How Shortodella Handles Image Generation and Editing

Shortodella generates and edits images on a visual canvas driven by plain-English prompts, so you don't need design software or prior design skills. You describe what you want, and an AI agent generates, edits, and arranges the result on the canvas. This applies to the beta version of the product; image work sits alongside video generation in the same studio.

What image generation covers

According to the site, image generation supports any style and any size, ranging from photorealistic product shots to illustrations and concept art. That range matters if you're producing marketing assets, design drafts, or influencer-style visuals from one tool rather than switching between a photo editor and an illustration app.

The generation models named on the page are Nanobanana, Kling, Grok, and Veo. The site describes the studio as generating from text, turning photos into video, and editing on a visual canvas.

How the canvas workflow works

The core of Shortodella is an open canvas where ideas become visuals. Three image-related actions are listed directly:

• Create images on canvas — start from a text prompt and generate.
• Edit images on canvas — modify what you've generated or brought in.
• Photo to video on canvas — extend a still image into motion (a video feature, but it starts from your image).

The AI agent is the connective layer: you describe what you want in plain English, and the agent "thinks, generates, edits, and arranges for you." In practice, that means you're not hunting through menus for each operation — you state the change and the agent applies it on the canvas.

A concrete example

Say you need a product shot for a landing page. You'd describe the product, the style (photorealistic), and the composition in plain language. The agent generates it on the canvas. If the background is wrong, you describe the fix rather than masking it manually, and the agent edits in place. If you later want a short clip of that same image, the photo-to-video path on the canvas handles that step.

What you need to get started

The page states no design skills required — the interface is built around conversation with the AI rather than manual tooling. The product is in beta, and the editor is opened directly ("Open the editor and describe your first visual").

Access to the AI tools is metered by energy, which varies by plan:

Plans from Beginner up include the full media gallery (images, videos, sound, templates), the canvas AI editor and AI agent, interface tools, MCP tools, and no attribution requirement. A one-time Extra Pack of 390 energy costs $49 and is valid for 3 months, for topping up without a subscription. Monthly and yearly billing are offered, with yearly shown at −20%.

Choosing based on your image workload

• Just testing image generation: the Free tier gives access to basic image collections, but requires attribution and doesn't list energy for AI tools — so treat it as a trial of the gallery, not the generator.
• Occasional image creation: Beginner's 80 energy/mo and 100 MB storage suit light, intermittent use.
• Regular marketing or design output: Premium (190 energy) or Pro (390 energy) give more generation headroom and storage, and both drop the attribution requirement.
• Unpredictable spikes: the one-time Extra Pack adds 390 energy without changing your plan.

Because energy is consumed by AI tool use, the plan you pick should track how many generations and edits you expect per month, not just storage. If your image work is steady and low-volume, a smaller plan plus an occasional Extra Pack may fit better than upgrading tiers.