When a still needs a clear idea — a scene, a poster mood, or a short line of type — Ideogram is a useful model to try. The free Ideogram image generator on CanvaPro offers Text to Image and Image to Image on the live form. You do not need an account, and the usual download does not pick up a watermark from the page.
Image to Image accepts a JPG, PNG, or WEBP up to 10 MB. That upload path is on the page, even if older FAQ text once said you do not add a photo. Aspect ratios are Auto, 1:1, 3:2, 2:3, 9:16, 16:9, 3:4, and 4:3, with Auto selected by default. There is no separate model or 1K/2K/4K picker on this form. After you write a prompt, complete the security check and click Generate Image. A preview typically appears in about a minute.
Text to Image and Image to Image
Text to Image invents the frame from your description. Image to Image starts from a reference you upload and uses the prompt to guide the edit or variation. Only upload a file you have the right to change. A simple, sharp still usually steers the result more reliably than a busy thumbnail.
How to generate an image, step by step
- Choose Text to Image or Image to Image. In Image to Image, upload a JPG, PNG, or WEBP under 10 MB.
- Write a prompt that names the subject, the setting, the light, and any short wording you want in the scene. In Image to Image, say what should change and what should stay.
- Pick an aspect ratio, complete the security check, and click Generate Image once.
- Review the preview. If the composition and any letters look close enough, download the file. If not, change one part of the prompt and run again.
Type, scenes, and a fair limit
Ideogram is often used when a still includes a sign, a title, or a short label, because some prompts hold lettering more clearly than on other models. That is not a guarantee of perfect typography. If the words have to be legally exact, add the final type in a design app. Creators also use the tool for atmosphere stills, social drafts, and concept art. Treat every output as synthetic media, and label it when the context requires it.
If the letters are meant to be a brand mark rather than a scene, start with how to create an AI logo from your brand name.
If the preview misses the brief
Simplify the prompt, confirm the 10 MB limit in Image to Image, and make sure the security check is still valid. If you would rather pick Seedream 5 Lite or Pro and a 1K, 2K, or 4K size, open the Seedream image generator and run the same idea there.
Uploads and prompts travel over HTTPS. Requests are handled to complete generation and are not sold. Only upload reference photos you have the right to use.
If the letters are meant to be a brand mark, the AI logo generator is a closer starting point than a full scene with a sign in it.
After the Ideogram preview appears
Judge the still at the aspect and size you will publish. Check any lettering carefully. If the scene is right but the type is not, keep the image and set the words yourself. Save the file with a short note of the prompt and ratio so you can refine it later.
Read every word in the still, and if a label is misspelled, tighten the prompt and generate again with the Ideogram generator.
Working with signs and short labels
If the still needs a shop name, a poster title, or a simple label, put that exact wording in the prompt and keep the rest of the scene simple. Long paragraphs of legal type or tiny footnotes rarely come out clean. A short, high-contrast line on a wall, a neon sign, or a book cover is a more realistic request. Always read the letters in the preview, even when they look good at a glance.
Image to Image is useful when you already have a layout or a photo whose composition you want to keep. Describe the change in one sentence. Text to Image is better when the whole scene is invented. In either mode, set the aspect ratio to match the final placement so a vertical story is not cropped out of a wide still.
Because this form has no size or model picker, your main controls are the prompt, the mode, and the aspect ratio. Change one of those at a time if you are refining a near-miss, and keep the earlier download so you can compare.
Other text-to-image options for general scenes are covered in the article on how to generate images with GPT Image.
A short checklist
- Pick Text to Image, or Image to Image with a JPG, PNG, or WEBP under 10 MB.
- Write one clear prompt and choose Auto or a specific aspect ratio.
- Click Generate Image once and wait about a minute for the preview.
- Download the still you like, and add any critical typography in a design app if needed.
When you are ready, describe a single scene, generate once, and save the preview only after the composition looks right. One considered still is easier to use than a long string of near-duplicates.