own page with settings and a worked example. This is the short version, by job. | Job | Models to try | Why | | --- | --- | --- | | Finished product and campaign photos | [Nano Banana Pro](https://sloosh.ai/docs/nano-banana-pro.md) | Listed for e-commerce and product photography, with strong text. | | Quick drafts | [Nano Banana Lite](https://sloosh.ai/docs/nano-banana-lite.md), [Nano Banana 2](https://sloosh.ai/docs/nano-banana-2.md) | Lite is the fastest, for 1K drafts. Nano Banana 2 is the all-rounder, from 512px drafts to 4K. | | Posters, labels and text in images | [Ideogram 4.5](https://sloosh.ai/docs/ideogram-4-5.md), [GPT Image 2](https://sloosh.ai/docs/gpt-image-2.md), [GPT Image 2.5 Flare](https://sloosh.ai/docs/gpt-image-2-5-flare.md), [GPT Image 2.6 Flare](https://sloosh.ai/models/gpt-image-2.6-flare) | Ideogram is built for typography. The GPT Image models suit layouts with several blocks of text. | | Exact colours | [FLUX 2 Pro](https://sloosh.ai/docs/flux-2-pro.md) | Matches colours given as hex codes. | | Change one part of an image | [GPT Image 2.5 Sunburst](https://sloosh.ai/docs/gpt-image-2-5-sunburst.md), [GPT Image 2.6 Sunburst](https://sloosh.ai/models/gpt-image-2.6-sunburst), [Seedream 5 Pro](https://sloosh.ai/docs/seedream-5-pro.md) | Built for precise edits and region changes. | | Large images and many languages | [FLUX 3 Image](https://sloosh.ai/docs/flux-3-image.md) | Generates and edits up to 4K, with text in many languages. | | Layouts that need planning | [Meta Muse](https://sloosh.ai/docs/meta-muse.md) | Plans its layout and checks its own drafts. | Each model sets its own reference limit, and Studio shows it when you add a reference. In Sloosh the Nano Banana models take up to 14 reference images, the GPT Image models up to 16, FLUX 3 Image, Seedream 5 Pro and Meta Muse up to 10, FLUX 2 Pro up to 8, and Ideogram 4.5 up to 5. [Models](https://sloosh.ai/docs/models.md) has the limits for each one. - [Prompt guide](https://sloosh.ai/docs/prompt-guide.md): write a brief, not a bag of keywords. - [Templates](https://sloosh.ai/docs/templates.md): recreate a result that works, then make it yours. - [AI video generator](https://sloosh.ai/docs/ai-video-generator.md): turn an idea into a video. ## Frequently asked questions ### How do I make an AI image from a photo in Sloosh? Open a Space such as [Social Media Photo Set](https://sloosh.ai/spaces/social-media-photo-set) and upload your photo. Or open [Image](https://sloosh.ai/studio/image) in Studio, add your photo from the + menu and say in the prompt what the photo is and what must not change. Studio shows each model's reference limit. ### Do I need design skills to make AI images in Sloosh? No. Write a prompt, add any photo, or pick a Space and add your input. ### Which AI image model takes the most reference images in Sloosh? The GPT Image models take the most: up to 16 reference images. The Nano Banana models take up to 14. FLUX 3 Image, Seedream 5 Pro and Meta Muse take up to 10. ### Which AI image model handles text in images in Sloosh? [Ideogram 4.5](https://sloosh.ai/docs/ideogram-4-5.md) is built for typography such as posters, labels and promo tiles. For layouts with several blocks of text, like menus and recipe cards, try [GPT Image 2](https://sloosh.ai/docs/gpt-image-2.md), [GPT Image 2.5 Flare](https://sloosh.ai/docs/gpt-image-2-5-flare.md) or [GPT Image 2.6 Flare](https://sloosh.ai/models/gpt-image-2.6-flare). Put every word that must appear in quotes, and check the text before you publish. ### Can I make 4K images in Sloosh? Yes, on the models that offer it. These image models do: GPT Image 2.6 Sunburst, GPT Image 2.6 Flare, Nano Banana 2.1, GPT Image 2.5 Sunburst, GPT Image 2.5 Flare, FLUX 3 Image, GPT Image 2, Kling Image O3, Nano Banana 2 and Nano Banana Pro. Every Sloosh workspace can make 4K, whatever the plan. ### Can I edit an image after I make it? Yes. Open an image in My generations to Upscale it to 2K or 4K, Remove BG, Resize it, use AI Removal to take out an object, or Refine to paint over the part to change. Editing works on images Sloosh made, not on files you only attached to a prompt.