> For the complete documentation index, see [llms.txt](https://docs.ideogram.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.ideogram.ai/create/models.md). # Models Compare Ideogram image models by reference-image support, transparency, style controls, resolution and premium access. Find out why a model may be missing. Pick a model from the **Model** picker in the Image app. Each one suits different jobs, such as logos, photo editing and restoration, product photos, wide banners, stickers and t-shirt designs; see [Ideogram models](#ideogram-models). Each model has its own settings, and the panel changes when you switch. The list comes from Ideogram's servers, so what you see can change over time. ## Which image model should I choose? Choose by the inputs and controls your task requires. A model with more settings isn't necessary for every image. | You need | Model or workflow to consider | | --------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------- | | A short form without choosing a model yourself | **Auto**, which selects a model when you generate. | | To edit or combine up to five reference images with an Ideogram model | **Ideogram 4.5**. Use Precise Edit when the change needs a mask. | | Style presets, style references, a negative prompt or a color palette | **Ideogram 3.0**. Style references guide the look; they aren't source images to edit. | | A transparent image from a prompt | **Ideogram 4.5** with Background set to Transparent, or a dedicated **Transparent** model. | | Reference-image masking and a Background control on a partner model | **GPT Image 2.5**, where available with premium access. | | A model trained on your own image set | A [custom model](/create/custom-models.md). Check its base to know which controls it supports. | For a fair comparison, keep the prompt and intended output shape consistent, then review each model's credit quote. Resolution, quality and image count can change the cost.
Model picker open with the filter chips My models, Team models, Ideogram, OpenAI, Google and Tongyi highlighted above the All models list

Use the chips to filter the list by owner or provider.

## Auto **Auto** sits at the top of the picker, and the Image app opens on it. You write the prompt; Auto picks a model for you when the run starts. If you attach reference images, it picks a model that treats your prompt as an edit instruction. Auto keeps the panel short: * **Reference images**, up to 10 * **Prompt** * **Aspect ratio**: Auto, 1:1, 4:3, 3:4, 3:2, 2:3, 16:9 or 9:16 * **Number of images**: Auto gives 4, or 2 when you attach references * **Seed**, under **Advanced settings** * **Add to Collection** Auto has no Magic Prompt or Quality setting. Because the model isn't known until the run starts, the **Generate** button shows an estimated cost with a `~` in front. You pay what the chosen model would charge. ## Ideogram models Every plan, free included, can use Auto and all Ideogram models. * **Ideogram 4.5** accepts reference images in the Image app, so you can edit or combine images with a prompt. Use references for photo editing, photo restoration, product photos, mockups and keeping a character consistent. In the Precise Edit app you can mask the area you want to change (inpainting). See [Masks and Inpainting](/edit/masks-and-inpainting.md). * **Ideogram 4.0** offers very wide aspect ratios such as 23:9 and 3:1, at 1K or 2K. It suits banners, website headers, posters and thumbnails. * **Ideogram 3.0** is the only model with style presets, style reference images, negative prompts and color palettes. That makes it good for logos, brand graphics and matching a set style. * **Ideogram 4.0 Transparent** and **Ideogram 3.0 Transparent** make images with no background, for stickers, t-shirt and print-on-demand designs, icons and clip art. See [Transparent Backgrounds](/create/transparent-backgrounds.md). | | Ideogram 4.5 | Ideogram 4.0 | Ideogram 3.0 | | ----------------- | -------------------------------------------------------------------------------------- | --------------------------------------------- | ---------------------------------------------------------------------------- | | Prompt | Text or [JSON](/prompting/json-prompting.md), up to 10,000 characters | Text or [JSON](/prompting/json-prompting.md) | Text | | Reference images | Up to 5 | None | None (style reference images instead) | | Aspect ratio | Auto or a ratio, then **Resolution** 1K or 2K. With references, **Size** replaces both | Auto or a ratio, then **Resolution** 1K or 2K | 15 ratios from 1:3 to 3:1, default 1:1. No resolution choice | | Quality options | Very low (with references only), Low, Medium, High | Turbo, Default, Quality | Turbo, Default, Quality | | Magic Prompt | On/off toggle. Hidden when you attach references | On/off toggle | On/off toggle | | Background | Auto, Transparent or Opaque, under **Advanced settings** | No setting; use Ideogram 4.0 Transparent | No setting; use Ideogram 3.0 Transparent | | 3.0-only settings | No | No | Style, style presets, style reference images, negative prompt, color palette | [Image Settings](/create/image-settings.md) explains each setting. ### Transparent models **Ideogram 4.0 Transparent** and **Ideogram 3.0 Transparent** make images with a clear background. Neither takes reference images. See [Transparent Backgrounds](/create/transparent-backgrounds.md) for other ways to get one. | | Ideogram 4.0 Transparent | Ideogram 3.0 Transparent | | --------------- | ---------------------------------------------------------------------------------------------- | ------------------------------- | | Prompt help | **Prompt upsampling**: Auto, On or Off | **Magic Prompt** toggle | | Size | **Output resolution** 1K, 2K, 4K or 8K. Ideogram upscales anything above 2K after it generates | **Upscale factor** 1x, 2x or 4x | | Aspect ratio | Auto, or 1:1 up to 4:1 and the portrait mirrors | Same list as Ideogram 3.0 | | Quality options | Turbo, Default, Quality | Turbo, Default, Quality | Both also have **Seed** and **Add to Collection**. ## Partner models The Image app also runs models from other providers. Premium models need a paid plan or bought credits; on a free plan, picking one opens an upgrade window. * **GPT Image 2.0**: up to 16 reference images; Resolution 1K, 2K or 4K. Premium. * **GPT Image 2.5 Flare** and **GPT Image 2.5 Sunburst**: up to 16 reference images, and you can paint a mask on a reference to limit the change to that area. Adds **Quality** (Auto, Low, Medium, High) and, under **Advanced settings**, **Background** (Auto, Transparent, Opaque). Premium. * **Nano Banana 2** and **Nano Banana Pro**: up to 10 reference images; Resolution 1K, 2K or 4K. Premium. * **Z-Image**: no reference images; **Inference steps** 20, 30, 40 or 50 ("More steps trade speed for detail."). Free. * **P-Image-Ideogram**: no reference images; **Prompt upsampling** on or off, Resolution 1K or 2K or custom dimensions, and **Quality** from Very Low to High. Free. Partner models have no Magic Prompt toggle. All of them have **Aspect ratio**, **Seed** and **Number of images**. ## Custom and community models A custom model learns a look from images you upload. Yours appear under **My models** in the picker, and your team's under **Team models**. Select **Browse community models** at the bottom of the picker to use models other people have published. The standard custom-model workflow uses Ideogram 3.0 and its settings. Some accounts can have models built on another base, with different controls. Check the model's **Base model** rather than assuming all custom models have the same settings. See [Custom Models](/create/custom-models.md) to train one. ## Pin a model you use often Select the pin beside a model in the picker. Saved choices appear under **Pinned**, above the ordinary model lists. Select the pin again to unpin it. On desktop the control appears when you hover over a row; on touch screens it stays visible. ## Why can't I find or select a model? The model picker shows the catalog available to your account and workspace. It is different from a fixed list of every model Ideogram has ever supported. * **No models match your search:** clear the search and provider or ownership filters before assuming a model is unavailable. * **Models unavailable:** use **Try loading models again**. A catalog-loading problem is different from an empty search result. * **Coming soon:** the entry is listed but can't be selected yet. * A missing custom or team model: check the workspace and the **My models** or **Team models** filter. Changing models can also change which inputs remain active. Review [what carries over between models](/create/image-settings.md#what-changes-when-i-switch-models) and [reference-image limits](/create/reference-images.md) before generating. ## Older Ideogram models Ideogram 2.0 and 2a may still appear in the picker. For new work, use Ideogram 4.5 or 4.0. ## In this topic: creating images 1. [Create Images](/create/create.md): make your first image 2. **Models** (this page): pick the model for the job 3. [Image Settings](/create/image-settings.md): set size, quality and other options 4. [Prompting Basics](/prompting/prompting.md): write a prompt that works 5. [Fix Common Problems](/prompting/fix-common-problems.md): fix results that come out wrong