AI Just Got a Permanent Seat in the Design Builder

Hi there,

For a while, AI in Abyssale meant reaching into a menu, buried a click or two away from the layer you were actually working on. That's changed. Remove Background, Auto Focus, the Eraser, and AI Text-to-Image now sit together in a single AI toolbar that appears the moment you select an image layer, and each of them just got meaningfully more capable.

Here's a full walkthrough of what's new, with a link to the dedicated guide for each feature if you want the details.

One Toolbar, Four AI Actions

Select any image layer in the Design Editor and an AI toolbar appears at the bottom of the canvas, with all four AI actions right there: Remove Background, Focus, Erase, and Ai text to image. No more navigating through separate modals or side-panel menus depending on which action you needed, it's the same entry point every time, for every action.

From there, each action opens its own context directly in the toolbar, where you configure it and generate without leaving the canvas.

Remove Background: Pick the Model, Fine-Tune the Result

Background removal now gives you a choice of model instead of a single fixed engine. Click the model dropdown to see the available options, each labeled with its relative AI credit cost:
​

• Bria RMBG 2.0 (default) — a high-precision, licensed-data model that's a safe default for most images
• Birefnet — an open-source segmentation model, a solid freely-licensed alternative
• Ideogram's — strong at fine detail like hair or fur
• PixelCut — built for e-commerce and product photography
• imageUtils — a straightforward, no-frills option

If your first pass doesn't cleanly isolate the subject, especially around tricky edges, switching models is usually faster than repeating the same one. Two additional controls round out the feature: Trim Transparent Pixels, which crops the image down to its subject after removal, and Manual Selection, which lets you draw a box around the area you want to guarantee is kept (Design Editor only, not available via API).

Once you're happy with a result, you can save it as the rule for that layer going forward, so every future variation gets the same treatment automatically.

→ Read the full guide: Remove Image Backgrounds

Auto Focus: Smarter Framing for People and Objects

Auto Focus keeps your subject perfectly framed regardless of the original image's size or orientation, and it offersn the two detection models depending on what you're framing:

• People Model — built for human subjects, with control over portrait framing (face, head, shoulders, or full body), zoom intensity, and, when there's more than one person in frame, which subject takes priority (largest, centered, leftmost, rightmost, or all). Enterprise plans also get Celebrity Matching, letting you name a public figure to automatically center the focus on them.
• General Model — for objects, animals, vehicles, or complex scenes. The AI detects individual elements as "Tags" you can select and merge into a single composition, with the same zoom controls (off, low, medium, max).

During automated variations, if the AI detects the tags you've chosen in a new image, it merges them automatically to keep your composition consistent at scale, useful for anything from headshots to product shots run through a large batch.

→ Read the full guide: Auto Focus

AI Eraser: Remove Objects Without Leaving the Canvas

The AI Eraser lets you paint over any object, logo, or unwanted detail in an image and have it intelligently replaced with matching background content — no manual retouching required. It's a natural fit for cleaning up product photos, removing logos from reused assets, or hiding distracting background elements.

Two selection modes are available: brush mode, with an adjustable size for fine edges or broader areas, and bounding box mode, for quickly clearing larger or simpler shapes. Like the other AI actions, you now choose which AI model handles the erase before applying it, and the edit is non-destructive until you confirm it.

→ Read the full guide: Erase Unwanted Objects from Images

AI Text-to-Image: More Models, Reference Images, and API Access

Text-to-Image turns a written description into a custom visual directly inside the builder, no stock photo search, no manual illustration. The feature now supports multiple AI models instead of a single one, and depending on the model you choose, you can add up to 4 reference images to steer the generation instead of working from the prompt alone.

Other capabilities carried over and still worth knowing:

• Choose the output ratio (square, landscape, portrait, ultra-wide, and more) so the generated image fits your layout without awkward cropping
• Browse your prompt history during the current session to reuse or tweak earlier prompts
• Auto-generate a starting prompt from an existing image in the layer, if you want a variation that stays visually consistent with what's already there

Text-to-Image is also available through the API: pass a text_to_image prompt on an image element instead of a static URL, and Abyssale generates the visual in real time as part of your automation.

→ Read the full guide: AI Text to Image

Save Once, Scale Everywhere

The biggest shift isn't any single action, it's that none of them are one-off anymore. Save an AI action once (Remove Background, Auto Focus, or Text-to-Image) and it becomes the standing rule for that image layer.

Every future variation of the design inherits it automatically, whether it's generated through Quick Generation, a spreadsheet, or the API, including having each variation generate its own unique AI image, not just reuse the same one.

That reach comes with control. In Design Settings, you decide whether AI Text-to-Image is allowed on a design at all. For Quick Generation specifically, you can also decide whether the end user creating a new variation is allowed to generate an AI image inside it, or not, so self-serve generation stays exactly as open, or as locked down, as you want it.

For the technical details on wiring any of this into your own workflows, remove_bg, auto_focus, and text_to_image element properties, model names, and payload examples — the API reference has the full spec.

→ Read the API reference: Image element properties