--- title: "AI Image Generation Studio for Product Photos, Ads & Visuals" summary: "Generate, compose, and edit product images, brand visuals, posters, social graphics, illustrations, and photo variations." url: "https://beatra.ai/en/skills/ai-image-generation-studio" language: "en" version: "0.2.6" last_verified: "2026-11-09" --- [Skills](https://www.beatra.cn/en/skills) · [Image design](https://www.beatra.cn/en/skills/categories/image-design) # One clear visual, from direction to finished image AI Image Generation Studio creates and refines images from a written brief, one to four ordered reference images, or an existing base image to edit. It returns up to four PNG images at 1K, 2K, or 4K for product photos, ad creative, brand visuals, posters, social graphics, illustrations, and concept art, and a generated image can start a short video clip. AI Image Generation Studio works in Claude Code, Codex, Cursor, and other agents that run Skills. ```text Install AI Image Generation Studio and tell me when I need to sign in: https://beatra.ai/skills/ai-image-generation-studio/install.md ``` Send it to WorkBuddy, Codex, Claude Code, or another agent to install. Sign in once the first time you use it. [install.md](https://www.beatra.cn/skills/ai-image-generation-studio/install.md) · [GitHub](https://github.com/beatra-ai/ai-image-generator-skill) · [Docs](https://docs.beatra.cn/en/docs/capabilities) · [Use it on your phone: WeChat mini program](https://www.beatra.cn/en/mini-program?utm_source=website&utm_medium=skill) ## Three useful ways to create ### Direction before generation Define the message, subject, composition, style, light, color, destination, and must-keeps before creating. ### Start from the source that matters Use a written brief, one to four ordered reference images, or one base image while keeping your chosen starting point clear. ### Review before another version Inspect the generated image, then choose one focused edit, new composition, or new generation. ## How it is made ### Plan before generation · Every image starts with a clear visual brief Confirm the purpose, message, subject, sources, composition, style, light, canvas, output count, and review criteria before creation. - Define one message and its destination - Choose subject, composition, style, light, and color - Inspect every source image before using it - Review each generated image against the brief ### Three ways to create · Generate, compose, or edit Choose the starting point that matches your real material and intended change. - Generate a new image from a written direction - Compose a new image from ordered references - Edit an existing base image - Use a reviewed result as the source for one focused follow-up ### Current model choices · Choose a model that fits this image Available choices depend on the source images, canvas, number of results, relationship between results, and requested creative settings. A named compatible model remains your choice. - Match the model to the requested image and sources - Keep a named compatible choice - Confirm model and input compatibility before creation - Review the actual result against the visual brief ### Review the result · Watch the image before choosing the next step Check message, subject, composition, style, text, actual dimensions, and destination fit, then change only what matters. - Compare each result with the visual brief - Check actual dimensions and destination fit - Inspect every available option - Choose one focused next step ## Images for real production needs ### Create product images Place a supplied product into a new scene or generate a new product concept, then check shape, color, label, and destination fit. ### Build ad and brand visuals Turn one message, palette, and audience into a campaign image or brand-led visual draft. ### Make social graphics and posters Plan one image around the channel, orientation, room for text, and message. ### Develop illustrations and concepts Explore a named visual style for an illustration, cover, scene, or concept image. ### Change a photo or background Use an existing image as the base and focus the requested change on an object, region, background, or overall treatment, then inspect the whole result. ### Compose from reference images Use ordered product, subject, style, or scene references to guide a new image, then check what carried through. ## Inputs and outputs | Input or output | Type | Formats | Specifications | | --- | --- | --- | --- | | Input | Text — Written image brief | — | — | | Input | Image — Reference images or a base image to edit (optional) | JPG, PNG, WEBP | up to 4 images per request | | Output | Image — Generated or edited images | PNG | up to 4 images per request; 1K, 2K, 4K | | Output | Video — Short clip that starts from a generated image (optional) | MP4 | — | Specifications last checked 2026-11-09 · Sources: [Model catalog](https://docs.beatra.cn/en/docs/models) · [Documentation](https://docs.beatra.cn/en/docs/mcp-tools) · [Terms of Service](https://www.beatra.cn/en/terms) Install tested 2026-11-09 in Claude Code, Codex, Gemini CLI, GitHub Copilot CLI, Grok CLI, and Antigravity CLI. [All results](https://www.beatra.cn/en/compatibility) ## Questions ### What can AI Image Generation Studio make? It can create product images, ad creative, brand visuals, posters, social graphics, illustrations, concept art, photo variations, and background changes from text, references, or an existing base image. ### Can it use my own photos or product images? Yes. One to four supplied images can guide a new composition, or the first supplied image can remain the base for an edit. ### Can it change only part of an image? Yes. A focused edit changes only a defined area of an existing base image. ### Which image models does it use? It matches the image goal, reference materials, canvas, output count, and creative controls with current models, and keeps a named model when it fits those inputs. ### How is a series made to match? Every image in the series reuses the same direction, wording, reference images, subject cues, style, logo placement, and text plan. ## Related Skills - [AI Image Realism & Artifact Fixer](https://www.beatra.cn/en/skills/ai-image-realism): Diagnose the most visible artificial detail, repair it with a focused pass, and keep the accepted subject, product, layout, and surrounding image recognizable where possible. - [AI Logo Maker](https://www.beatra.cn/en/skills/ai-logo-maker): Start from a brand name and industry cue, transform sketches and brand assets, or refine an accepted draft—with precise brand colors and favicon-ready composition. - [AI Photo Cleanup Studio](https://www.beatra.cn/en/skills/ai-photo-cleanup-studio): Remove what you do not want, and see the result before you post it. - [AI Photo Restyler](https://www.beatra.cn/en/skills/ai-photo-restyler): Turn a selfie, portrait, or pet photo into anime, cartoon, comic, or clay art that still looks like the original subject. [More Image design Skills](https://www.beatra.cn/en/skills/categories/image-design)